Pricing Data

# Build Pricing Model

## User Input
- **Target requirement:** [Opportunity, solicitation, GovTribe link, SOW/PWS, contract, award, IDV, labor category set, or pricing question]
- **Pricing objective:** [Price-to-win, rate sanity check, labor-cost build-up, MAS benchmark, recompete pricing, or bid review]
- **Target company:** [Optional vendor, incumbent, or offeror context]
- **Roles or labor categories:** [Optional draft labor categories, roles, levels, quantities, hours, or staffing plan]
- **Pricing assumptions:** [Optional indirects, fee, escalation, worksite, clearance, POP, subcontracting, travel, material, or ODC assumptions]

## Goal
Use GovTribe MCP tools to build an evidence-backed pricing model or pricing posture for a target requirement.
Separate cost-based wage evidence, market-visible labor-rate evidence, awarded-price evidence, Service Contract Inventory service-footprint context, and solicitation-specific assumptions.
Return a practical model that a pricing, capture, or proposal team can review before bid or rate decisions.

## Required Input
The user must provide a target pricing requirement before analysis begins.

Accept any of the following:
- GovTribe opportunity, award, IDV, vehicle, or government-file link
- Solicitation number, contract number, title plus agency, or other exact identifier
- SOW, PWS, pricing sheet, CLIN structure, amendment, Q&A, or uploaded file context
- Labor category set, draft rates, proposed staffing plan, or company pricing assumptions
- Plain-language requirement description only if it is specific enough to price without guessing the target

Optional constraints the user may provide:
- Pricing objective such as price-to-win, rate sanity check, labor-cost build-up, MAS benchmark, recompete pricing, or bid review
- Target company, incumbent, or offeror context
- Draft roles, labor categories, levels, quantities, hours, or staffing plan
- Indirects, fee, escalation, worksite, security clearance, period of performance, subcontracting, travel, material, or ODC assumptions
- Agency, vehicle, NAICS, PSC, place of performance, or known predecessor context

Input rules:
- If the input resolves cleanly to one target pricing requirement, proceed immediately.
- If the input is too vague to resolve to one target pricing requirement, ask for the minimum missing detail required to proceed.
- Do not guess the target requirement, incumbent, labor mix, or pricing assumptions.
- Do not start substantive pricing analysis until the target requirement is resolved or the user confirms that the model should be assumption-driven.

## Workflow

### Steps
1. Call `Documentation` once with `collections=["govtribe-for-agents", "govtribe-user-guide"]`, `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", "Vector-store content retrieval", "Troubleshoot search results", "Service Contract Inventory analysis", "Pricing Data"]`, and `max_tokens=16000` before any other GovTribe tool.
   - Treat the returned guide articles as binding for search behavior, query construction, date and location filtering, relationship filters, aggregation-first review, vector-store retrieval, search-context management, troubleshooting, SCI interpretation, and pricing-source boundaries.
   - 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 requirement.
   - Use `Search_Federal_Contract_Opportunities` for current notices, solicitations, RFIs, sources sought notices, presolicitations, or opportunity links.
   - Use `Search_Federal_Contract_Awards` for predecessor awards, incumbent award context, recent obligated value, award structure, or contract-number lookups.
   - Use `Search_Federal_Contract_IDVs` or `Search_Federal_Contract_Vehicles` when vehicle, IDV, BPA, GWAC, IDIQ, or schedule context affects pricing.
   - Use `Search_Vendors` only when target-company, incumbent, awardee, parent-child, UEI, CAGE, or vendor identity context materially improves the model.
   - Resolve agencies, NAICS, PSC, vehicles, IDVs, vendors, and places of performance only when they materially sharpen later pricing evidence.
3. Pull and interpret requirement files when they affect pricing.
   - Use `Search_Government_Files` for files connected to the resolved opportunity, award, IDV, vehicle, or related parent record.
   - Request fields such as `govtribe_id`, `govtribe_url`, `name`, `posted_date`, `content_snippet`, `download_url`, `parent_record`, and `govtribe_ai_summary`.
   - Focus on SOW/PWS language, pricing instructions, Section L/Section M, CLINs, labor categories, staffing tables, Q&A, amendments, evaluation factors, period of performance, place of performance, worksite, clearances, travel, materials, and ODCs.
   - If snippets are not enough and file text is necessary, use `Add_To_Vector_Store`, then `Search_Vector_Store`.
   - If no relevant files are returned or file text is unavailable, say so and keep the model scoped to the available record evidence and user-provided assumptions.
4. Extract pricing drivers from the resolved requirement and user input.
   - Identify labor categories, role levels, quantities, hours, expected staffing shape, period of performance, location, worksite, security clearance, customer, NAICS, PSC, vehicle, pricing type, set-aside posture, incumbent or predecessor context, and likely major cost drivers.
   - If roles or quantities are missing, infer candidate roles only when the requirement text supports them and label them as assumptions.
   - Separate fixed facts, model assumptions, and unresolved questions.
5. Build the wage baseline with `BLS_Occupational_Wage_Data`.
   - Map each role or labor category to the cleanest defensible occupation title or occupation proxy.
   - Prefer MSA-level geography when the place of performance is known, then state-level geography, then nationwide only when no better location is available.
   - Use role-level logic consistently: junior maps to lower-percentile wage evidence, journeyman maps to median evidence, senior maps to upper-percentile evidence, and SME requires explicit rationale above normal senior-level evidence.
   - Use escalation only when future-year pricing or a multi-year period of performance makes it necessary.
   - Treat BLS output as wage-oriented cost evidence, not fully burdened bill rates, not GSA Schedule ceiling rates, and not awarded prices.
6. Apply burden, fee, escalation, and hours only from user-provided assumptions or clearly labeled model assumptions.
   - Use user-provided fringe, overhead, G&A, fee, escalation, hours, workshare, travel, materials, and ODC assumptions first.
   - If assumptions are missing, provide placeholders or scenario assumptions rather than presenting invented rates as facts.
   - Use a consistent formula when enough inputs exist: `Burdened Rate = Wage x (1 + Fringe) x (1 + Overhead) x (1 + G&A) x (1 + Fee/Profit)`.
   - For future years, apply escalation before burdening or clearly state the formula used.
7. Benchmark with `Search_GSA_Labor_Rates` when MAS, ceiling-rate, schedule, labor-category, or market-visible rate context is relevant.
   - Search precise labor-category titles instead of broad generic role names.
   - Use structured filters for vendor, IDV, vehicle, SIN, category, education, years of experience, worksite, business size, security clearance, rate year, contract start, and contract end when available.
   - Use `price_stats`, `price_percentiles`, and top-term aggregations before relying on individual rows.
   - Treat returned values as GSA Schedule labor-rate evidence, not wages and not guaranteed payable task-order rates.
8. Add awarded-price and predecessor evidence when it materially improves the model.
   - Use federal awards and IDVs for predecessor values, contract type, pricing type, obligations, ceiling value, awardee, agency, vehicle, NAICS, PSC, and period-of-performance context.
   - Use `Search_Line_Items` only when comparable state/local line-item evidence is relevant to the pricing question.
   - Compare line items only when unit of measure, quantity, description, parent-award context, and category context are close enough to support the comparison.
   - Use awarded and line-item evidence to strengthen market and reasonableness sections, not to replace wage logic when the user needs a labor build-up.
9. Add Service Contract Inventory context when the pricing model is labor-heavy federal services.
   - Use `Search_Service_Contract_Inventory` when incumbent footprint, contractor hours, FTEs, prime/sub workshare, subcontractor reliance, agency/vendor footprint, or derived hourly-rate context affects price-to-win or staffing realism.
   - Anchor SCI searches to fiscal year, vendor, award, IDV, agency, PSC, NAICS, contract number, or place of performance when available.
   - Use `role: ["prime"]` for row-level dollar, total-hour, FTE, subcontractor-count, and derived-rate context.
   - Use `subcontractor_count_range.max = 0` when a cleaner prime-only derived hourly-rate proxy is more useful than a blended prime-plus-sub workshare signal.
   - Request fields such as `fiscal_year`, `role`, `contract_number`, `description`, `hours_invoiced`, `ftes`, `total_dollar_amount_invoiced`, `total_contractor_hours_invoiced`, `total_ftes`, `subcontractor_count`, `sub_hours_share`, `derived_hourly_rate`, `vendor`, `federal_contract_award`, `federal_contract_idv`, `psc_category`, `naics_category`, `contracting_federal_agency`, `funding_federal_agency`, and `source_url`.
   - Treat `derived_hourly_rate` as source-row context, not a loaded labor-category rate, wage benchmark, or complete price.
10. Synthesize the pricing model.
   - Reconcile the BLS wage baseline, burdened cost build-up, GSA labor-rate benchmark, awarded-price evidence, SCI service-footprint context, solicitation constraints, and user-provided assumptions.
   - Build pricing scenarios such as aggressive/low, competitive midpoint, and premium/risk-adjusted when the evidence supports scenario analysis.
   - Explain where evidence agrees, diverges, or constrains the recommended posture.
   - Do not overstate precision when the model depends on inferred labor mix, missing file text, sparse comparables, broad role mappings, or uncertain indirect rates.
11. Perform a verification pass before finalizing the answer.
   - Remove weak comparables and obvious outliers.
   - Confirm units, role mappings, geography, period of performance, and workshare assumptions are comparable.
   - Lower confidence when evidence is sparse, roles are inferred, file text is unavailable, or the strongest pricing evidence is not close to the requirement.
   - If the available evidence is too thin for a defensible pricing model, provide a scoped evidence summary and the minimum information needed to complete the model.

## Output Format
Return the answer in this order:

1. **Pricing Posture Summary**
   - State the recommended pricing posture, model type, and confidence.
   - Say whether this is a price-to-win model, labor-rate sanity check, cost build-up, MAS benchmark, recompete pricing review, or assumption-driven model.
2. **Resolved Requirement and Assumptions**
   - Use a compact table for target, agency/customer, vehicle or contract context, POP, NAICS/PSC, worksite, period, and known pricing constraints.
   - Separate confirmed facts from assumptions.
3. **Pricing Evidence Approach**
   - Briefly explain which tools and evidence layers were used: requirement files, BLS, GSA labor rates, federal awards or IDVs, line items, SCI, and user-provided assumptions.
4. **Labor Category Mapping**
   - Use a required markdown table.
   - Recommended columns: `User Role`, `Mapped Occupation / Benchmark`, `Level`, `Geography`, `Evidence Used`, `Notes`.
5. **Cost Build-Up**
   - Use a markdown table when enough inputs exist.
   - Recommended columns: `Role`, `Wage Basis`, `Escalation`, `Burden / Fee Assumption`, `Modeled Rate`, `Confidence`.
   - If user assumptions are missing, show placeholders or scenario assumptions instead of invented rates.
6. **Market Benchmarks**
   - Include GSA labor-rate, awarded-price, and line-item evidence only when those branches were used.
   - Explain whether modeled rates appear below, within, above, or not comparable enough to the visible benchmark range.
7. **SCI Staffing and Workshare Context**
   - Include only when SCI was used.
   - Explain FTE, hours, subcontractor, workshare, and derived hourly-rate signals without treating SCI as a complete pricing benchmark.
8. **Recommended Pricing Scenarios**
   - Use a compact table.
   - Recommended columns: `Scenario`, `When To Use`, `Rate / Price Logic`, `Evidence Support`, `Main Risk`.
9. **Pricing Risks, Gaps, and Questions**
   - List unresolved labor mix, file, indirect-rate, escalation, travel, material, subcontracting, incumbent, or evaluation-factor questions.
10. **Overall Confidence**
   - State confidence and explain what would raise or lower it.

### Optional charts
Use Mermaid only when aggregation evidence materially improves interpretation:
- `pie` for workshare, vendor concentration, or evidence mix
- `xychart-beta` for year-over-year rate, hours, FTE, or value comparisons

Fallback to compact markdown tables when the data is sparse.

## 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.