US Government Contracts — Federal Awards Search (AI)

See exactly who is winning US federal money — and what that means for your pipeline. Hand this Actor a company name or a keyword like cybersecurity, and it searches the official USAspending.gov award data: every federal contract and grant that matches, who won it, how much, and from which agency. Then OpenAI reads the whole award set and writes a plain-English summary of that company's or sector's federal footprint — totals, top agencies, the kinds of work being funded, and a one-line opportunity signal for a B2G seller.

You bring names or keywords. It hands back the money trail plus the read on it.

---

The flow

1. Give company names or keywords     2. USAspending.gov API              3. Get awards + AI summary
   (e.g. "Palantir",              →      official federal award      →      one row per award +
    "cybersecurity")                      data, no key needed                a footprint summary

1. List your queries — company / recipient names (Booz Allen, Palantir) or keywords describing a sector (cybersecurity, satellite, nursing).
2. The Actor calls the public USAspending API for each query, pulling the top awards by dollar amount in your look-back window.
3. OpenAI summarises the footprint — grounded strictly in the award rows, never inventing amounts — and you get a clean dataset: one record per award plus one summary record per query.

---

What you get per query

For every query, the Actor:

1. Pulls the top federal awards by amount from USAspending.gov for your chosen award types (contracts and/or grants) and look-back window (default 3 years). One dataset record per award: awardId, recipient, amount, awardingAgency, subAgency, startDate, endDate, awardType, description, and a direct usaspendingUrl to the award page.
2. Aggregates the set — totalAwards, totalAmount (sum of award amounts), topAgencies and topRecipients (with dollar totals and counts).
3. Summarises with AI (OpenAI gpt-4o-mini, a fast and low-cost model), grounded only in the data:
   • summary — 2–3 sentences on the federal footprint (totals, main recipient, main agency).
   • topAwards — the largest awards (awardId, recipient, amount, agency, whatFor).
   • themes — what kinds of work the awards fund.
   • notableAgencies — the agencies that show up most / spend most.
   • opportunitySignal — one sentence: for a B2G seller, where the budget and the buyers are.

All of this lands in one recordType: "summary" row per query.

---

Three ways people use it

• B2G / government sales intelligence — see which agencies actually fund your category, how big the deals are, and which incumbents hold the federal contracts today. Walk into a GovCon pitch already knowing the money trail from the USAspending API.
• Competitor federal-win tracking — drop in a rival's name and read their government awards history: total federal revenue signal, which agencies buy from them, and the kinds of federal contracts they keep winning.
• Market / sector research — search a keyword (AI, cybersecurity, logistics) to map a whole B2G sector: top recipients, spending agencies and funding themes across years of government awards — ideal for market sizing, diligence and investor research.

Keywords: federal contracts, USAspending API, government awards, GovCon, B2G, federal grants, government spending data, public procurement, award search.

---

Input

Field	Type	Notes
queries	array	Required. Company / recipient names OR keywords. One per line. Each is searched and summarised.
awardTypes	array	contracts (codes A/B/C/D) and/or grants (codes 02/03/04/05). Default ["contracts"].
timePeriodYears	integer	Look back this many years from today. Default 3.
maxAwardsPerQuery	integer	Top awards (by amount) to pull per query. Default 25.
maxResults	integer	Max queries to process. Default 100.
maxConcurrency	integer	Queries processed in parallel. Default 3.
model	string	Override the OpenAI model. Default gpt-4o-mini.

Minimal input example

{
  "queries": ["Palantir", "Booz Allen", "cybersecurity"],
  "awardTypes": ["contracts"],
  "timePeriodYears": 3
}

---

Output example

An award row:

{
  "query": "Booz Allen",
  "recordType": "award",
  "awardId": "47QRAA20D000X",
  "recipient": "BOOZ ALLEN HAMILTON INC.",
  "amount": 318450000.0,
  "awardingAgency": "Department of Defense",
  "subAgency": "Department of the Army",
  "startDate": "2021-09-30",
  "endDate": "2026-09-29",
  "awardType": "Delivery Order",
  "description": "IT AND TELECOM- IT AND TELECOM SUPPORT SERVICES",
  "usaspendingUrl": "https://www.usaspending.gov/award/CONT_AWD_..."
}

A summary row (one per query):

{
  "query": "Booz Allen",
  "recordType": "summary",
  "totalAwards": 25,
  "totalAmount": 2140000000,
  "topAgencies": [
    { "agency": "Department of Defense", "amount": 1450000000, "count": 14 },
    { "agency": "Department of Homeland Security", "amount": 410000000, "count": 5 }
  ],
  "topRecipients": [
    { "recipient": "BOOZ ALLEN HAMILTON INC.", "amount": 2140000000, "count": 25 }
  ],
  "themes": ["IT and telecom support", "cyber and intelligence analytics", "systems engineering"],
  "notableAgencies": ["Department of Defense", "Department of Homeland Security"],
  "topAwards": [
    { "awardId": "47QRAA20D000X", "recipient": "BOOZ ALLEN HAMILTON INC.", "amount": 318450000, "agency": "Department of Defense", "whatFor": "IT and telecom support services" }
  ],
  "opportunitySignal": "Defense IT and cyber budgets dominate this footprint — a B2G seller of secure IT services should target DoD and DHS program offices.",
  "summary": "Booz Allen's recent federal footprint is concentrated in Defense IT, cyber and analytics work, led by large DoD delivery orders. The Department of Defense is by far the dominant buyer, with Homeland Security a distant second."
}

---

Pay-per-event pricing

This Actor uses pay-per-event billing with a single event:

Event	Charged when	Price
query-analyzed	Once per company or keyword searched against USAspending and summarised with AI.	$0.15

The Actor logs its OpenAI token usage and the estimated AI cost at the end of every run, so the event price always stays safely above the model cost.

---

Data source

All award data comes from USAspending.gov — the US government's official, free, public source of federal spending data, via its open API (no API key required). This Actor reads only published award records; it does not add or alter any figures.

---

Setup

The AI summary calls the OpenAI API. Set the environment variable / secret OPENAI_API_KEY on the Actor. Without it the run stops before the summary — the award search itself needs no key.

---

Use it from an AI agent (Apify MCP server)

This Actor is available through the Apify MCP server, so AI agents (Claude, ChatGPT, or anything that speaks MCP) can call it as a tool — hand it queries, and read back the federal awards and footprint summary — with no custom integration code.

---

Run it locally

npm install
# put your input in storage/key_value_stores/default/INPUT.json
export OPENAI_API_KEY=sk-...   # required for the AI summary
apify run -p

---

Related actors

• Nordic Public Tenders — NO/FI/SE public procurement tenders normalised into one English schema.
• AI Company Enrichment — Turn a list of domains into structured company profiles — firmographics, contacts, socials and ICP fit.
• B2B Account Brief — AI account research briefs for B2B sales teams.
• SEC Filings Extractor — Pull structured data from US SEC filings.

---

Part of the No Niner toolkit — no-code web scraping, enrichment & AI data tools, all pay-per-use. Browse the full set at noniner.io.