Usaspending

Quality – / 100not scored

Not scored: fewer than three checks apply, usually because no remote answered a credential-free probe or the server is a local package.

Tool list unknown · tools last changed 2026-10-17 · checked 2026-10-20 13:17 UTC

Tool changes

• 2026-10-17usa_expiring_awardsremoved

  Federal contracts EXPIRING soon -- the recompete calendar. "Which VA IT contracts over $10M expire in the next 12 months?" / "what is up for recompete at DHS next year" / "find follow-on opportunities in NAICS 5415" / "whose contract is ending". Returns the incumbent holding each award, its period of performance, obligated dollars, agency, NAICS/PSC, and a usaspending.gov link. Filter by agency, sub-agency, NAICS or PSC prefix, incumbent name, and minimum obligated dollars. Covers awarded CONTRACTS already held by a vendor; for open solicitations still accepting bids use samgov/govcon tools.

• 2026-10-17usa_spending_trendsremoved

  "How has [agency] contract spending trended over the last N fiscal years?" / "is [agency] spending on X growing?" / "federal spending history for [topic]" — US FEDERAL contract/award spending over time from USAspending.gov, grouped by fiscal year, quarter, or month. Filter by keywords or by federal agency (DHS/Homeland Security, DOD/Defense, HHS, VA, DOE, NASA, State, Treasury). Returns the historical dollar amount per period for trend and budget-forecasting questions. Federal only — for state & county award data use gov_contracts_search.

• 2026-10-17usa_spending_by_categoryremoved

  Analyze federal spending by industry, product/service, recipient, or agency. Returns spending totals per category. Use for market research and identifying government contracting opportunities.

• 2026-10-17usa_award_searchremoved

  Search US federal PROCUREMENT CONTRACTS / government contract awards for goods and services. Use recipient_name for "contracts won by Lockheed Martin"; keywords searches award descriptions/topics, not contractor identity. Dates are optional and default to the last 12 months for "recent" questions. Dates select awards ACTIVE in the window (not signed in it) and award_amount is the award's LIFETIME obligation, so do not sum it as spending for the period. Results are paged: 100 per page max — pass `page` (and read `page_metadata.has_next`) to reach the rest. Returns recipient, award amount, outlays (with an outlays_reported flag, since DoD awards usually report none), dates, and contract type.

• 2026-10-17recallremoved

  Retrieve a value previously saved via remember, or list all saved keys (omit the key argument). Use to look up context the agent stored earlier — the user's target ticker, an address, prior research notes — without re-deriving it from scratch. Scoped to your identifier (anonymous IP, BYO key hash, or account ID). Pair with remember to save, forget to delete.

• 2026-10-17scan_competitor_ai_presenceremoved

  Compare AI visibility across multiple entities side-by-side. Probes each entity (your brand + N competitors) with ai_visibility_check, ranks by score, surfaces which is most/least recognized. Useful for competitive AI-marketing audits: "does Claude know about us as well as our competitors?". Returns ranked list with score, confidence, signal density per entity.

• 2026-10-17generate_llms_txtremoved

  Generate a production-ready llms.txt file for any URL so AI crawlers (ChatGPT, Claude, Perplexity) can index the site cleanly. Fetches the page, extracts title/description/key links, and emits the standard llms.txt markdown format. Output is a single text blob ready to drop at site-root/llms.txt. Useful for: getting a client's site indexed by AI, drafting llms.txt for your own project, or auditing how an AI crawler would see a competitor.

• 2026-10-17pipeworx_trendingremoved

  What other AI agents are calling on Pipeworx right now. Returns the top tools, top packs, and total call volume over a recent window (24h, 7d, or 30d). Useful for: (1) discovering what data sources are hot for current events, (2) confirming a popular tool is the canonical choice before asking your own question, (3) seeing whether your use case aligns with what most agents need. Self-aggregating signal — derived from CF analytics-engine, no PII, just (pack, tool, count). Cached 5min-1h depending on window.

• 2026-10-17classify_rowremoved

  Cheap categorization: given a company and a list of candidate labels, decide which labels apply — the most common GTM/AI usage shape (tagging a list by industry, ICP fit, etc.), one small model call. Same evidence contract as research_row: each label comes back {label, applies, evidence_url, quote, status: found|inferred|not_established} — "found" only when the model's quote is independently verified as a verbatim substring of the text used. Pass text directly (cheapest — no fetch) or entity.domain to fetch the homepage once as a fallback. No text and no domain means every label is not_established with no model call made.

• 2026-10-17research_rowremoved

  Claygent-style per-row research: answer ONE question about ONE company and return a JSON object matching your output_schema, with every field wrapped in its own evidence — {value, evidence_url, quote, status}. status is NEVER self-reported by the model: "found" means this code independently verified the model's quote is a VERBATIM substring of text actually fetched; "inferred" means a value was given but the quote could not be verified; "not_established" means no source answered the field, and its value is always null — never guessed, never a blended score. Sources: "web" fetches the company's own site (entity.domain required — homepage, /about, /leadership) via fetch_url; "catalog" checks entity_profile (SEC EDGAR; resolved:false for a private company is expected, not a failure); "both" (default) tries both. max_cost (USD, default 0.02, max 0.50) scales how many pages are fetched and refuses up front if it is too small to pay for even one extraction call (floor $0.002) — never silently overspends. A row where every source comes back empty costs nothing: every field is mechanically not_established with NO model call made. For a boolean/derived field (e.g. "does this company sell to healthcare"), the quote only has to SUPPORT the value — a descriptive sentence about customers/products counts, the source need not state the answer verbatim. leadership_page_status ("fetched"|"not_found"|"not_attempted", plus leadership_note) says plainly whether a leadership/team page was actually read, so a named-person field (head_of_sales) coming back not_established is distinguishable from "this company just doesn't publish one" vs. "we never checked". model_output_empty:true means the model returned nothing usable (a transport/budget problem) — every field is not_established for THAT reason, never read as 20 individual "no" judgments. Use with a fixed question + schema across many rows for "Claygent over N companies with a hard cost cap" (composes with batch callers). For picking from a fixed label list instead of extracting open fields, use classify_row (cheaper, one model call).

Showing the latest 10. Full history: list_changes · trend: quality JSON.

Checks run on what our credential-free, read-only probes observe; tools are never called and no code audit is performed. How it is computed.