Capture Workflows
Use GovTribe MCP capture prompt templates to qualify opportunities, find incumbents, compare bidders, match past performance, and plan buyer expansion.
Use these prompts when the output should help you decide what to pursue, how to pursue it, or how to improve capture position.
Relevant Opportunities
Use this prompt when you want a focused list of open opportunities that match a company, product, capability, customer, location, certification, or market lane.
Relevant Opportunities: Find open opportunities that match a specific company, product, or capability.
# Relevant Opportunities
## User Input
- **Target profile:** [Company, product, capability, website, or offering description]
## Goal
Use GovTribe MCP tools to identify the open federal contract or grant opportunities most relevant to a target company, solution, or capability profile.
Prioritize opportunities the target is plausibly positioned to pursue, then rank them with grounded evidence, explicit caveats, and clear confidence.
## Required Input
The user must provide a target company, solution, or capability profile before analysis begins.
Accept any of the following:
- Company name
- GovTribe link
- Company website
- Capability statement, one-pager, or other uploaded material
- Plain-language description of the company’s offerings
Optional constraints the user may provide:
- Agencies or customers of interest
- Geographic scope
- NAICS, PSC, or other classifications
- Contract type, funding instrument, or vehicle preferences
- Set-aside or eligibility preferences
- Due date window
- Incumbent or recompete preference
- Clearances, certifications, or deployment requirements
Input rules:
- If the target profile resolves cleanly, proceed immediately.
- If the target is too vague to search well, ask for the minimum missing detail needed to proceed.
- Do not guess the target or silently broaden it into a generic market scan.
- Do not start substantive opportunity analysis until the target profile is resolved.
## Workflow
### Steps
1. Call `Documentation` once with `collections=["govtribe-for-agents"]`, `article_names=["Choose a search mode and write queries", "Manage search context", "Date filtering", "Location filtering", "Filter by related records and hierarchies", "Aggregations and leaderboards", "Find similar records", "Vector-store content retrieval", "Troubleshoot search results"]`, and `max_tokens=16000` before any other GovTribe tool.
- Treat the returned guide articles as binding for search behavior, query construction, date and location handling, relationship filters, aggregation-first narrowing, similar-record retrieval, vector-store retrieval, and troubleshooting used in this workflow.
- Use the selected tool schema as the source of truth for tool-specific arguments, available fields, filters, sorts, aggregation keys, and response shapes.
2. Resolve the target company, solution, or capability profile and extract the strongest reusable signals.
- Use `Search_Vendors` when the input is a company name, GovTribe link, or otherwise appears to map to a vendor record.
- For exact company names or identifiers, use a double quoted `"query"`.
- Request the fields needed to interpret the target, including identifiers, business types, certifications, classifications, parent-child context, descriptions or summaries, and linked award context when needed.
- Capture as many of these signals as possible: company name, core offerings, product versus services versus software versus R&D profile, customer or mission alignment, NAICS, PSC, certifications, set-aside status, geography, likely value band, technical keywords, and recent relevant awards when they materially sharpen fit.
- If the user supplied only a website URL, treat website content as usable only when that content is already present in user-provided context or available through an allowed file workflow.
3. Review text evidence in addition to structured fields.
- Use `Search_User_Files` for uploaded capability statements, one-pagers, and other user-provided files.
- Request `fields_to_return` such as `name`, `description`, `content_snippet`, `download_url`, and `govtribe_ai_summary` when file evidence is needed.
- If `content_snippet` is insufficient, use `Add_To_Vector_Store`, then `Search_Vector_Store`.
- Keep the strongest technical phrases, mission language, and delivery-model clues for later `query` construction.
4. Resolve filter IDs before broad opportunity retrieval when the user supplied structured constraints.
- Use `Search_Federal_Agencies` for `federal_agency_ids`.
- Use `Search_Naics_Categories` for `naics_category_ids`.
- Use `Search_Psc_Categories` for `psc_category_ids`.
- Use `Search_Federal_Grant_Programs` for `federal_grant_program_ids`.
5. Run an aggregation-first market-sizing and narrowing pass when the initial scoped market is broad or when concentration checks will improve the answer.
- Use `per_page: 0` when filters define the cohort.
- Contract path:
- Use `Search_Federal_Contract_Opportunities`.
- Apply concrete filters such as `federal_agency_ids`, `naics_category_ids`, `psc_category_ids`, `set_aside_types`, `place_of_performance_ids`, `due_date_range`, and `opportunity_types`.
- Use `aggregations` such as `top_federal_agencies_by_doc_count`, `top_set_aside_types_by_doc_count`, `top_locations_by_doc_count`, `top_naics_codes_by_doc_count`, and `top_psc_codes_by_doc_count`.
- Grant path:
- Use `Search_Federal_Grant_Opportunities`.
- Apply concrete filters such as `federal_agency_ids`, `federal_grant_program_ids`, `funding_instrument_types`, `funding_activity_categories`, `due_date_range`, and `opportunity_types`.
- Use `aggregations` such as `top_federal_agencies_by_doc_count`, `top_federal_grant_programs_by_doc_count`, and `top_points_of_contact_by_doc_count` when outreach density or filing complexity materially affects the answer.
- Use the aggregation results to estimate market size, describe whether the scoped market is concentrated or fragmented, and tighten filters before row-by-row review when the cohort is still too broad.
6. Run a keyword and structured-filter opportunity retrieval pass before semantic expansion.
- Do not proceed to Step 7 until you have retrieved and reviewed row-level results from the Step 5 cohort.
- If the Step 5 cohort is 200 results or fewer, paginate through the full cohort before any semantic pass.
- Contract path:
- Use `Search_Federal_Contract_Opportunities`.
- Request `fields_to_return` explicitly, including `govtribe_id`, `govtribe_url`, `name`, `solicitation_number`, `opportunity_type`, `opportunity_state`, `part_of_mas`, `descriptions`, `govtribe_ai_summary`, `federal_agency`, `naics_category`, `psc_category`, `set_aside_type`, `federal_contract_vehicle`, `place_of_performance`, `posted_date`, `due_date`, `government_files`, and `points_of_contact`.
- Grant path:
- Use `Search_Federal_Grant_Opportunities`.
- Request `fields_to_return` explicitly, including `govtribe_id`, `govtribe_url`, `name`, `solicitation_number`, `description`, `govtribe_ai_summary`, `federal_agency`, `federal_grant_programs`, `award_ceiling`, `award_floor`, `funding_instruments`, `applicant_types`, `funding_activity_categories`, `posted_date`, `due_date`, `forecast_posting_date`, `forecast_due_date`, `government_files`, and `points_of_contact`.
- If the user requested only open or active results, make that an explicit filter decision rather than a loose interpretation.
7. Broaden only after the keyword and filter-first pass.
- Semantic search is a broadening pass only. It must not replace the Step 6 keyword and structured-filter row retrieval pass.
- If the initial opportunity cohort is thin or repetitive and at least one strong kept opportunity already exists from Step 6, you may run one seeded similarity pass before broader semantic expansion.
- Contract path: use `Search_Federal_Contract_Opportunities` with `similar_filter` from the strongest kept contract opportunity and keep the strongest agency, NAICS, PSC, set-aside, due-date, and eligibility filters in place.
- Grant path: use `Search_Federal_Grant_Opportunities` with `similar_filter` from the strongest kept grant opportunity and keep the strongest agency, program, instrument, due-date, and eligibility filters in place.
- Do not pair this branch with a broad semantic `query` in the same call unless one narrow clarifying phrase is needed.
- Use the same opportunity search tool with `search_mode: "semantic"` and a concise plain-language `query` built from the resolved capability profile, delivery model, mission language, and domain synonyms.
- Keep the strongest structured filters in place while broadening.
- Use `_score`-based `sort` for semantic passes.
- Use `per_page` and follow-up calls as needed. Do not stop because the first page contains plausible matches.
8. Compare each candidate opportunity to the target and keep only meaningfully relevant opportunities.
- Evaluate direct scope fit, mission or customer fit, delivery-model fit, classification overlap, contract type or funding instrument fit, eligibility fit, geography, due-date practicality, and alignment between the target profile and opportunity `descriptions` or `description` plus `govtribe_ai_summary`.
- Exclude opportunities that are too broad, too generic, too far outside the target’s delivery model, or supported only by weak keyword overlap.
9. Add validation branches only when they materially improve the answer.
- Use `Search_Federal_Contract_Awards` when incumbent, recompete, or prior contract-delivery evidence matters.
- Use `Search_Federal_Grant_Awards` when grant-history validation materially improves a grant ranking.
- For cohort-level validation, you may run an aggregation-only pass with `per_page: 0` and the same structural filters to confirm the refined market shape.
10. Rank the remaining opportunities using the fit labels below. Base the ranking on evidence, not intuition.
11. Perform a verification pass on the top-ranked opportunities.
- Remove weak, edge-case, or low-similarity matches and check whether the ordering still holds.
- Re-run the final filtered cohort rather than trusting the first page.
- Use additional pagination or a repeat aggregation check when needed to confirm coverage.
- If the ranking changes materially after cleanup, lower confidence and explain why.
### Fit Labels
- **Very High**: Strong direct fit to the target’s offering and customer mission, with no obvious eligibility or delivery-model mismatch.
- **High**: Clear relevance with multiple supporting signals, but not as direct as the strongest matches.
- **Medium**: Plausible and potentially worth watching, but one or more meaningful gaps remain.
- **Low**: Only partial or adjacent fit. Plausible, but weakly supported.
- **Exclude**: Clear mismatch in scope, customer, eligibility, delivery model, geography, timing, or textual evidence.
Scoring factors:
- Direct fit to the target’s core offering
- Alignment with the target’s delivery model
- Same or very similar customer mission
- Same or adjacent NAICS, PSC, or grant-program pattern
- Similar technical requirements
- Similar contract type, funding instrument, or vehicle pattern
- Eligibility fit, including set-aside or applicant-type alignment
- Geographic and operational fit
- Realistic pursuit timing based on due date and stage
- Consistency between the target profile and opportunity text or summary evidence
Ranking rules:
- Do not rank an opportunity above **Medium** unless there is strong direct scope fit and at least one additional supporting signal such as the same agency, same classification, same contract type, same operational environment, or strong text alignment.
- Do not include opportunities based mostly on keyword overlap.
## Output Format
Return the answer in this order:
1. **Target Profile Summary**
- Briefly summarize how the target company, solution, or capability profile was interpreted.
2. **Search Approach**
- Briefly explain which `Search_*` tools, filters, and parameters were most important.
- Briefly explain how the aggregation-first pass, keyword and filter-first row pass, and semantic pass were used.
3. **Market Slice Summary**
- Start with a compact markdown table summarizing the dominant agencies, programs, classifications, set-aside patterns, or other market-shape signals in the scoped cohort.
- Briefly summarize whether the scoped market looked concentrated or fragmented.
- If concentration or distribution is central to the answer, you may add one small Mermaid `pie` or `xychart-beta` chart.
- Add the chart only when it materially improves interpretation, include a short explanation, and fall back to the compact table if the data is sparse or Mermaid is unavailable.
4. **Top Relevant Open Opportunities**
- Present this section as a compact markdown table first.
- Recommended columns: `Rank`, `Opportunity`, `Agency`, `Due Date`, `Fit`, `Why It Matters`.
- Keep the table compact and move overflow detail into short notes immediately below the table when needed.
5. **Why Others Were Excluded**
- Briefly note close-but-rejected or weak-fit opportunities.
6. **Overall Confidence**
- State overall confidence in the ranking and explain why.
## Citation Rules
- Only cite sources retrieved in the current workflow.
- Never fabricate citations, URLs, IDs, or quote spans.
- Use exactly the citation format required by the host application.
- Attach citations to the specific claims they support, not only at the end.
## Grounding Rules
- Base claims only on provided context or GovTribe MCP tool outputs.
- If sources conflict, state the conflict explicitly and attribute each side.
- If the context is insufficient or irrelevant, narrow the answer or state that the goal cannot be fully completed from the available evidence.
- If a statement is an inference rather than a directly supported fact, label it as an inference.Find Incumbent for a Federal Contract Opportunity
Use this prompt when you need the strongest defensible incumbent read for a specific federal opportunity.
Find Incumbent for a Federal Contract Opportunity: Resolve a specific federal contract opportunity and determine the confirmed or most likely incumbent.
# Find Incumbent for a Federal Contract Opportunity
## User Input
- **Target opportunity:** [Solicitation number, GovTribe link, or opportunity title plus agency]
## Goal
Use GovTribe MCP tools to determine the confirmed incumbent for a specific federal contract opportunity when the opportunity thread exposes direct evidence and, if it does not, recover the most defensible current child order or award before resorting to broader predecessor evidence and tightly constrained fallback evidence.
## Required Input
The user must provide a specific target opportunity before analysis begins.
Accept any of the following:
- Solicitation number
- GovTribe link
- Opportunity title plus agency
- Plain-language description only if it is specific enough to resolve a single opportunity
Input rules:
- If the input resolves cleanly to one opportunity, proceed immediately.
- If the input is too vague to resolve a single opportunity, ask for the minimum missing detail needed to proceed.
- If no direct incumbent can be confirmed, continue to current child-order recovery, then broader predecessor recovery, and only then to the likely-incumbent fallback.
- Include vehicle, IDV, or opportunity-thread context only when it materially clarifies the incumbent determination.
- Do not guess the target.
- Do not start substantive analysis until the target is resolved.
## Workflow
### Steps
1. Call `Documentation` once with `collections=["govtribe-for-agents"]`, `article_names=["Choose a search mode and write queries", "Manage search context", "Date filtering", "Filter by related records and hierarchies", "Aggregations and leaderboards", "Find similar records", "Troubleshoot search results"]`, and `max_tokens=14000`.
- Treat the returned guide articles as binding for search behavior, query construction, date filtering, relationship filters, aggregation verification, similar-record fallback, search-context management, and troubleshooting used in this workflow.
- Use the selected tool schema as the source of truth for tool-specific arguments, available fields, relationship fields, filters, sorts, aggregation keys, and response shapes.
2. Resolve the target opportunity exactly with `Search_Federal_Contract_Opportunities`.
- Favor exact lookup first.
- For exact solicitation numbers, quoted titles, or exact GovTribe-derived identifiers, use a double quoted `"query"`.
- If the user provides a GovTribe link, use the record identity embedded in the link when possible; otherwise resolve it through exact quoted lookup.
- If the user provides an opportunity title plus agency, use the strongest exact title phrase plus agency context, then disambiguate with returned fields.
- Use `fields_to_return` explicitly.
- At minimum request:
- `govtribe_id`, `govtribe_url`, `govtribe_type`, `solicitation_number`, `name`, `opportunity_type`, `opportunity_state`, `part_of_mas`, `posted_date`, `due_date`, `set_aside_type`, `descriptions`, `govtribe_ai_summary`, `federal_meta_opportunity_id`, `federal_contract_vehicle`, `federal_agency`, `place_of_performance`, `naics_category`, `psc_category`, `federal_contract_awards`, `federal_contract_idvs`, `points_of_contact`
3. If multiple opportunities match, disambiguate with the minimum additional evidence needed.
- Compare agency, opportunity type, posted date, due date, set-aside, NAICS, PSC, and vehicle context.
- Do not merge multiple possible matches into one narrative.
- If the record still cannot be resolved to a single opportunity, stop and ask for one clarifying detail.
4. Run Tier 1 direct incumbent discovery before any fallback search.
- Use direct dataset linkage first.
- If the resolved opportunity has `federal_meta_opportunity_id`, query `Search_Federal_Contract_Awards` with `federal_meta_opportunity_ids`.
- If the resolved opportunity already exposes direct linked-award relationships, use those linked awards as the primary thread evidence.
- For direct-link searches, request explicit row fields needed to interpret incumbent ownership and thread context:
- `govtribe_id`, `govtribe_url`, `name`, `contract_number`, `award_date`, `completion_date`, `ultimate_completion_date`, `contract_type`, `descriptions`, `govtribe_ai_summary`, `dollars_obligated`, `ceiling_value`, `set_aside_type`, `awardee`, `parent_of_awardee`, `federal_contract_idv`, `federal_contract_vehicle`, `contracting_federal_agency`, `funding_federal_agency`, `naics_category`, `psc_category`, `place_of_performance`, `originating_federal_meta_opportunity_id`, `originating_federal_contract_opportunity`
- Use the label `Confirmed Incumbent` only when the evidence supports current or thread-direct incumbent ownership and the linked award or order is current or recent exact-scope work.
- If direct linked evidence is exact-scope but clearly older historical work rather than the current or most recent order, treat it as supporting predecessor evidence rather than `Confirmed Incumbent`.
- If multiple directly linked award rows are returned and performer concentration matters, add a narrow aggregation-only verification pass:
- Use `Search_Federal_Contract_Awards`
- Use `per_page: 0`
- Reuse the same `federal_meta_opportunity_ids` or other direct-link award filters
- Use `aggregations` such as `dollars_obligated_stats`, `top_awardees_by_dollars_obligated`, and `top_contracting_federal_agencies_by_dollars_obligated`
- Use that aggregation branch only to distinguish a single dominant direct performer from a more distributed direct-history thread.
- If the opportunity clearly references a linked vehicle or IDV and the direct award thread is still ambiguous, run one targeted parent lookup only when it materially clarifies the incumbent thread.
- IDV path with `Search_Federal_Contract_IDVs`:
- Use the linked IDV when available, or an exact quoted contract number if that is all you have.
- Request `govtribe_id`, `govtribe_url`, `name`, `contract_number`, `award_date`, `last_date_to_order`, `contract_type`, `pricing_type`, `description`, `govtribe_ai_summary`, `ceiling_value`, `set_aside`, `solicitation_procedures`, `extent_competed`, `legislative_mandate`, `multiple_or_single_award`, `awardee`, `parent_of_awardee`, `federal_contract_vehicle`, `contracting_federal_agency`, `funding_federal_agency`, `naics_category`, `psc_category`, `place_of_performance`, `task_orders`, `blanket_purchase_agreements`, `originating_federal_meta_opportunity_id`, and `originating_federal_contract_opportunity`
- Vehicle path with `Search_Federal_Contract_Vehicles`:
- Use the linked vehicle when available, or an exact quoted vehicle name if needed.
- Request `govtribe_id`, `govtribe_url`, `name`, `award_date`, `last_date_to_order`, `contract_type`, `descriptions`, `govtribe_ai_summary`, `set_aside_type`, `shared_ceiling`, `originating_federal_meta_opportunity_id`, `originating_federal_contract_opportunity`, `federal_agency`, and `federal_contract_awards`
- If a parent lookup exposes candidate `task_orders` or `blanket_purchase_agreements`, treat them as mandatory leads for the next current child-order recovery step rather than as order-level proof by themselves.
- Do not use parent-instrument context alone to overstate incumbency when task-order ownership remains unclear or multiple awardees remain plausible.
5. Run Tier 2 current child-order incumbent recovery immediately after Tier 1 if no direct linked award confirms the incumbent.
- Use `Search_Federal_Contract_Awards` as the primary recovery surface.
- Treat missing `federal_meta_opportunity_id` linkage or other direct-thread linkage as a Tier 1 miss only, not as negative evidence against Tier 2 or Tier 3.
- Derive exact quoted office, program, site, platform, system, acronym, and scope phrases from the resolved opportunity's `descriptions` and `govtribe_ai_summary`.
- Generate normalized quoted variants for office, program, site, and platform names, including acronyms, punctuation variants, apostrophe variants, and shortened office phrasing.
- Prioritize exact quoted platform or system names and office acronyms as the first recovery terms.
- Treat quoted platform or system names and office acronyms as higher-signal than NAICS, PSC, or agency-level filters when distinguishing one office's work from another inside the same contracting agency.
- Run this tier in order:
1. Exact quoted platform or system name, office acronym, and office, program, or site terms without broadening.
2. The same quoted terms with the strongest available same contracting-agency context and, when present, same NAICS, PSC, vehicle, IDV, set-aside, or place filters.
3. One narrow semantic retry using those same office or platform terms only if the keyword sweep remains too broad or too thin.
- Do not move to Tier 3 until this office-first keyword pass and the single narrow semantic retry are exhausted.
- If a same-agency, same-office, same-functional-scope award appears inside the recent performance window, review it even when the branded site or platform name is absent from the initial row text.
- Always request the fields needed to judge current order status and lineage:
- `govtribe_id`, `govtribe_url`, `name`, `contract_number`, `award_date`, `completion_date`, `ultimate_completion_date`, `contract_type`, `descriptions`, `govtribe_ai_summary`, `dollars_obligated`, `ceiling_value`, `set_aside_type`, `awardee`, `parent_of_awardee`, `federal_contract_idv`, `federal_contract_vehicle`, `contracting_federal_agency`, `funding_federal_agency`, `naics_category`, `psc_category`, `place_of_performance`, `originating_federal_meta_opportunity_id`, `originating_federal_contract_opportunity`
- Mine `govtribe_ai_summary` and `descriptions` for exact identifiers such as contract numbers, IDV numbers, task-order numbers, child-award references, and other exact lineage hints.
- If any exact identifier is surfaced, rerun an exact quoted lookup on that identifier immediately and treat the resulting record as stronger evidence than semantic similarity.
- Use `sort` with `awardDate` descending for this sweep, then compare `ultimate_completion_date` across the returned cohort.
- Prefer the most recent exact-scope child order or award whose completion or ultimate completion timeline is nearest to the new opportunity timeline.
- When the evidence suggests the incumbent likely sits under an IDV or parent instrument, bias toward order-like awards using documented award-type filters or ranking rather than hard-coded industry phrase banks.
- If a candidate award references a `federal_contract_idv`, or if the row text, AI summary, or surfaced identifier reveals parent/child contract lineage, lineage expansion is mandatory before exclusion.
- Resolve the referenced IDV, parent instrument, or exact identifier immediately.
- If a candidate award references a `federal_contract_idv`, resolve that IDV and inspect its `task_orders` before finalizing incumbent status.
- If child orders exist, resolve them with `Search_Federal_Contract_Awards`.
- Use the child order or child award as the incumbent record and the IDV only as lineage.
- If the same vendor holds multiple overlapping or sequential exact-scope child orders or awards, treat them as reinforcing evidence of one incumbent chain rather than as competing candidates.
- Use the most current or recent exact-scope child order or award as the incumbent record.
- Treat the related overlapping or sequential order as continuation or bridge evidence that strengthens the same incumbent conclusion.
- Do not weaken same-office, exact-scope, recent or current child-order evidence merely because the new opportunity does not yet name a vehicle.
- Do not weaken same-office, same-scope, current or recent child-order evidence merely because a continuation or bridge order sits on a different vehicle.
- Use the label `Confirmed Incumbent` for a current or recent exact-scope child order or award.
- Use the label `Likely Incumbent` only when the current-period match is strong but not exact.
6. Run Tier 3 predecessor award or order recovery only if Tier 1 and Tier 2 do not confirm an incumbent.
- Extract exact office names, acronyms, branded website names, internal platform names, and 1-3 high-signal scope phrases from `descriptions` and `govtribe_ai_summary`.
- Preserve acronyms and branded names exactly as retrieved, and search multiple quoted variants when the record supplies them, including punctuation variants, apostrophe variants, and shortened office phrasing.
- Run exact quoted keyword searches before any `similar_filter` or semantic fallback.
- If a same-agency, same-office, same-functional-scope award or parent candidate is surfaced inside the recent performance window, review it even when the branded site or platform name is absent from the initial row text.
- Use `Search_Federal_Contract_Awards` as the primary predecessor-recovery surface.
- Use quoted office, site, program, and scope phrases plus the strongest available same-agency, same vehicle or IDV, set-aside, place, and recent-window filters.
- Request the same award fields used in Tier 1 so the recovered rows can be compared directly.
- Mine `govtribe_ai_summary` and `descriptions` for exact identifiers such as contract numbers, IDV numbers, task-order numbers, child-award references, and other exact lineage hints.
- If any exact identifier is surfaced, rerun an exact quoted lookup on that identifier immediately and treat the resulting record as stronger evidence than semantic similarity.
- Use `Search_Federal_Contract_IDVs` when the opportunity language, direct evidence, or recovered awards suggest a parent instrument.
- Use exact quoted office, site, program, and scope phrases or an exact quoted contract number when one is available.
- Request `govtribe_id`, `govtribe_url`, `name`, `contract_number`, `award_date`, `last_date_to_order`, `contract_type`, `pricing_type`, `description`, `govtribe_ai_summary`, `ceiling_value`, `set_aside`, `solicitation_procedures`, `extent_competed`, `legislative_mandate`, `multiple_or_single_award`, `awardee`, `parent_of_awardee`, `federal_contract_vehicle`, `contracting_federal_agency`, `funding_federal_agency`, `naics_category`, `psc_category`, `place_of_performance`, `task_orders`, `blanket_purchase_agreements`, `originating_federal_meta_opportunity_id`, and `originating_federal_contract_opportunity`
- Prioritize exact same office, program, or site-name matches over same NAICS, PSC, vehicle, or generic same-agency similarity.
- Treat same sub-agency, same office, and same website matches as a first-class recovery path even when NAICS or PSC differ.
- If a candidate IDV, parent award, or surfaced lineage reference is found, expanding that lineage is mandatory before concluding incumbent status.
- If a candidate IDV is found, inspecting its `task_orders` and `blanket_purchase_agreements` is mandatory before concluding incumbent status.
- If `task_orders` exposes candidate child award IDs or names, resolve them with `Search_Federal_Contract_Awards`.
- Prefer the child order or child award over the parent IDV as the incumbent evidence record.
- Treat older exact-scope predecessor child orders or awards as supporting predecessor evidence unless they remain current or recent enough to satisfy Tier 2.
- Use the label `Likely Incumbent` only for weaker predecessor matches that are strong but not exact.
- Do not label a parent IDV alone as the incumbent contract. When both a child order or award and a parent IDV or vehicle are found, report the child as the evidence record and the parent only as `Supporting Lineage`.
7. Normalize vendor identity only when it materially affects interpretation.
- If incumbent identity, parent-child structure, or legal-entity naming matters, use `Search_Vendors`.
- Prefer `vendor_ids` from relationships when available.
- Otherwise use an exact quoted company name.
- Request:
- `govtribe_id`, `govtribe_url`, `name`, `uei`, `dba`, `parent_or_child`, `parent`, `business_types`, `sba_certifications`, `govtribe_ai_summary`
- Use vendor normalization to clarify entity ownership, not to replace direct-link or predecessor evidence.
8. Run Tier 4 constrained likely-incumbent fallback only if Tier 1, Tier 2, and Tier 3 do not confirm an incumbent.
- Use the resolved opportunity as the seed.
- Use `similar_filter` on the resolved opportunity only when direct linkage, current child-order recovery, and predecessor recovery are exhausted.
- Keep strict structural filters in place when available:
- Same agency
- Same NAICS or PSC
- Same vehicle or IDV when available
- Same set-aside context
- A recent award window, defaulting to the last 5 years when no tighter thread timing is available
- If office, site, or program terms survive into this tier, let exact quoted office, site, or program matches outrank generic same-agency digital-services similarity.
- Use `Search_Federal_Contract_Awards` as the primary fallback surface.
- Use `_score` sorting only for this fallback tier unless a date sort materially sharpens the answer.
- Use `search_mode: "semantic"` only inside this fallback tier when the exact and filter-first fallback pass is still too thin.
- Use the label `Likely Incumbent` only for strong constrained matches.
- Do not widen into open-ended likely-bidders or general prior-performer logic.
9. Exclude weak or misleading evidence explicitly.
- Exclude awards that are only keyword-adjacent.
- Exclude same-agency work with the wrong scope.
- Exclude same sub-agency work that does not reference the same office, site, or program.
- Exclude same-vehicle work with the wrong capability lane.
- Exclude parent-only IDVs when no child order or award tied to the requirement is identified.
- Exclude entity-mismatched vendor results.
- Exclude predecessor or fallback matches that are too thin to support an incumbent claim.
10. Perform a verification pass before final ranking.
- Remove weak fallback matches, weak predecessor matches, weak current child-order matches, or weak direct-link rows that distort the thread.
- Re-check whether the top conclusion still holds.
- Collapse same-vendor overlapping or sequential exact-scope child orders into one incumbent conclusion rather than listing them as separate competing candidates.
- Before returning `No Defensible Incumbent`, perform one mandatory lineage-expansion pass over every plausible Tier 2 or Tier 3 IDV, parent-award, same-office same-functional-scope, or surfaced-identifier candidate.
- Do not return `No Defensible Incumbent` until each plausible Tier 2 or Tier 3 lineage candidate has been either expanded or explicitly rejected with a reason.
- If a direct-link aggregation pass was used, confirm the final evidence label still matches the direct cohort shape after weak rows are removed.
- If the answer depends on Tier 2 current child-order recovery rather than direct thread linkage, say so explicitly and explain why the current or recent child-order evidence supports the label.
- If the answer depends on older predecessor recovery rather than direct thread linkage or Tier 2, say so explicitly and present that evidence as supporting predecessor evidence unless it still qualifies as current or recent.
- If the answer depends only on Tier 4 fallback evidence, lower confidence explicitly.
- If only a parent IDV or vehicle could be tied to the work, say that order-level incumbency remains unconfirmed and present the parent only as `Supporting Lineage`.
- If no defensible direct, predecessor, or fallback incumbent remains, return `No Defensible Incumbent`.
- If the question becomes primarily about the underlying notice or the awarded contract rather than incumbency, recommend `Federal Contract Opportunity Deep Dive` or `Federal Contract Award Deep Dive` instead of overloading this workflow.
## Output Format
Return in this order:
1. **Resolved Target Summary**
- Briefly explain how the opportunity was resolved
2. **Direct Incumbent Evidence**
- Present this section as a compact markdown table first
- Recommended columns: `Performer`, `Evidence Label`, `Direct Record`, `Why`
- Use `Confirmed Incumbent` only when the evidence is direct, thread-grounded, and current or recent exact-scope work
- If no direct thread-grounded incumbent was confirmed, say so briefly
3. **Current Child-Order Recovery**
- Include this section only if Tier 2 was needed
- Present current child-order recovery results as a compact markdown table first
- Recommended columns: `Performer`, `Evidence Label`, `Current Order / Award`, `Supporting Lineage`, `Why`
- Use `Confirmed Incumbent` only for current or recent exact-scope child orders or awards
- Use `Likely Incumbent` only for strong current-period matches that remain slightly indirect
- If the same vendor holds overlapping or sequential exact-scope orders, use the lead current or recent order as the main record and describe the related order or orders in `Why` as reinforcing continuation or bridge evidence
- Use `Why` to state when a surfaced identifier or expanded child-order chain materially drove the conclusion
- If no defensible current child-order evidence remains, say so briefly
4. **Recovered Predecessor Evidence**
- Include this section only if Tier 3 was needed
- Present recovered predecessor results as a compact markdown table first
- Recommended columns: `Performer`, `Evidence Label`, `Recovered Record`, `Supporting Lineage`, `Why`
- Use `Supporting Predecessor Evidence` for older exact-scope same-office, same-program, or same-site work that helps explain lineage but is not current enough to be `Confirmed Incumbent`
- Keep older exact-scope same-vendor orders here unless they are current or recent enough to belong in Tier 2
- Use `Likely Incumbent` only for weaker predecessor matches that remain strong but not exact
- Use `Why` to state when a surfaced identifier or expanded child-order chain materially drove the conclusion
- If no defensible predecessor evidence remains, say so briefly
5. **Supporting Lineage**
- Use this section for parent IDVs, vehicles, and thread lineage that materially support the incumbent determination
- Use the label `Supporting Lineage` for parent IDVs or vehicles
- Never center this section as the incumbent record when a child order or award exists
- Do not place bridge, continuation, or other child-order evidence in this section
- If only parent lineage was confirmed, say that order-level incumbency remains unconfirmed
6. **Likely Incumbent Fallback**
- Include fallback results only if Tier 1, Tier 2, and Tier 3 did not confirm an incumbent
- Present fallback results as a compact markdown table first
- Recommended columns: `Performer`, `Evidence Label`, `Closest Record`, `Why`
- Use `Likely Incumbent` only for strong constrained fallback matches
- If no defensible fallback remains, say `No Defensible Incumbent`
7. **Why Others Were Excluded**
- Briefly note weak, mismatched, or insufficiently supported candidates that were rejected
8. **Risks, Gaps, or Unknowns**
- Briefly note missing linkage, ambiguity, sparse history, or other data limits
9. **Overall Confidence**
- State overall confidence and why
## Citation Rules
- Only cite sources retrieved in the current workflow.
- Never fabricate citations, URLs, IDs, or quote spans.
- Use exactly the citation format required by the host application.
- Attach citations to the specific claims they support, not only at the end.
## Grounding Rules
- Base claims only on provided context or GovTribe MCP tool outputs.
- If sources conflict, state the conflict explicitly and attribute each side.
- If the context is insufficient or irrelevant, narrow the answer or state that the goal cannot be fully completed from the available evidence.
- If a statement is an inference rather than a directly supported fact, label it as an inference.Likely Bidders
Use this prompt when you need a realistic competitive field for a target opportunity.
Likely Bidders: Identify who is most likely to bid on a specific opportunity.
# Likely Bidders
## User Input
- **Target opportunity:** [Solicitation number, GovTribe link, title plus agency, or opportunity description]
## Goal
Use GovTribe MCP tools to identify the vendors most likely to bid on a target federal or state and local contract opportunity, or the organizations most likely to receive a target federal grant opportunity.
Use prior awards as the primary pivot for identifying likely bidders or likely recipients, then rank candidates with grounded evidence, explicit caveats, and clear confidence.
## Required Input
The user must provide a target opportunity before analysis begins.
Accept any of the following:
- Solicitation number
- GovTribe link
- Title plus agency
- Plain-language description only if it resolves to a single target without ambiguity
Input rules:
- If the input resolves cleanly to one opportunity, proceed immediately.
- If the input is too vague to resolve to one opportunity, ask for the minimum missing detail required to proceed.
- Do not guess the target.
- Do not start substantive analysis until the target is resolved.
## Workflow
### Steps
1. Call `Documentation` once with `collections=["govtribe-for-agents"]`, `article_names=["Choose a search mode and write queries", "Manage search context", "Date filtering", "Location filtering", "Filter by related records and hierarchies", "Aggregations and leaderboards", "Find similar records", "Vector-store content retrieval", "Troubleshoot search results"]`, and `max_tokens=16000` before any other GovTribe tool.
- Treat the returned guide articles as binding for search behavior, query construction, date and location handling, relationship filters, aggregation-first review, similar-record retrieval, vector-store retrieval, and troubleshooting used in this workflow.
- Use the selected tool schema as the source of truth for tool-specific arguments, available fields, filters, sorts, aggregation keys, and response shapes.
2. Resolve the target opportunity to a single GovTribe record.
- Use `Search_Federal_Contract_Opportunities` for federal contracts, `Search_Federal_Grant_Opportunities` for grants, and `Search_State_And_Local_Contract_Opportunities` for state and local contracts.
- For exact identifiers, titles or quoted phrases, use a double quoted `"query"`.
- Request the fields needed to interpret the target, including identifiers, summary text, relevant classifications or taxonomies, agency or jurisdiction context, timing, place of performance when available, and supporting files when available.
- Resolve reusable IDs before deeper search when needed:
- `Search_Federal_Agencies` for `federal_agency_ids`
- `Search_Naics_Categories` for `naics_category_ids`
- `Search_Psc_Categories` for `psc_category_ids`
- `Search_Federal_Grant_Programs` for `federal_grant_program_ids`
- `Search_States` for `state_ids`
- `Search_Jurisdictions` for `jurisdiction_ids`
- `Search_Nigp_Categories` for `nigp_category_ids`
- `Search_Unspsc_Categories` for `unspsc_category_ids`
3. Extract the strongest structured signals from the resolved target, such as title, agency, office, description, NAICS, PSC, grant program, state, jurisdiction, NIGP, UNSPSC, set-aside or eligibility constraints, vehicle or instrument type, value band, place of performance, and due-date context.
4. Run a filter-first award matching pass before semantic broadening.
- Contract path:
- If the resolved opportunity has `federal_meta_opportunity_id`, start with `Search_Federal_Contract_Awards` using `federal_meta_opportunity_ids`.
- Then add the strongest available agency, NAICS, PSC, set-aside, vehicle, date, and value filters.
- If `federal_meta_opportunity_id` is absent or the direct comparable-award cohort is still thin, you may run one fallback pass using `Search_Federal_Contract_Awards` with `similar_filter` from the resolved federal contract opportunity.
- Keep the strongest same-agency, NAICS, PSC, set-aside, vehicle, and recent-award filters in place. Do not combine this fallback with a broad semantic `query` in the same call unless one narrow clarifying phrase is needed.
- Grant path:
- Start with `Search_Federal_Grant_Awards` using the strongest available grant-program, agency, assistance-type, date, value, and place-of-performance filters.
- If the direct comparable-award cohort is still thin, you may run one fallback pass using `Search_Federal_Grant_Awards` with `similar_filter` from the resolved federal grant opportunity.
- Keep the strongest program, agency, assistance-type, date, value, and place-of-performance filters in place. Do not combine this fallback with a broad semantic `query` in the same call unless one narrow clarifying phrase is needed.
- State and local path:
- Start with `Search_State_And_Local_Contract_Awards` using the most precise first-pass `query` you can build from the resolved opportunity title, exact identifiers, and scoped description phrases.
- Add `state_ids` and `contact_ids` when the resolved opportunity provides strong state or contact signals.
- Prefer quoted phrases from the opportunity title or scope language over broad paraphrases on the first pass.
- If the initial award cohort is thin or noisy, run one peer-opportunity similarity pass with `Search_State_And_Local_Contract_Opportunities` using `similar_filter` from the resolved state and local opportunity.
- Keep the same state, jurisdiction, NIGP, UNSPSC, due-date, and topic signals in place, and use the returned similar opportunities only to tighten the later award query rather than as bidder evidence by themselves.
- Do not rely on keywords alone when structured bridges are available.
5. Run an aggregation-only pass on the comparable-award cohort before full ranking.
- Use the same structural filters that define the comparable cohort.
- Use `per_page: 0`.
- Use awardee, agency, program, vehicle, NAICS, PSC, location, and dollars-obligated aggregations as appropriate to measure concentration and determine whether the market is incumbent-dominated, moderately concentrated, or fragmented.
- State and local award aggregation path:
- Use `Search_State_And_Local_Contract_Awards`
- Use `aggregations` such as `dollars_obligated_stats`, `top_contract_entities_by_dollars_obligated`, `top_nigp_codes_by_dollars_obligated`, `top_unspsc_codes_by_dollars_obligated`, and `top_states_by_dollars_obligated`
- When historical state and local award coverage is thin, you may add an opportunity aggregation pass with `Search_State_And_Local_Contract_Opportunities` using `top_states_by_doc_count`, `top_jurisdictions_by_doc_count`, `top_unspsc_codes_by_doc_count`, and `top_nigp_codes_by_doc_count` to understand the active-solicitation market shape before final ranking.
6. Broaden only after the keyword and aggregation passes.
- If a `similar_filter` branch already recovered enough comparable records, skip generic semantic broadening.
- Use the same award search tool with `search_mode: "semantic"` and a concise plain-language `query`.
- Keep the strongest structured filters in place while broadening.
- Use semantic broadening to capture near-neighbor work, not to replace the comparable-award cohort.
- For state and local work, use `Search_State_And_Local_Contract_Opportunities` for semantic peer-opportunity discovery only when active-solicitation language is needed to improve the award search, not as a substitute for historical bidder evidence.
7. Use text evidence as part of similarity scoring.
- For contracts, inspect both `descriptions` and `govtribe_ai_summary`.
- For grants, inspect both `description` and `govtribe_ai_summary`.
- For state and local work, inspect the opportunity `description`, award `description`, `govtribe_ai_summary`, and `line_items` when available.
- If supporting file content materially improves the analysis, use `Search_Government_Files`.
- If snippets are insufficient, use `Add_To_Vector_Store`, then `Search_Vector_Store`.
8. Compare each candidate award to the target and keep only meaningfully similar awards.
- Evaluate scope overlap, agency or customer overlap, state or jurisdiction overlap, classification or taxonomy overlap, contract type or assistance-type overlap, vehicle or instrument overlap, eligibility overlap, value-band similarity, recency, and alignment between the target text and award text.
- Exclude awards that are only keyword-adjacent or otherwise poor fits.
9. Normalize the surviving awardees with `Search_Vendors` when vendor identity, parent-child relationships, or entity consolidation matters to the ranking and the awardee appears to map cleanly to a GovTribe vendor record.
10. Rank the likely bidders or recipients using the labels below. Base the ranking on retrieved evidence, not intuition.
11. Perform a verification pass on the top candidates.
- Remove weak, edge-case, or low-similarity awards and check whether the ordering still holds.
- Re-run at least one aggregation check on the cleaned cohort using the same structural filters.
- If the leaderboard shifts materially after weak matches are removed, lower confidence and explain why.
### Likelihood Labels
- **Very High**: Incumbent or repeated winner on highly similar work for the same or very similar customer, with no obvious eligibility issue.
- **High**: Multiple strong comparable awards with clear scope and customer overlap.
- **Medium**: Some relevant comparable work, but one or more meaningful gaps remain.
- **Low**: Only adjacent or partial overlap. Plausible, but weakly supported.
- **Exclude**: Clear mismatch in scope, customer, eligibility, award type, or textual evidence.
Scoring factors:
- Direct scope overlap with the target
- Repeated wins on highly similar awards
- Same agency, office, or buying organization
- Same NAICS, PSC, grant-program, assistance-type, or instrument pattern
- Same contract vehicle or acquisition pattern
- Similar dollar range
- Recent relevant activity
- Eligibility fit, including set-aside or recipient type
- Consistency between the target and award descriptions or summaries
Ranking rules:
- Do not rank a candidate above **Medium** unless there is at least one award with strong scope overlap and at least one additional supporting signal such as the same agency, same classification, same vehicle or assistance type, repeat performance, or strong text alignment.
- Do not infer that a vendor is likely to bid or that an organization is likely to receive the award if the evidence is thin or mostly keyword-based.
## Output Format
Return the answer in this order:
1. **Target Opportunity Summary**
- Briefly summarize how the target opportunity was interpreted.
2. **Search Approach**
- Briefly explain which `Search_*` tools, filters, and parameters were most important.
- Briefly explain how the keyword pass, aggregation pass, and semantic pass were used.
3. **Comparable Market Summary**
- Start with a compact markdown table summarizing the dominant awardees, customer concentration, vehicle, program, or taxonomy signals, and overall market shape.
- Briefly summarize whether the cohort looked highly concentrated, moderately concentrated, or fragmented.
- If awardee concentration is central to the answer, you may add one small Mermaid `pie` chart.
- Add the chart only when it materially improves interpretation, include a short explanation, and fall back to the compact table if the cohort is small or Mermaid is unavailable.
4. **Likely Bidders or Recipients**
- Present this section as a compact markdown table first.
- Recommended columns: `Rank`, `Vendor`, `Likelihood`, `Why`, `Key Evidence`, `Caveats`.
- Keep the table compact and move overflow detail into short notes immediately below the table when needed.
5. **Why Others Were Excluded**
- Briefly note close-but-rejected candidates or weak matches.
6. **Overall Confidence**
- State overall confidence in the ranking and explain why.
## Citation Rules
- Only cite sources retrieved in the current workflow.
- Never fabricate citations, URLs, IDs, or quote spans.
- Use exactly the citation format required by the host application.
- Attach citations to the specific claims they support, not only at the end.
## Grounding Rules
- Base claims only on provided context or GovTribe MCP tool outputs.
- If sources conflict, state the conflict explicitly and attribute each side.
- If the context is insufficient or irrelevant, narrow the answer or state that the goal cannot be fully completed from the available evidence.
- If a statement is an inference rather than a directly supported fact, label it as an inference.Past Performance Match
Use this prompt when a company needs to know whether its record supports a target opportunity, requirement, grant, buyer, or statement of work.
Past Performance Match: Assess whether a specific company’s past performance truly supports a target opportunity.
# Past Performance Match
## User Input
- **Target company:** [Company name, UEI, CAGE, GovTribe link, or company description]
- **Target requirement:** [Solicitation number, GovTribe link, opportunity title plus agency, uploaded SOW/PWS/RFI, or work description]
## Goal
Use GovTribe MCP tools to determine **how well a target company’s past performance aligns to a specific federal contract or grant opportunity, solicitation, requirement, or statement of work**.
Identify the strongest defensible past performance references, map them to the requirement, and explain the most important gaps or risks.
## Required Input
The user must provide both of the following before analysis begins:
1. A **target company**
2. A **target opportunity or requirement**
Accept any of the following for the target company:
- Company name
- UEI
- CAGE
- GovTribe link
- Plain-language description of the company
Accept any of the following for the target opportunity or requirement:
- Solicitation number
- GovTribe link
- Opportunity title plus agency
- Uploaded solicitation, SOW, PWS, RFI, or requirement text
- Plain-language description of the work
Input rules:
- If either the company or the target requirement is too vague, ask for the minimum missing detail needed to proceed.
- Do not guess the company, the requirement, or the applicable procurement lane.
- Do not start substantive analysis until both sides are resolved well enough to search.
## Workflow
### Steps
1. Call `Documentation` once with `collections=["govtribe-for-agents"]`, `article_names=["Choose a search mode and write queries", "Manage search context", "Date filtering", "Location filtering", "Filter by related records and hierarchies", "Aggregations and leaderboards", "Find similar records", "Vector-store content retrieval", "Troubleshoot search results"]`, and `max_tokens=16000`.
- Treat the returned guide articles as binding for search behavior, query construction, date and location handling, structural relationship filters, aggregation-first review, similar-record retrieval, vector-store retrieval, and troubleshooting used in this workflow.
- Use the selected tool schema as the source of truth for tool-specific arguments, available fields, filters, sorts, aggregation keys, and response shapes.
2. Resolve the target company and normalize identity where possible.
- Use `Search_Vendors` when the input is a company name, GovTribe link, UEI, or other known vendor identity.
- For exact names or identifiers, use a double quoted `"query"`.
- Use `vendor_ids` when a GovTribe vendor ID or UEI is already known.
- Request at least `govtribe_id`, `govtribe_url`, `name`, `uei`, `dba`, `business_types`, `sba_certifications`, `parent_or_child`, `parent`, `naics_category`, and `govtribe_ai_summary`.
- Capture the resolved vendor identity for reuse later through `vendor_ids`.
- Normalize the legal name, common name or DBA, UEI when available, CAGE only if it appears in retrieved evidence, and any parent or subsidiary relationships that materially affect interpretation.
3. If the target can be resolved through GovTribe opportunity or program records, resolve the target opportunity or requirement and branch early to contract, grant, or file-first handling.
- First determine whether the target is a contract opportunity, a grant opportunity, or a file-first requirement that does not resolve cleanly to a GovTribe opportunity record.
- Contract path:
- Use `Search_Federal_Contract_Opportunities`.
- For exact solicitation numbers, or quoted titles, use a double quoted `"query"`.
- Request at least `govtribe_id`, `govtribe_type`, `govtribe_url`, `solicitation_number`, `name`, `opportunity_type`, `opportunity_state`, `part_of_mas`, `descriptions`, `govtribe_ai_summary`, `federal_meta_opportunity_id`, `federal_agency`, `naics_category`, `psc_category`, `set_aside_type`, `federal_contract_vehicle`, `place_of_performance`, `posted_date`, `due_date`, `government_files`, and `points_of_contact`.
- Resolve reusable IDs before deeper search when needed:
- `Search_Federal_Agencies` -> `federal_agency_ids`
- `Search_Naics_Categories` -> `naics_category_ids`
- `Search_Psc_Categories` -> `psc_category_ids`
- Grant path:
- Use `Search_Federal_Grant_Opportunities`.
- For exact grant IDs or quoted titles, use a double quoted `"query"`.
- Request at least `govtribe_id`, `govtribe_type`, `govtribe_url`, `solicitation_number`, `name`, `description`, `govtribe_ai_summary`, `federal_agency`, `federal_grant_programs`, `award_ceiling`, `award_floor`, `funding_instruments`, `applicant_types`, `funding_activity_categories`, `place_of_performance`, `posted_date`, `due_date`, `forecast_posting_date`, `forecast_due_date`, `government_files`, and `points_of_contact`.
- If the user gives a CFDA or ALN-style identifier or a program-centric target, resolve it with `Search_Federal_Grant_Programs` first, then reuse `federal_grant_program_ids`.
- Resolve reusable IDs before deeper search when needed:
- `Search_Federal_Agencies` -> `federal_agency_ids`
- `Search_Federal_Grant_Programs` -> `federal_grant_program_ids`
- File-first requirement path:
- If the target is primarily an uploaded requirement artifact and does not resolve cleanly to a GovTribe opportunity record, extract the requirement from Step 4 before constructing award searches.
- Extract as many of these attributes as possible:
- Opportunity title
- Agency, subagency, or buying office
- Scope of work
- Key tasks or required outcomes
- NAICS, PSC, CFDA, ALN, or other relevant classifications
- Contract type, vehicle, or instrument type
- Set-aside or eligibility constraints
- Estimated value or value band
- Place of performance
- Required clearances, certifications, facilities, or operational environment
- Timing or period of performance, if available
4. If uploaded or opportunity-linked requirement files exist, use requirement text and file evidence explicitly, not generically.
- For uploaded solicitation, SOW, PWS, RFI, or requirement documents, use `Search_User_Files`.
- For `Search_User_Files`, request `govtribe_id`, `govtribe_ai_summary`, `govtribe_url`, `name`, `description`, `content_snippet`, and `download_url`.
- If the resolved opportunity returns one or more `government_files`, this branch is required. Call `Search_Government_Files` with `federal_contract_opportunity_ids` or `federal_grant_opportunity_ids` before final scoring, even when the opportunity `govtribe_ai_summary` already looks detailed.
- For `Search_Government_Files`, request `govtribe_id`, `govtribe_ai_summary`, `govtribe_url`, `name`, `content_snippet`, `download_url`, `posted_date`, and `parent_record`.
- If `content_snippet` is not enough, use `Add_To_Vector_Store`, then `Search_Vector_Store`.
- Treat file chunks as supporting requirement evidence, not as a substitute for award matching.
- Keep the target’s `descriptions` or `description`, `govtribe_ai_summary`, and file-derived requirement language for later `query` construction and alignment checks.
5. If the resolved target can be matched against prime-award history, use keyword and filter-first award searches before semantic expansion.
- There is no separate structured-search tool. Use the relevant award tool with structured filters first.
- Always anchor the cohort to the resolved target company using `vendor_ids` unless the user explicitly asks for a broader comparable-market scan.
- Use `fields_to_return` explicitly because the default row payload is only `govtribe_id`.
- Contract award path with `Search_Federal_Contract_Awards`:
- If the resolved opportunity has `federal_meta_opportunity_id`, call `Search_Federal_Contract_Awards` first with `vendor_ids` and `federal_meta_opportunity_ids`.
- Then add the strongest available `contracting_federal_agency_ids`, `funding_federal_agency_ids`, `naics_category_ids`, `psc_category_ids`, `federal_contract_vehicle_ids`, `federal_contract_award_types`, `set_aside_types`, `award_date_range` for the last 24 months, `ultimate_completion_date_range`, `dollars_obligated_range`, `ceiling_value_range`, and `place_of_performance_ids`.
- Request at least `govtribe_id`, `govtribe_url`, `name`, `contract_number`, `award_date`, `completion_date`, `ultimate_completion_date`, `contract_type`, `descriptions`, `govtribe_ai_summary`, `dollars_obligated`, `ceiling_value`, `set_aside_type`, `awardee`, `parent_of_awardee`, `contracting_federal_agency`, `funding_federal_agency`, `naics_category`, `psc_category`, `federal_contract_vehicle`, `originating_federal_meta_opportunity_id`, and `originating_federal_contract_opportunity`.
- Grant award path with `Search_Federal_Grant_Awards`:
- Start with `vendor_ids` and the strongest available `federal_grant_program_ids`, `funding_federal_agency_ids`, `contracting_federal_agency_ids`, `assistance_types`, `award_date_range` for the last 24 months, `ultimate_completion_date_range`, `dollars_obligated_range`, and `place_of_performance_ids`.
- Request at least `govtribe_id`, `govtribe_url`, `name`, `grant_number`, `award_date`, `completion_date`, `ultimate_completion_date`, `dollars_obligated`, `assistance_type`, `assistance_recipient_type`, `description`, `govtribe_ai_summary`, `awardee`, `parent_of_awardee`, `funding_federal_agency`, `contracting_federal_agency`, `federal_grant_program`, and `place_of_performance`.
- Do not rely on keywords alone when resolved company IDs and opportunity-derived filters are available.
6. Broaden the search only after the keyword and filter-first pass.
- Run this branch only when the keyword and filter-first pass leaves plausible coverage gaps, vague award text, or uncertainty that semantic broadening could materially improve the answer.
- If the company-constrained comparable-award cohort is thin, vague, or obviously under-retrieved and the requirement resolved cleanly to a specific opportunity, prefer one seed-based recovery pass before generic semantic broadening.
- Contract path: use `Search_Federal_Contract_Awards` with `similar_filter` from the resolved federal contract opportunity while keeping `vendor_ids` and the strongest requirement-derived agency, classification, vehicle, set-aside, date, and value filters in place.
- Grant path: use `Search_Federal_Grant_Awards` with `similar_filter` from the resolved federal grant opportunity while keeping `vendor_ids` and the strongest program, agency, assistance-type, date, and location filters in place.
- Do not pair this branch with a broad semantic `query` in the same call unless one narrow clarifying phrase is needed.
- Only keep awards from this branch if they survive the same company and requirement screening used for the rest of the comparable cohort.
- There is no separate semantic-search tool. Use the same award search tools again with `search_mode: "semantic"`.
- Build a concise plain-language `query` from the resolved requirement, mission language, key tasks, and a few domain-aware synonyms or paraphrases.
- Keep the strongest company and requirement filters in place while broadening.
- Use `_score`-based `sort` for semantic passes.
- Use `similar_filter` only if the current tool supports it and you have a strong seed record with the correct `govtribe_type` and `govtribe_id`.
- Do not let semantic broadening override the core company constraint or the requirement-derived filter set.
- If the keyword and filter-first pass already yields a small, well-supported candidate set and no material uncertainty remains, you may skip this branch and say why.
7. Use dataset-specific text evidence during comparison.
- For contract opportunities and contract awards, inspect both `descriptions` and `govtribe_ai_summary`.
- For grant opportunities and grant awards, inspect both `description` and `govtribe_ai_summary`.
- For user-uploaded and government files, use `content_snippet` first and escalate to vector-store retrieval only when snippets are not enough.
- Do not assume every dataset exposes the same description field name.
8. Compare each candidate award to the target requirement and keep only awards that are meaningfully relevant.
- Evaluate alignment using:
- Scope and task overlap
- Agency or customer overlap
- NAICS, PSC, CFDA, ALN, or classification overlap
- Contract type, vehicle, or instrument overlap
- Set-aside or eligibility overlap
- Value band similarity
- Period of performance or recency
- Clearance, facility, certification, or environment fit
- Alignment between textual extracts, especially `descriptions` or `description` plus `govtribe_ai_summary`
- File-derived requirement evidence when it materially sharpens the comparison
9. Exclude awards that are only keyword-adjacent, too generic, too small, too different in delivery model, or otherwise not truly comparable.
10. If many candidate awards remain after the comparable cohort is built, run an aggregation pass before final scoring.
- Use this step only when the cohort is broad enough that lane-shape evidence materially improves the answer.
- Do not treat this step as mandatory when the candidate set is already small, well-understood, and unlikely to benefit from lane-shape quantification before scoring.
- For aggregation-only calls:
- Use `per_page: 0`
- Keep the same `vendor_ids` and the same structural filters that define the comparable cohort
- Omit `fields_to_return` unless rows are also needed
- Contract path with `Search_Federal_Contract_Awards`:
- Use `aggregations` such as `dollars_obligated_stats`, `top_contracting_federal_agencies_by_dollars_obligated`, `top_naics_codes_by_dollars_obligated`, and `top_psc_codes_by_dollars_obligated`.
- Grant path with `Search_Federal_Grant_Awards`:
- Use `aggregations` such as `dollars_obligated_stats`, `top_funding_federal_agencies_by_dollars_obligated`, `top_federal_grant_programs_by_dollars_obligated`, and `top_locations_by_dollars_obligated`.
- Use this pass to quantify whether the company’s relevant history is concentrated in the same agency, category, program, location, or value lane as the target, whether the candidate set is too broad or off-pattern, and whether the fit is backed by repeated activity or just a few isolated rows.
- If recency materially affects match strength, compare a recent window and a prior window using the same filters so the trend claim is grounded.
11. If no sufficiently relevant evidence remains, say so clearly and stop.
12. For the remaining awards, identify the strongest **past performance references** and map them to the target requirement.
- Distinguish which requirement areas are directly supported, partially supported, or unsupported by the available evidence.
13. Identify material gaps, such as missing capability evidence, missing customer or agency relevance, missing contract type, vehicle, or instrument relevance, missing clearance, facility, certification, or location fit, or weak scale or complexity comparability.
14. Rank the overall match strength using only these labels:
- **Very Strong**
- **Strong**
- **Moderate**
- **Weak**
- **No Credible Match**
- Score the match using:
- Direct overlap between the requirement and prior award scope
- Similarity of customer, office, or mission context
- Same or adjacent NAICS, PSC, CFDA, ALN, or category
- Same contract type, vehicle, instrument, or acquisition pattern
- Similar scale, value, and complexity
- Recent relevant performance
- Clearance, facility, certification, or environment fit
- Consistency between requirement and award `descriptions` or `description`
- Consistency between requirement and award `govtribe_ai_summary`
- Strength of file-derived requirement evidence when that evidence was needed to interpret the target
- Guidance:
- **Very Strong**: Multiple awards strongly support the target requirement with clear scope overlap and no major fit issues.
- **Strong**: Good supporting evidence exists, but one or two meaningful gaps remain.
- **Moderate**: Some relevant evidence exists, but the fit is mixed or incomplete.
- **Weak**: Only partial or adjacent support exists; the match is not well grounded.
- **No Credible Match**: The available evidence does not support a meaningful past performance claim.
- Do not rate the match above **Moderate** unless there is at least one award with strong direct scope overlap and at least one additional supporting signal such as same agency, same classification, same contract type, similar scale, or strong alignment in `descriptions`, `description`, or `govtribe_ai_summary`.
- Do not force-fit a company to a requirement based on thin evidence or broad capability language.
15. If prime-award evidence remains and verification is needed for the most important conclusions, perform a verification pass.
- Remove weak, edge-case, or low-similarity awards and check whether the conclusion still holds.
- Rerun the cleaned cohort rather than trusting the first page.
- Use `per_page` and additional pages as needed to confirm coverage.
- Run at least one aggregation or metadata pass with `per_page: 0`, the same `vendor_ids`, and the same structural filters:
- Contract path with `Search_Federal_Contract_Awards`:
- `aggregations` such as `dollars_obligated_stats`, `top_contracting_federal_agencies_by_dollars_obligated`, `top_naics_codes_by_dollars_obligated`, or `top_psc_codes_by_dollars_obligated`
- Grant path with `Search_Federal_Grant_Awards`:
- `aggregations` such as `dollars_obligated_stats`, `top_funding_federal_agencies_by_dollars_obligated`, or `top_federal_grant_programs_by_dollars_obligated`
- If the conclusion shifts materially after cleanup, lower confidence and explain why.
## Output Format
Use compact markdown tables by default for relevant-history summaries, best-fit references, and requirement-to-evidence mapping.
Use Mermaid only when a real recent-versus-prior comparison materially improves readability; otherwise stay table-first.
Return the answer in this order:
1. **Match Summary**
- Briefly summarize how the target company and target requirement were interpreted.
- State the overall match strength using one of the labels from Step 14.
2. **Search Approach**
- Briefly explain which `Search_*` tools, filters, and bridge parameters were most important.
- Briefly explain how the keyword or filter-first pass, any aggregation pass, and the semantic pass were used.
- Briefly note any file-retrieval or vector-store steps used.
3. **Relevant History Summary**
- If aggregation analysis was used, start with a compact markdown table summarizing the main lane-shape or recency signals.
- Briefly summarize how concentrated the company’s relevant history looked in the target lane.
- Mention one or two aggregation-derived signals when aggregation analysis was used.
- If the workflow actually used recent-versus-prior window comparison and that trend materially affects the conclusion, you may add one small Mermaid `xychart-beta`.
- Only add the chart when it materially improves interpretation. Include a one to two sentence explanation and fall back to the compact table if the comparison is sparse or Mermaid is unavailable.
4. **Best-Fit Past Performance References**
- Present this section as a compact markdown table first.
- Recommended columns: `Rank`, `Award`, `Agency`, `Evidence Type`, `Match Strength`, `Why It Fits`.
- Add short notes below the table only when specific evidence or caveats do not fit cleanly in the table.
5. **Requirement-to-Evidence Mapping**
- Use a mandatory markdown table.
- Recommended columns: `Requirement Area`, `Support Level`, `Best Evidence`, `Gap / Caveat`.
- Use only evidence grounded in the retrieved awards and provided requirement materials.
6. **Gaps and Risks**
- Briefly identify the most important capability, customer, scale, clearance, vehicle, instrument, or geographic gaps.
7. **Overall Confidence**
- State overall confidence in the assessment and why.
## Citation Rules
- Only cite sources retrieved in the current workflow.
- Never fabricate citations, URLs, IDs, or quote spans.
- Use exactly the citation format required by the host application.
- Attach citations to the specific claims they support, not only at the end.
## Grounding Rules
- Base claims only on provided context or GovTribe MCP tool outputs.
- If sources conflict, state the conflict explicitly and attribute each side.
- If the context is insufficient or irrelevant, narrow the answer or state that the goal cannot be fully completed from the available evidence.
- If a statement is an inference rather than a directly supported fact, label it as an inference.Federal Buyer Expansion Plan
Use this prompt when you know the company and the federal buyer office you want to expand into.
Federal Buyer Expansion Plan: Build a one-office federal buyer expansion plan for a target vendor using recent buying evidence, contacts, and ordering paths.
# Federal Buyer Expansion Plan
## User Input
- **Target vendor:** [Vendor name, UEI, CAGE, GovTribe link, or company description]
- **Target buyer office:** [Federal agency, component, office, VISN, IC, command, acronym, or GovTribe link]
## Goal
Use GovTribe MCP tools to build a grounded **one-office federal buyer expansion plan** for a specific target vendor and a specific target buyer office.
A complete answer should produce an office-specific plan with representative buys, evidence-backed contacts, ordering-path analysis, and a light micro-offer menu.
## Required Input
The user must provide both of the following before analysis begins:
1. A **target vendor**
2. A **target buyer office**
Accept any of the following for the target vendor:
- Company name
- UEI
- CAGE
- GovTribe link
- Plain-language description only if it resolves to a single vendor without ambiguity
Accept any of the following for the target buyer office:
- Federal agency, component, office, VISN, IC, or command name
- Acronym
- GovTribe link
- Plain-language description only if it resolves to a single federal agency record without ambiguity
Optional constraints the user may provide:
- Additional context that may help resolve the vendor or the buyer office cleanly
Input rules:
- If either the target vendor or target buyer office does not resolve cleanly to one entity, ask for the minimum missing detail required to proceed.
- Do not guess the vendor, the office, or the office hierarchy.
- Do not start substantive analysis until both sides are resolved well enough to search.
## Workflow
### Steps
1. Call `Documentation` once with `collections=["govtribe-for-agents"]`, `article_names=["Choose a search mode and write queries", "Manage search context", "Date filtering", "Filter by related records and hierarchies", "Aggregations and leaderboards", "Troubleshoot search results"]`, and `max_tokens=12000` before any other GovTribe tool.
- Treat the returned guide articles as binding for search behavior, query construction, date filtering, relationship filters, aggregation-first review, search-context management, and troubleshooting used in this workflow.
- Use the selected tool schema as the source of truth for tool-specific arguments, available fields, filters, sorts, aggregation keys, and response shapes.
2. Resolve the target vendor with `Search_Vendors`.
- Use a double quoted `"query"` for exact names, UEIs, CAGEs, or GovTribe links.
- Request `fields_to_return` explicitly. At minimum request `govtribe_id`, `govtribe_url`, `name`, `uei`, `dba`, `business_types`, `sba_certifications`, `parent_or_child`, `parent`, `naics_category`, and `govtribe_ai_summary`.
3. Resolve the target buyer office with `Search_Federal_Agencies`.
- Use a double quoted `"query"` for exact names or acronyms.
- Request `fields_to_return` explicitly. At minimum request `govtribe_id`, `govtribe_url`, `name`, `alternate_name`, `acronym`, and `defense_or_civilian`.
- If the office label does not resolve to one federal agency record, stop and ask for the minimum clarification needed.
4. Set the fixed planning window and derive the vendor's lane focus.
- Use the last 24 months for office buying analysis. Do not ask the user to choose a different time window in this workflow.
- Run `Search_Federal_Contract_Awards` for the resolved `vendor_ids` as an aggregation-first vendor-history pass.
- Use `per_page: 0`.
- Request aggregations that characterize the vendor's recent federal lane. At minimum use `dollars_obligated_stats`, `top_naics_codes_by_dollars_obligated`, `top_psc_codes_by_dollars_obligated`, `top_set_aside_types_by_dollars_obligated`, `top_federal_contract_vehicles_by_dollars_obligated`, and `top_idvs_by_dollars_obligated`.
- Use this pass to derive the vendor's dominant recent NAICS, PSC, set-aside pattern, vehicle or IDV usage, and likely entry lanes.
- If this pass is too thin or too noisy to support a defensible lane focus, stop and ask the user for the minimum NAICS, PSC, or work-category guidance needed.
- Analyze the buyer office as both a `contracting_federal_agency` and a `funding_federal_agency` in later steps. Keep those roles separate.
5. Run aggregation-first office buying passes with `Search_Federal_Contract_Awards` for both office roles.
- Use `per_page: 0`.
- Run one pass with the resolved office in `contracting_federal_agency_ids`.
- Run a separate pass with the resolved office in `funding_federal_agency_ids`.
- Keep the 24-month window stable in both passes.
- Use the vendor-derived lane focus from Step 4 to interpret which office buying lanes are most relevant. Only add resolved `naics_category_ids` or `psc_category_ids` when the vendor-history aggregation pass fails and the user then provides explicit lane guidance.
- Request aggregations that support buyer planning. At minimum use `dollars_obligated_stats`, `top_awardees_by_dollars_obligated`, `top_naics_codes_by_dollars_obligated`, `top_psc_codes_by_dollars_obligated`, `top_federal_contract_vehicles_by_dollars_obligated`, `top_idvs_by_dollars_obligated`, and `top_transaction_points_of_contact_by_dollars_obligated`.
- Use these passes to identify how the office buys as a contracting node versus as a funding node, where those roles overlap, and whether the office appears to buy mainly through stand-alone awards, IDVs, or master vehicles.
6. Run row-level office award retrieval pass(es) with `Search_Federal_Contract_Awards` before any optional branch.
- Reuse the same stable 24-month window and office-role filters from Step 5.
- Paginate as needed rather than assuming the first page is enough.
- Retrieve representative rows for both the contracting role and the funding role. If one role is sparse or mostly duplicates the same core awards, say that clearly instead of forcing a redundant second row set.
- If the first page is dominated by very large outlier awards, off-lane buys, or records that are not representative of the vendor's plausible entry lane, run at least one additional row pass using the vendor-derived lane focus from Step 4 or a more representative sort before selecting the office's representative buys.
- Request `fields_to_return` explicitly. At minimum request `govtribe_id`, `govtribe_url`, `name`, `contract_number`, `award_date`, `completion_date`, `ultimate_completion_date`, `contract_type`, `descriptions`, `govtribe_ai_summary`, `dollars_obligated`, `ceiling_value`, `set_aside_type`, `awardee`, `parent_of_awardee`, `contracting_federal_agency`, `funding_federal_agency`, `naics_category`, `psc_category`, `federal_contract_vehicle`, `federal_contract_idv`, `transaction_contacts`, `originating_federal_meta_opportunity_id`, and `originating_federal_contract_opportunity`.
- Use these rows to select representative recent buys and confirm how the office behaves in each role, its ordering-path pattern, and repeat-awardee behavior.
7. Run a vendor-fit and access pass with `Search_Federal_Contract_Awards`.
- Use the resolved `vendor_ids` for the target vendor.
- First check for direct office overlap in the same 24-month window against both the contracting-role cohort and the funding-role cohort from Step 5.
- If direct office evidence is sparse or absent, run one careful adjacent-evidence pass that compares the vendor against the office's dominant NAICS, PSC, value band, and recurring vehicle or IDV patterns.
- Keep direct evidence separate from adjacent evidence. Label adjacent evidence as adjacent or inferred rather than presenting it as direct office familiarity.
- Use this pass to decide whether the vendor appears to have direct office access, partial ordering-path access, only adjacent lane evidence, or no meaningful evidence yet in each office role.
8. Run the ordering-path branch only when the office award evidence shows meaningful IDV or vehicle concentration.
- First use `federal_contract_vehicle` and `federal_contract_idv` already returned on award rows.
- Only call `Search_Federal_Contract_IDVs` or `Search_Federal_Contract_Vehicles` when a dedicated follow-on lookup materially improves correctness.
- For IDV follow-on calls, seed the search from IDs already returned on award rows whenever possible and request fields such as `govtribe_id`, `govtribe_url`, `name`, `contract_number`, `award_date`, `last_date_to_order`, `contract_type`, `pricing_type`, `description`, `govtribe_ai_summary`, `ceiling_value`, `multiple_or_single_award`, `set_aside`, `solicitation_procedures`, `extent_competed`, `legislative_mandate`, `awardee`, `parent_of_awardee`, `federal_contract_vehicle`, `contracting_federal_agency`, `funding_federal_agency`, `naics_category`, `psc_category`, `task_orders`, `transaction_contacts`, `originating_federal_meta_opportunity_id`, and `originating_federal_contract_opportunity`.
- For vehicle follow-on calls, seed the search from IDs already returned on award rows whenever possible and request fields such as `govtribe_id`, `govtribe_url`, `name`, `award_date`, `last_date_to_order`, `contract_type`, `descriptions`, `govtribe_ai_summary`, `set_aside_type`, `shared_ceiling`, `federal_agency`, `federal_contract_awards`, `originating_federal_meta_opportunity_id`, and `originating_federal_contract_opportunity`.
- Use this branch to explain how the office routes work, whether the lane is stand-alone or vehicle-mediated, and whether the vendor already holds a plausible access path.
9. Run the evidence-backed contact branch with `Search_Contacts`.
- Use the resolved office through `federal_agency_ids`.
- Prefer `reference_types` of `pointOfContact` and `transactionContact`.
- When representative awards from Step 6 materially sharpen the contact set, add `referenced_govtribe_ids` from those awards.
- If the office-wide contact cohort is broad, noisy, or dominated by contacts outside the vendor-relevant lane, narrowing with `referenced_govtribe_ids` from the most representative awards is required.
- Request `fields_to_return` explicitly. At minimum request `govtribe_id`, `govtribe_url`, `name`, `email`, `phone`, `title`, `role`, `organization`, and `parent_organization_details`.
- If this branch returns no usable contacts, say so clearly. Do not invent broader outreach targets.
10. Run the current-opportunity branch as a required live-demand check.
- Use `Search_Federal_Contract_Opportunities` with the resolved office and the strongest office-lane filters derived from earlier steps.
- Run an active-solicitation pass with `opportunity_types=["Solicitation"]`.
- Use a future-facing `due_date_range` so the solicitation results are currently open for bid.
- Run a recent pre-solicitation pass with `opportunity_types=["Pre-Solicitation"]`.
- Use `posted_date` with `from="now-180d/d"` on the pre-solicitation pass so only recent near-term demand remains.
- Request `fields_to_return` explicitly. At minimum request `govtribe_id`, `govtribe_url`, `name`, `solicitation_number`, `opportunity_type`, `opportunity_state`, `part_of_mas`, `set_aside_type`, `posted_date`, `due_date`, `descriptions`, `govtribe_ai_summary`, `federal_meta_opportunity_id`, `federal_contract_vehicle`, `federal_agency`, `naics_category`, `psc_category`, and `points_of_contact`.
- Keep active solicitations separate from pre-solicitations in the final answer.
- If one bucket returns no usable results, say that clearly rather than implying current demand exists.
- Use this step to validate whether current demand resembles the historical buying pattern and to sharpen pursuit angles and next actions.
- Do not let sparse or off-pattern live opportunities override the office's core buying profile.
11. Perform a verification pass before finalizing the office plan.
- Remove obvious outlier awards or weak adjacent-evidence claims and confirm the main office-buying pattern still holds.
- Lower confidence if the plan depends on sparse office history, one-off vehicle signals, or one-record contact evidence.
- This pass does not require an extra tool call unless the current evidence still leaves the office pattern in doubt.
- If evidence is too thin to support a credible office plan, say so clearly and stop.
## Output Format
Return the answer in this order:
1. **Vendor and Office Resolution**
- Briefly explain how the target vendor and target buyer office were resolved.
- State that this workflow uses the last 24 months of office buying behavior.
- State that the office was analyzed as both a contracting office and a funding office.
2. **Search Approach**
- Briefly explain which GovTribe tools were used.
- Briefly explain how the vendor-history lane-derivation aggregation pass, the office-role aggregation passes, the office row pass or passes, the vendor-fit pass, the contact pass, the mandatory active-solicitation pass, and the recent pre-solicitation pass were used.
3. **Office Buying Profile**
- Use a required markdown table.
- Recommended columns: `Dimension`, `Finding`, `Evidence`.
- Cover dominant work categories, leading awardees, value-band pattern, concentration, recurring ordering paths, the vendor-derived lane focus, and any contracting-versus-funding differences that matter.
4. **Representative Recent Buys**
- Use a compact markdown table.
- Recommended columns: `Role`, `Award`, `Awardee`, `Date`, `Value`, `Structure`, `Why It Matters`.
5. **Evidence-Backed Contacts**
- Use a compact markdown table.
- Recommended columns: `Contact`, `Organization`, `Role / Signal`, `Why Relevant`.
- If no evidence-backed contacts are available, say so clearly instead of fabricating a contact list.
6. **Ordering Path and Access Assessment**
- Explain whether the office appears stand-alone, IDV-led, vehicle-led, or mixed.
- Explain whether the vendor shows `Direct`, `Adjacent`, `Inferred`, or `Weak` access evidence and why.
- Label inferences clearly.
7. **Office-Specific Pursuit Angles / Light Micro-Offer Menu**
- Provide 3 to 5 concise pursuit angles or micro-offer themes.
- Tie each one directly to observed buying evidence, work category, value band, or ordering path.
- Do not turn this section into a full offer packet, CLIN build, or long outreach draft.
8. **Current Open and Near-Term Opportunities**
- Use a compact markdown table.
- Recommended columns: `Stage`, `Opportunity`, `Agency`, `Due Date / Posted`, `Lane Fit`, `Why It Matters`.
- Use the `Stage` column to distinguish `Open Solicitation` from `Pre-Solicitation`.
- If no open solicitations are found, say so clearly instead of implying current demand exists.
- If no recent pre-solicitations are found, say so clearly instead of implying near-term demand exists.
9. **Recommended Next Actions**
- Provide concise next steps for the vendor's federal buyer expansion plan.
- Reflect the current opportunity scan, including monitoring guidance when no open solicitations are found.
10. **Overall Confidence**
- State overall confidence and briefly explain the main supporting evidence and limitations, including live-demand signal quality.
## Citation Rules
- Only cite sources retrieved in the current workflow.
- Never fabricate citations, URLs, IDs, or quote spans.
- Use exactly the citation format required by the host application.
- Attach citations to the specific claims they support, not only at the end.
## Grounding Rules
- Base claims only on provided context or GovTribe MCP tool outputs.
- If sources conflict, state the conflict explicitly and attribute each side.
- If the context is insufficient or irrelevant, narrow the answer or state that the goal cannot be fully completed from the available evidence.
- If a statement is an inference rather than a directly supported fact, label it as an inference.Related articles
- GovCon workflows with MCP: Review the other GovTribe MCP workflow families.
- GovTribe MCP: Manage GovTribe MCP access, API keys, credits, and supported AI tools.
- Market Intelligence: Move from one target into buying patterns, early signals, and recompete analysis.
- Pricing Data: Build pricing models, benchmark labor rates, and pressure-test pricing assumptions.
- Deep Dive: Start with one opportunity, award, or vendor and build a source-backed brief.