analyze_capture_opportunity
ChatGPTUse this when the user wants a full capture-ready intelligence package for a specific opportunity space — useful for bid/no-bid decisions, capture planning, and win-strategy formulation. Returns a computed GO / EXPLORE / NO-GO recommendation. Aggregates five factors in parallel: active solicitations matching the space, budget backing, competitive landscape (who's winning and incumbent strength), agency protest risk, and recompete timing. The recommendation scores those factors: GO (4-5 positive), EXPLORE (2-3 positive), NO-GO (0-1 positive). For agency-wide overviews (not program-specific), use get_agency_briefing.
analyze_protest_patterns
ChatGPTUse this when the user wants cross-case pattern analysis over GAO bid-protest decisions — agency sustain rates, outcome predictors by issue tag, FAR-citation effectiveness, repeat-protester patterns, incumbent-advantage signals, or tag co-occurrence clusters. Filter with agency (use "DoD" to match Navy, Army, Air Force, Marine Corps), protester, awardee, naics_code, or date range. Use focus= to refine to an issue area — examples: "technical_evaluation", "price_evaluation", "organizational_conflict_of_interest", "past_performance", "sole_source", "best_value", "disparate_treatment". For individual case detail use list_protest_decisions; for simple counts and sustain rates use get_protest_sustain_rates.
build_igce
ChatGPTDeterministic IGCE. Missing burden for OEWS/WD lines → missing_inputs, total null. labor_lines[] (required): each object needs: - category (or labor_category): e.g. "senior software engineer" - hours: number - rate_source (or source): "calc" | "oews" | "wd" aliases: calc+/ceiling → calc; bls → oews; sca/dba → wd - percentile: p10|p25|median|p75|p90 (default median) - rate: optional explicit $/hr (skips snapshot lookup) - wd lines also: county, state, wd_type, occupation_code periods: {"base": 1, "options": 2} (aliases: base_year/base_years, option_years/option_year) — each option year escalates by escalation_rate. burden: {"fringe","overhead","g_and_a","fee"} required when any line is oews/wd.
classify_opportunity
ChatGPTUse this when the user has solicitation or RFP text and needs SCOUT's govcon taxonomy — primary industry, work type, and sub-categories — without searching live opportunities. Pass title (required), description, and agency/office when available. Returns structured JSON classification suitable for pipeline tagging, CRM enrichment, or pre-search filtering. Pair with search_opportunities to find similar live federal/SLED bids: pass the returned work_type= and/or industry= (primary_industry) as hard filters. Keyword-only search already reranks on these fields; the filters consume them.
ebuy_notifications
ChatGPTUse this when the user wants to view parsed GSA eBuy RFQ notifications — filtered by importance, type, status, NAICS, agency, or contract vehicle. Each notification includes RFQ details, importance scoring, triage summary, and recommended action items. Filter by importance ("high", "medium", "low"), notification_type ("new_rfq", "amendment", "cancellation", "award_notice", "extension"), or status ("unread", "read", "actioned", "dismissed").
find_demand_primes
ChatGPTWho already delivers this work, and whether they subcontract. Optional intent is delivery_partners, primes_to_sub, or incumbents_recompete. delivery_partners needs seller.capability_keywords or seller.uei; otherwise the default weights stay. The scores.total field is a demand-fit rank. It does not decide whether to make contact. Pass at least one of products (gazetteer names such as ServiceNow), category, psc_codes, or work_type. NAICS is a secondary filter only. Reseller channel firms are returned on excluded, not dropped. The scores.total field is a demand-fit rank. It is not a PWin and it is not a go/no-go. Dollar figures use order obligations and parent ceiling. estimated_value is not used. Subaward rows looked up by prime UEI are undated unless the source row has an action date. SAM email, phone, and fax are omitted (FOUO). limit is at most 25, and the ranked list is returned in this response.
find_pipeline_forecasts
ChatGPTUse when the user asks about pre-solicitation acquisition forecasts, agency planning dashboards, or opportunities before they appear on SAM.gov (DHS APFS, DOT, DOJ, GSA FCO). Returns planning data only — not live solicitations. For awarded/recompete data use find_recompete_contracts.
find_policy_intel
ChatGPTUse when the user asks about congressional hearing signals — NDAA, appropriations, budget testimony, procurement policy, or committee oversight affecting federal contracting. Returns structured intel chunks from transcribed hearings (not live SAM data). Pair with find_pipeline_forecasts or find_recompete_contracts for full capture context.
find_recompete_contracts
ChatGPTUse this when the user asks about contracts coming up for re-bid — incumbent research, pipeline building, capture planning, or expiring-contract discovery. Returns incumbent, estimated value, period-of-performance end date, and days until expiry. Set within_months to the horizon the user asked for (default 24, max 60): "next 6 months" -> 6, "next 2 years" -> 24, "next 5 years" -> 60. Set include_historical=true to include awards whose PoP already ended within the same window (+/- within_months). For value-targeted questions ("over $100M", "between $10M and $50M"), set min_value / max_value in raw dollars (e.g. 100000000 for $100M) — the filter is applied server-side before the detail-row cap so big-ticket contracts aren't dropped. Set sort_by="value" to rank returned rows by estimated value descending, "expiry" to rank by soonest PoP end, or omit for the default relevance score. The response always includes a pipeline_by_value_band histogram (counts and totals in <$1M / $1M–$10M / $10M–$100M / ≥$100M buckets) over the full matched pipeline, so you can answer "how many ≥ $100M" without paging through detail rows. DATE FIELDS (per row): - pop_end_current / days_until_pop_end_current — soonest date a recompete must be in place (current PoP end, before any options are exercised). Use this for capture-planning urgency. - pop_end_potential / expiry_date (= same value) and days_until_expiry — latest the work could continue if every remaining option is exercised. expiry_date is preserved for backward compatibility with widgets; new consumers should prefer pop_end_potential to make the option-period semantic explicit. A contract whose options have not yet been exercised will show pop_end_current years earlier than pop_end_potential — both are real signals. For award history and spending totals, use get_award_history.
find_sled_recompetes
ChatGPTUse when the user asks about state/local/education (SLED) or cooperative contracts nearing expiration — NOT federal USASpending (use find_recompete_contracts for DoD/civilian agency awards only). Required routing examples: - "SLED contracts expiring in Virginia with Esri" → find_sled_recompetes(vendor="Esri", state="VA", within_months=12) - "NASPO / Sourcewell recompetes" → find_sled_recompetes(query="NASPO cooperative", within_months=24) - "Oregon GIS contracts expiring" → find_sled_recompetes(query="GIS geospatial", state="OR") Returns jurisdiction, incumbent vendor, cooperative vehicle, expiration date, and days until expiry. Rows include ingest tags is_gis / is_esri plus enhanced_classification when classified. When query mentions GIS, geospatial, Esri, or ArcGIS, results auto-filter to classified rows. Optional vendor= narrows to incumbent name (e.g. vendor="Esri"). Optional state= is a two-letter code. Optional work_type= / industry= (alias primary_industry=) / sub_categories= / custom_tags= are exact enhanced_classification filters. Distinctive keywords in query= are AND-matched; empty results include zero_reason and are never padded with nearest-expiry contracts. Also returned in search_opportunities when source_type is sled or all (sled_recompetes block). Set within_months from the user's horizon (default 24, max 60). sort_by="value" ranks by estimated_value when any matched row has a dollar amount; if none do, the response sets sort_applied=false and falls back to expiry instead of pretending the value sort ran.
find_sled_vendors
ChatGPTUse when the user wants a vendor-side SLED prospect list — publishers, integrators, or custom-dev shops that hold cooperative/state awards — not open solicitations and not federal primes. Default vendor_role is publisher,integrator,custom_dev (resellers like Carahsoft/SHI/CDW-G are excluded). Default persona=capture_bd ranks by unique cooperative-master count and keeps global SIs (Accenture, Kyndryl, Oracle, Esri, …). Pass persona=vendor_partner when selling engineering capacity into GovTech vendors: that drops captive-offshore SIs, collapses NASPO state addenda to one master, and sorts 1–5 unique masters first (then value, then jurisdiction spread). Optional work_type filters on enhanced_classification (semantic), not title substring. Optional state=, vehicle=, min_contract_value=, expiring_within_months= (default 24). Examples: "who holds SLED contracts in Texas" → find_sled_vendors(state="TX"); "which GovTech software companies should we sell engineering to" → find_sled_vendors(persona="vendor_partner"). Zero matches stay empty — explain why and suggest loosening vendor_role / dropping work_type. Never substitute reseller names. For contract-level expirations use find_sled_recompetes.
find_subawards
ChatGPTUse this when the user wants disclosed federal subawards — by prime PIID, subrecipient name or UEI, or as an aggregate across a class of prime contracts. Modes (highest-precedence argument wins): piid -> subawards under a specific prime; subrecipient_uei -> exact UEI match; subrecipient_name -> substring on subrecipient; prime_awardee_name -> who a named prime typically subcontracts to; prime_naics_prefix + prime_keyword -> aggregate ranked subrecipients across a class of primes (example: prime_naics_prefix="5415" with prime_keyword="cybersecurity"). Pair with get_award_history when the user starts with a prime contractor and wants the full picture.
find_teaming_partners
ChatGPTUse this when the user wants teaming partners whose capabilities complement theirs on a bid — including 8(a), SDVOSB, WOSB, or HUBZone partners. Matches public teaming profiles on NAICS, capabilities, and certifications. opportunity_uid is optional. When supplied (from search_opportunities), the call is enriched with NAICS and title keywords from that solicitation; otherwise pass capabilities= (required keywords) with optional naics_code and certifications. For past prime-contract winners (not a teaming recommendation), use get_award_history. For disclosed subcontracts under a specific PIID, use find_subawards.
generate_discovery_report
ChatGPTUse this when the user wants a curated, AI-ranked opportunity discovery report across all active solicitations — federal, state/local, education, and commercial — filtered by keywords, NAICS, and/or agencies. report_type accepts "quick_insights", "detailed_analysis", or "trending_opportunities". Pass fresh=true to bypass any cached report. Reports typically complete in 1-3 minutes.
generate_entity_brief
ChatGPTUse this when the user wants a company entity brief — recompete cliff, sole-source share, subaward dollars, GAO sustain rate, NAICS rank, and corporate family — framed for compete, claim, or diligence. Pass entity as exactly one of {uei}, {slug}, or {company_name}. Facts are identical across lenses; only ordering and the closing CTA change. format is json (default) or html. Never authors figures: every number traces to a SCOUT tool return.
generate_grant_discovery_report
ChatGPTCurated grant discovery / mission-eligible FOA shortlist for grant practitioners. Pass keywords, agencies, applicant_types, and optionally ein= (IRS EIN), ntee=, mission_lane= (food_ag|environment|youth_ed|community_dev|rural_health), state=, include_weak=. Requires grant_discovery (Tactics+). Separate from generate_discovery_report (contracts).
generate_oasis_expiring_landscape
ChatGPTSave a hosted OASIS expiring-task landscape on the account and return its URL. Same report as generate_recompete_priority_list with an OASIS preset (default oasis_fy26_dozen). Pass within_months, audience, and query to narrow it.
generate_recompete_priority_list
ChatGPTSave a hosted recompete priority report on the account and return its URL. Use this when the user wants an expiring landscape, priority list, or CEO/BD brief scoped to a GWAC/MAC vehicle or filters. Examples: "8(a) STARS III expiring tasks next 18 months", "Polaris expiring landscape", "Alliant recompete priority list". Combines a curated or dynamic shortlist with optional pipeline stats, incumbent board, urgency bands, and capture narrative. Set report_style="executive_brief" for a two-page executive brief. Set include_synthesis=false to skip the narrative. audience: ceo | bd_lead (optional — shapes narrative emphasis) preset: curated shortlist id (default oasis_fy26_dozen); ignored when mode=dynamic query: user scope keywords (title + narrative emphasis; also parsed for filters) vehicle: GWAC/MAC filter (POLARIS, ALLIANT_2, STARS_III, OASIS, …) routing_target: candidate-generator preset (aas_defense, fedsim, oasis_plus) — not vehicle-migration detection cage_code: awardee CAGE (e.g. 05DZ5) solicitation_procedures: MAFO, fair opportunity, SB, etc. set_aside: 8(a), SDVOSB, WOSB, HUBZone, … mode: curated | dynamic — auto-selected when omitted include_synthesis: LLM narrative (default true; set false for data-only) include_pipeline: broader pipeline stats (default false for speed) group_by_parent_idv: also return parent-IDV rollups (useful for AAS Defense)
get_account_info
ChatGPTUse this when the user wants to see their current account profile — plan, MCP tool access, monthly call limit, current usage, and account status.
get_agency_briefing
ChatGPTUse this when the user wants an executive intelligence briefing on a federal agency before a meeting, gate review, or capture strategy session. Aggregates five data sources in parallel: budget priorities from Congressional Budget Justification, agency-wide budget trends, contracting landscape (top contractors and spend), GAO protest risk, and recompete pipeline. For program-specific capture intelligence with a GO/NO-GO recommendation, use analyze_capture_opportunity instead.
get_award_announcements
ChatGPTUse this for same-day federal contract award announcements before USASpending/FPDS enrichment lands. Prefer this over get_award_history when the user asks about today's awards, this morning's wins, or trade-press wins not yet in USASpending. Daily briefs use days=1 for fresh wins only. Feed filter (primary for 'DoD awards', 'NASA awards', etc.): pass sources= as comma-separated ingest keys: dod, nasa, doe, va, gsa, dhs, sam, contracts. You can also pass those phrases in agency= (e.g. agency=DoD awards, agency=FPDS awards) — they auto-map to the feed. contracts is the SAM Contract Awards API (FPDS successor) for civilian IDIQ task orders with referenced IDV + bidder count. Company watch: awardee= partial name match (e.g. awardee=Hive) across all feeds. Component filter: agency= for contracting offices within a feed (e.g. Missile Defense Agency, NASA Goddard) — not the same as sources=. Vehicle: vehicle= partial match on contract vehicle text (OASIS+, SEWP, MAS, etc.). Also: department=, since_date=, days= (default 7, max 90), min_amount=, limit= (max 100). Returns provisional rows with enrichment_pending=true until USASpending confirms the PIID.
get_award_history
ChatGPTUse this when the user asks what contracts a specific company has won, how much a company has been awarded (obligated or ceiling), past contract history, or agency-level historical spending. Data source: federal contract awards from USASpending, contracts over $100K. Set awardee= to a company or contractor name (partial match is fine). If awardee= receives a 12-character SAM.gov UEI it is matched as an exact UEI. Optional filters: recipient_uei, agency, naics_code, psc_code, set_aside_type. DATE FIELDS (per row): - award_date (= latest_action_date) — date of the most recent federal action against this PIID (base award OR latest modification). Sourced from action_date with MAX aggregation. - original_award_date — earliest action_date for this PIID within the loaded transaction window (typically the last 5–7 years). For contracts whose base award predates the load window, this is the earliest visible action, not the true base-award date. When precision matters for an old contract, prefer pop_start_date as the signal of when work actually began. - transaction_count — number of FPDS transactions visible for this PIID. A higher count signals an actively-modified long-running contract. - pop_start_date — period-of-performance start (when the contract's work was scheduled to begin). Each transaction carries the contract's POP start, so this stays accurate even when older base-award transactions have aged out of the load window. - data_refresh_date — USASpending warehouse row-update timestamp. NOT a contractual date; reflects only when the data feed was last refreshed. - is_undefinitized (when present) — True if the latest transaction is a UCA / letter contract that has not yet been definitized. By default, IDV / IDIQ base vehicle rows (which carry zero obligation) are excluded; each row also carries is_idv_base so the consumer can distinguish vehicles from task orders. For live open solicitations, use search_opportunities. For aggregated market statistics, use get_award_summary. For teaming-partner recommendations on a specific bid, use find_teaming_partners.
get_award_summary
ChatGPTUse this when the user asks for aggregated market statistics over past contract awards — totals, top awardees, year-over-year trends, or breakdowns by set-aside or category. Records are not returned individually; for individual rows use get_award_history. Classification: psc_code filters by what was purchased (use for market sizing and spend analysis). naics_code filters by seller's industry. Both can be combined. For plain-language domain queries ("cybersecurity services", "janitorial"), prefer the category= parameter, which accepts top-level OMB categories and subcategories.
get_budget_line_items
ChatGPTUse this when the user wants line-item federal budget data from Congressional Budget Justifications (Greenbook) for the 24 CFO Act agencies including the Department of Defense — to validate budget backing for an opportunity, forecast where new solicitations will emerge, or prioritize pursuits aligned with funded priorities. Filter by agency, fiscal_year, keyword (matches program and justification text), direction ("increase" | "decrease" | "flat"), or min_change_pct. Returns line items with year-over-year funding changes and extracted priority signals. For an aggregate view across all accounts, use get_budget_summary.
get_budget_summary
ChatGPTUse this when the user wants aggregate federal budget trends for an agency across all appropriation accounts — total request vs enacted, net change, count of increasing and decreasing accounts, and the top five accounts by largest increase and largest decrease. For individual line items, use get_budget_line_items.
get_capture_intelligence_bundle
ChatGPTOne-shot capture context: congressional policy intel + agency acquisition forecasts (+ optional recompete contracts). Cross-links by agency, NAICS, and incumbent PIID. Use for questions like DHS border tech, NDAA + pipeline, or recompete + policy together.
get_channel_for_product
ChatGPTGSA schedule / reseller channel map for a software product or manufacturer. Returns curated seed reseller rows when the OEM is in the seed map. This is not a live GSA eLibrary sync. When empty, use find_subawards for reseller dollars.
get_committee_control
ChatGPTChamber control, chair, and ranking member for committees in a Congress. An uncertified Congress returns the prior certified Congress and a pending note. Party is the label the chamber published.
get_company_hierarchy_profile
ChatGPTUse this for corporate family structure — ultimate parent, per-subsidiary obligation totals, and prime/sub teaming relationships. Companion to get_company_profile when the user needs a full family tree rather than the lightweight family block.
get_company_profile
ChatGPTUse this for a complete UEI-keyed contractor profile — identity, total prime obligations, agency/NAICS/PSC breakouts, fiscal-year trajectory, incumbent recompetes, and capability/teaming. Requires recipient_uei (12-char SAM UEI); do not name-match. Set rollup=family to aggregate across corporate siblings under the same ultimate parent. When the user states months_back (e.g. 24), pass that value — do not keep the 36-month default. recompete_window_months is a separate horizon (default 24) for incumbent expiries. The hosted company landscape includes capture rollups on this firm's full expiring book (pipeline_by_agency, pipeline_by_value_band, pipeline_by_expiry_band, pipeline_distributions), not just the capped recompetes[] table. Replaces stitching get_award_history + get_award_summary + find_recompete_contracts with client-side incumbent filtering.
get_company_tech_signals
ChatGPTInferred technographic signals for a target domain — primarily email/identity platform from public MX records (M365 vs Google Workspace). Set include_job_postings=true with company_name= for medium-confidence stack signals from public job posting snippets (P3). Label output as inferred installed-base signal, NOT confirmed full software stack.
get_contract_landscape
ChatGPTUse this when the user asks for a competitive intelligence brief or contract overview for an agency — individual contracts plus market statistics, offers analysis, and pattern detection (sole-source alerts, dominant incumbents, high-competition outliers) in a single response. Supports naics_codes (comma-separated, 4-digit prefix match), min_value (default $2M), modified_within_months (default 15), exclude_vehicles, set_aside_type, min_offers, pop_end_after / pop_end_before (YYYY-MM-DD window).
get_contract_vehicle_info
ChatGPTUse this when the user asks about federal contract vehicles (GWACs, IDIQs, BPAs, GSA MAS) — to identify competitors on a vehicle, validate vehicle fit for a NAICS, find ordering agencies, or size the market on a vehicle. Tracks 27 vehicles with task-order analytics including SEWP, ITES, OASIS+, Alliant 2, CIO-SP3/SP4, EIS, Polaris, 8(a) STARS III, GSA MAS, SeaPort-NxG, TRICARE, and MHS GENESIS. Pass a specific vehicle name or a sector keyword ("Fed Health", "DoD IT", "NASA GWACs", "GSA GWACs", "NITAAC") for a multi-vehicle rollup. Filter by ordering agency, awardee, or NAICS. Omit vehicle= to list all known vehicles.
get_cr_outlook
ChatGPTCurrent appropriations status for the twelve bills, with the source on each transcribed row.
get_daily_brief
ChatGPTUse this when the user asks for their morning brief, daily briefing, or "what's happening today" — returns the same unified daily intelligence the user sees on their PrimeRFP Scout dashboard and (when enabled) in their morning email. The brief covers six sections merged across all of the user's discovery scopes — the user does NOT pick a scope — sorted by deadline urgency, posted date, and value: 1. New Opportunities 2. Notable Awards & Recompetes 3. Latest News 4. Funding News 5. Agency News (filtered to scope agencies) 6. Marked Opportunity Updates (changes on watchlisted opportunities — amendments, deadline changes, awards, cancellations) For an agency-wide briefing (not user-personal), use get_agency_briefing instead.
get_flip_history
ChatGPTMeasured obligation changes after prior chamber flips. States the sample size. Does not predict the next flip.
get_grant_detail
ChatGPTFull grant FOA detail: enhanced_grant enrich (eligibility, readiness, PO, terms), grantor profile, prior winners, more-like-this. Pass uid from search_grants.
get_grant_summary
ChatGPTAggregate counts for open grants (by agency, instrument, program area, closing soon).
get_labor_rate_benchmarks
ChatGPTCALC+ awarded ceiling-rate distribution for a labor category. Matching is synonym-table only.
get_member_record
ChatGPTA member's committee seats and public acts, with sources. Does not classify the member as for or against a program.
get_opportunity_changes
ChatGPTUse this when the user asks what has changed on active solicitations — deadline pushes, status changes, amendments, modifications, or date extensions. A date window applies (maximum 30 days). Two modes: "summary" (default) returns aggregate stats over the window — totals, breakdown by change type, top modified opportunities, and daily change volume. "detail" returns individual change records with field-level diffs and a pre-formatted display string; requires opportunity_uid or change_type.
get_opportunity_detail
ChatGPTUse this when the user wants the full details for a single opportunity by its UID — contact information, attachments, set-aside, archive date, full description, and AI analysis that are not included in keyword search results. Call this after search_opportunities. Pass the uid= value from the search result row.
get_opportunity_summary
ChatGPTUse this when the user asks for counts, breakdowns, or volumes of currently open solicitations — federal (SAM.gov), state/local/education, and non-federal combined. Examples: "How many cybersecurity contracts are open?", "Breakdown of active IT solicitations at DoD", "How many open RFPs in Virginia?". For individual records, use search_opportunities. For historical award statistics, use get_award_summary. Filter by query (title/description keywords), naics_code, psc_code, agency, set_aside, source_type ("federal" | "sled" | "non-federal" | "all"), location (state/city substring), or posted_within_days (default 90).
get_per_diem_rates
ChatGPTGSA lodging and M&IE rates by city/state and fiscal year.
get_piid_dossier
ChatGPTUse this when the user provides a federal PIID (prime award or task order number) and wants the full dossier — prime contract record plus subaward totals, optionally with detailed subaward rows. Prefer this over calling get_award_history and find_subawards separately when the user has a specific PIID in hand. Set include_subaward_rows=true to include up to subaward_limit detail rows (default 25, max 100).
get_prices_paid
ChatGPTComparable past awards from the SCOUT GPU award cache (/api/mcp/prices-paid). Answers deal size and who won — award obligation / ceiling values, not hourly or unit prices. For labor rates use get_labor_rate_benchmarks (CALC+). Pitch framing: docs/runbooks/PRICING_PITCH_AND_WD_INGEST.md. Primary result stats (n/p25/median/p75) are always obligation to date (net dollars obligated so far; result.value_basis=obligation_to_date). Ceiling stats (ceiling_median / ceiling_p25 / ceiling_p75 on base_and_all_options_value) return automatically when the cache has them — no input parameter selects them. value_basis is not an input. Unknown parameters (typos like date_bais, retired value_basis) are rejected by the MCP call_tool gate — they do not silently fall back to defaults. date_basis controls the months_back window: - original (default): PoP start / original / earliest loaded tx; latest action fills null dates only — known-old PoP is excluded. - activity: in-window PoP OR in-window latest action (rescues older contracts that still received obligations). - latest_action: latest federal action date only. Retired IT PSCs (legacy D3xx end-dated Oct 2021) are flagged with successors (e.g. D302 → DA01/DA10). An empty original window is not “no market” when activity_included_n > 0 — re-query with date_basis=activity or a successor code. Discover retired codes via list_classification_values field=psc_code.
get_product_demand_fingerprint
ChatGPTProduct-firm demand intelligence: which agencies have funded demand for a named software product/category, who holds spend, and reseller channel signals. Use for software vendors (not services capture). Grounded in federal contract awards with named-product gazetteer extraction. Pass product= (e.g. "Microsoft 365", "ServiceNow") or vendor_product=. For a family of named OEMs pass products= as a comma list (or product= "OpenVMS, COBOL, Veeam") — Scout fans out one fingerprint per SKU and returns a single composite with federal $ and SLED estimated $ on separate planes. view_mode=composite (default when product+psc) adds PSC category envelope; view_mode=product is named-product slice only. include_category_envelope defaults to false (fastest first response). Set true for the PSC envelope, or use source_type=sled|all for the SLED dual-plane appendix. source_type=federal (USASpending obligations) | sled (state/local/cooperative award-registry expirations) | all (federal headline plus SLED appendix). Pass state= (e.g. TX) to narrow the SLED slice. SLED returns a dual view: named-product mentions plus a category-aligned enhanced_classification plane (not mixed into named-product totals). Does NOT confirm installed base — use get_company_tech_signals or score_prospect for inferred displacement signals.
get_product_lens_landscape
ChatGPTPortfolio product-firm landscape from award-description OEM mentions. Returns category mix, top funding agencies, PSC delivery-class mix, size bands, and dollars for awards whose descriptions matched the Scout product gazetteer. Optional agency= or category= (cyber, data_ai, zero_trust, …) filters the slice. Use for shelf/portfolio / “which agencies name these products” questions — NOT for a single named SKU (use get_product_demand_fingerprint). Not CLIN-level proof; not open SAM counts.
get_program_congressional_context
ChatGPTCommittees, gavel, and the incoming chair's public acts for a program, PIID, or budget line.
get_program_profile
ChatGPTFull program view for one named requirement: identity, status, incumbents, vehicles, funding, linked awards, notices, forecasts, and a SCOUT Durability contract read per linked active PIID. Use this when the user names a program or a program of record. Durability reads are not summed or scored. Vehicles are derived from parent IDVs on the linked awards. Membership from a recompete chain is a SCOUT grouping, not a successor the government wrote.
get_program_timeline
ChatGPTDated history of linked actions on one program: award actions, PoP ends, notices, and budget lines, each with its source id.
get_protest_sustain_rates
ChatGPTUse this when the user wants aggregate sustain / deny / dismiss counts and the merit sustain rate — sustains divided by (sustains + denies) — over published GAO decisions. Uses the same filter set as list_protest_decisions. Covers decided cases only; does not include open or pending matters.
get_recompete_methodology
ChatGPTUse this when the user asks why recompete numbers or dates from this app differ from another system they are comparing against — returns the internal methodology guide covering field mapping, PIID aggregation rules, upcoming-vs-historical behavior, and common variance causes. Does not query live award data. For live rows, use find_recompete_contracts or get_award_history.
get_supplier_page_channel
ChatGPTCrawl a supplier/partner directory page, resolve OEM names to Scout's product catalog, and fan out federal opportunity search for a named channel firm (optional UEI). Use when the user pastes a /suppliers or /partners URL and asks for federal opportunities or product matching for a reseller. Caps opportunity fan-out (default 12 products) and demand fingerprints (default 3). Unrecognized OEM names are saved to the product catalog for later review. By default also searches same-category catalog peers and labels them separately from exact OEM matches. Set exact_only=true to skip that fan-out. Pass NAICS or PSC only when the user supplies the code.
get_usage_metrics
ChatGPTUse this when the user wants their real usage metrics for the current calendar month: total tool invocations, remaining calls before the monthly limit, and per-tool call counts with success/error rates and average latency.
get_wage_benchmarks
ChatGPTBLS OEWS raw wage percentiles by occupation/SOC and area. Burden belongs in build_igce.
get_wage_determination
ChatGPTSCA or Davis-Bacon wage determination for a county. Until SAM.gov WD ingest is live, responses are a seed sample (coverage=seed_sample) — not a full SCA schedule. Prefer CALC+ / OEWS for IT and professional labor rates; do not pitch service-contract WD pricing from this tool yet.
list_classification_values
ChatGPTUse this when you need the exact Scout taxonomy label before calling search_opportunities or get_opportunity_summary with work_type=, industry= (alias primary_industry=), sub_categories=, or custom_tags=. field is one of work_type, industry, primary_industry, sub_categories, custom_tags. Optional query= substring-filters the labels. Returns exact strings to pass as filters — do not guess NAICS/PSC from these labels, and do not put them in query=.
list_oversight_events
ChatGPTCommittee and watchdog documents that name a UEI, program, or PIID. A name is not a finding against the company.
list_pack_cards
ChatGPTList report-pack cards the signed-in user owns or has joined: empty slots, status, the current report link, and the date unused cards expire. The invite code is included only for packs this user bought. Does not search the market.
list_protest_decisions
ChatGPTUse this when the user wants published GAO bid-protest decisions — individual case rows with decision URLs and (optionally) narrative previews. Covers decided cases only; does not list open or pending protests still before GAO. Pair with find_recompete_contracts and get_award_history to study sustain patterns at an agency. Filter by agency (use "DoD" to match Navy, Army, Air Force, Marine Corps), awardee, protester, naics_code, date range, or narrative_contains (substring on decision text). Set include_narrative=true for a capped preview.
lookup_regulation
ChatGPTUse when the user asks what a regulation says — FAR, DFARS, PGI, or 13 CFR cites (e.g. FAR 13.003, DFARS 252.204-7012, CFR 125.6, limitations on subcontracting). Returns quoted text from Scout's stored eCFR Title 48 + Title 13 + DFARSPGI corpus, with optional open notices that name the cite. Do not use resolve_program or find_policy_intel for bare regulation cites.
prepare_market_landscape_report
ChatGPTSave a SLED and/or federal market landscape report on the account, or return questions still needed. Pass what you know; SCOUT returns clarifying questions or a report URL when ready. The full internal search template is assembled server-side — not returned to clients. markets: `sled, federal, both, or empty to receive a markets question. mission_scope: durable domain lock (e.g. cybersecurity, construction). Federal runs refuse a generic wedge and return status=questions with how_to_continue until locked. naics_codes: comma-separated 6-digit NAICS lock (e.g. 237110,236220). Threaded into every federal sub-tool (find_recompete_contracts.naics_code, get_contract_landscape.naics_codes, get_award_summary.naics_code, etc.). Required for construction/utility briefs so the hosted report is not keyword-only. recipient_uei: optional 12-char SAM UEI — prefer UEI-keyed company profile + awards over a keyword-only landscape. persona: price_to_win | capture_bd | pe_ma | gov_buyer | vendor_partner — drives title framing and section emphasis. scope_lock: when true, honor explicit mission_scope / naics and do not niche-collapse diversified firms (e.g. federal IT services must not become software development). angle_note: optional freeform sender note (internal framing only; never surfaces inbound page visits or confidential diligence targets). session_state: the session_state object returned by an earlier call of this tool. Pass that object back to continue. It may include pws_naics_codes` as a list. Leave it empty on the first call.
push_crm_feed
ChatGPTUse this when the user asks which CRM or Chat integrations are connected, to land THIS conversation into HubSpot/Salesforce/Dynamics, to check the status of a company or pipeline deal already in the CRM, or to dry-run / Push an existing Scout feed. Call with no arguments to list THIS user's live connections, feeds, and session_land (which CRM, which Chat destinations will notify). Chat is Slack, Discord, or Teams — Teams is coming soon. Do not invent a destination as connected unless it appears in the response. Status lookup: pass match= (company, deal, PIID, solicitation, UEI) without rows. Optional lens=pipeline or accounts. If the result has needs_clarification=true, ask the user the ask= question — do not guess among candidates. Session land: pass rows from this session (recompetes or opportunities) plus optional report_id. Default limit=1 (the deal) unless they named a feed or said all/these. provider= only if more than one CRM is live. Dry-run first; push=true when they said update/write/land. Scheduled feed: pass feed_id from the list. Live write: push=true. HubSpot, Salesforce, and Dynamics receive the same Scout fields (PoP or close date, source report URL, dossier URL). Scout does not write Fit Score, PWin, or GO/NO-GO. A live CRM land/Push posts a line to each connected Chat destination (deal name, report URL, optional Slack @capture_lead).
report_empty_search
ChatGPTUse this when a user's opportunity search returned zero results — including NAICS adjacency expansion — and they want the support team to investigate. Sends an internal notification with the search context (NAICS, query, adjacent codes searched, optional user note).
resolve_program
ChatGPTGiven a PIID, solicitation number, notice id, or budget-line id, return the program it belongs to, the link confidence, and the evidence. Returns none when no link exists.
run_buyer_solution_engineering_analysis
ChatGPTRun a buyer-lens analysis for one agency. Optional offering, office, and customer_label narrow the narrative. Omit offering for an agency-wide read. Capture notes are a separate appendix. customer_label: customer name used in the title and narrative. title: optional full report title override. Example: agency='FEMA' or agency='DOD', offering='F-35'. Starts a stored analysis job on the account (about 10–20 minutes) and returns the hosted report when it finishes.
run_solution_engineering_analysis
ChatGPTUse this when a Premier user wants a full Solution Engineering Analysis (SEA) for one company — SWOT through notional-winner prompts at the company's STRONGEST and WEAKEST buyer agencies, plus a buyer-fit contrast synthesis with Executive and BD Capture one-pagers. Requires recipient_uei (12-char SAM UEI) or omit to auto-select a company with multi-agency history. You can include the UEI directly in the user prompt (e.g. "Run SEA for HQBRRJBLDQ37"). Optional scope follow-up from a growth research brief: routing_target (e.g. aas_defense), agency (e.g. DOD), within_months, follow_up_report_id (hosted report id), anchor_piid / anchor_title from the brief. Starts a stored analysis job on the account (about 15–25 minutes) and returns the hosted report when it finishes, including supporting phase documents and the executive report.
schedule_discovery_report
ChatGPTUse this when the user wants to save or update a recurring opportunity-discovery schedule — reports run automatically on the chosen cadence. Set frequency to "daily", "weekly", "biweekly", "monthly", or "never" (to pause). By default, results are stored for later retrieval; set send_email=true to also email them to the user's account address. Set enabled=false to pause without deleting the schedule.
score_prospect
ChatGPTProduct-firm prospect scoring: Demand-Fit (agency-side, contract-grounded) + Displacement (inferred, confidence-weighted). Demand-Fit ranks agencies by addressable obligated spend for the product/category. Displacement combines DNS/MX platform signals and contract product mentions — always labeled inferred with evidence trail.
search_grants
ChatGPTSearch federal (and cataloged state) GRANT funding opportunities / FOAs / NOFOs. NOT for contracts — use search_opportunities for procurements. source_type: federal | non-federal | all (preferred for market cut). source_category accepts those aliases OR exact Federal/State/SLED/Foundation/Tribal/Municipal. Place names in query (e.g. 'Missouri broadband') auto-set state and strip from keywords. Optional state= (CA) or region= (midwest). Geo scope excludes nationwide federal unless include_nationwide=true. Final-score / awardee announcement pages are excluded by default; set include_results=true for competitive-intel award outcomes. Returns eligibility, funding amount, deadlines, readiness snippets when enriched. For grant detail with grantor profile and prior winners, use get_grant_detail.
search_opportunities
ChatGPTUse this when the user wants to find currently active contracting opportunities — federal (SAM.gov), state/local/education (SLED), or non-federal — or to look up a specific solicitation or contract number. Set source_type to "federal", "sled", "non-federal", or "all" (default). When the user gives any solicitation, contract, order, or RFP/RFQ number, set solicitation_number= and leave query= empty. Otherwise, put subject-only keywords in query= (omit generic words like "opportunity", "solicitation", "active", "federal"). For historical awards or spending, use get_award_history or get_award_summary. For contracts expiring soon, use find_recompete_contracts. For teaming partners on a specific opportunity, use find_teaming_partners. To restrict to a geography, set location= to a state ("MO" or "Missouri"), a city + state ("Kansas City, MO"), or a county + state ("Jackson County, MO"). County filtering requires a state because county names repeat across states.
search_programs
ChatGPTFind programs by name, agency, NAICS, PSC, vehicle, incumbent, status, or next-action window. A program is a named requirement that persists across contract actions. It is not a vehicle (ITES-3S is a vehicle), not a budget line, and not one solicitation. Use this to build a pipeline around a domain. For one named program (NGEN-R, MHS GENESIS, a program of record), use get_program_profile. Empty results are a catalog boundary, not a finding that the agency has no program. Pass naics_code or psc_code only when the user stated the code.
send_report_email
ChatGPTUse this when the user wants a report built from session data emailed to themselves. Compose the report HTML (fragment or full document) and pass it as html_content. The body is wrapped in a branded email shell before delivery. Recipient: emails are delivered only to the authenticated user's own account email. If to_email is supplied it must match that address (case-insensitive). Optional parameters support a plain-text summary, up to five additional file attachments, and a short conversation_note label. By default, the email body is a short teaser and the full HTML report is attached as a file for correct rendering; set embed_full_report_in_email_body=true to inline it instead.
setup_ebuy_notifications
ChatGPTUse this when the user wants to set up or manage GSA eBuy RFQ notification forwarding — parsed, classified, and triaged automatically based on their profile. Set enabled=true to activate, false to pause. Use filter_rules for natural-language criteria (e.g. "only NAICS 541512, DoD agencies, minimum $500K"). Set digest_frequency to "immediate", "daily", "weekly", or "none" (in-app only).
summarize_contract_watchlist
ChatGPTBuild a recompete shortlist and save a hosted report on the account. Returns a bullet list of expiring or notable federal task orders. Use when the user wants a curated shortlist or bullet list for CEO/BD review. Provide contract_keys (parent-piid or bare PIID), preset (e.g. oasis_fy26_dozen), OR dynamic filters: vehicle (Polaris, Alliant, OASIS), agency, cage_code, solicitation_procedures (MAFO / fair opportunity), set_aside (8(a), SDVOSB). Returns bullets[], items[] with incumbent, value, bidders, PoP end, plus hosted report URL.
summarize_policy_topic_landscape
ChatGPTUse when the user asks for cross-agency policy topic themes — common threads by agency, dominant hearing metadata topics, or a policy landscape breakdown over a recent window. Aggregates LLM-tagged industries/services/signals from congressional hearing chunks (not SAM data). Returns narrative text plus structured per-agency top topics and an inline chart payload.
upload_opportunity_solicitation
ChatGPTUse this when the user provides a solicitation PDF/DOCX/TXT for a known opportunity UID and wants Scout to scan it (ClamAV), store the text, and refresh the regulation lens (FAR/DFARS/PGI cites). Pass opportunity_uid from search_opportunities or get_opportunity_detail. content_base64 is the raw file bytes. intent defaults to regulation_lens. Optional piid is recorded As stated until verified. Infected files are rejected and never stored as pdf_text. Prefer this over guessing cites from a thin notice description.
verify_figures
ChatGPTCheck figures in free text against a SCOUT envelope you already hold. stored_result is REQUIRED — pass the prior tool's full JSON (result + answer_card + query_hash). Server-side lookup by query_hash alone is not available; calling with only query_hash returns stored_result_required.