About The Demand Signal

What this is

The federal government announces what it intends to buy long before it buys it. Those announcements are public, and they are close to unreadable in bulk: tens of thousands of notices a week, most of them irrelevant to any particular reader, many of them the same requirement posted by several offices at once.

The Demand Signal reads them and ranks them for relevance for the tech builders who can deliver what the government needs from the deep tech world. Get insights fast into how you can serve key government missions. Demand Signal covers AI & Autonomy, artificial intelligence, machine learning, autonomous systems, Biotech, Quantum, Robotics, Cloud Compute, Cybersecurity and the infrastructure required for all these.

Our goal: informing your decisions so you can win and serve.

How it is built

Two tiers, and they meet only at a database. Collection, extraction and drafting run on an NVIDIA DGX Spark on premises. The Postgres on that machine is the system of record and is not reachable from the internet. Nothing inbound, outbound only.

Every night a job pulls the SAM.gov and other sources, filters new data against the edition's vocabulary, fetches full descriptions for anything that matched, and hands the new items to a model for extraction. A separate job then writes a projection of the results to a hosted Postgres database. This site reads that projection through a role with SELECT and nothing else. Corrections are applied to the system of record and travel outward from there, so the two tiers cannot disagree about what was published.

Every model call in the pipeline runs on that machine, on open-weight models. Extraction, scoring and the daily summary never leave it. That is a deliberate constraint rather than a cost decision: it keeps the analysis reproducible on hardware we control, and the pipeline works the same way whether or not any particular vendor has capacity today.

Scoring

Each notice gets a relevance score between 0 and 1, assigned against a five-band rubric with worked examples at every band. The question the score answers is narrow: is this procurement one a deep tech capability can service?

Procurement stage is handled separately, and deterministically, from the notice's own text. An intent to sole source, a cancelled requirement and a completed award are all real, and none of them is demand a reader can act on, so each ranks below its subject score. Mixing that judgment into the scoring prompt was tried and abandoned: the model began conflating subject with stage, and it took three passes to separate them again. A prompt is a request. Validation is a rule.

Cross-posted notices are collapsed to one line at the median of their copies. Taking the highest copy, which is what the obvious database query does, makes a displayed score the maximum of several samples, so a requirement posted nine times would outrank an identical one posted once. That is a sampling artifact, not a signal. The number you see is the median, and the line tells you how many postings it represents.

Summarizing

One model call a day writes the summary at the top of each page. The same text opens a daily brief, so the site and the brief cannot describe the same day differently.

Sources

We pull from SAM.gov, Department of War contract announcements, DoD SBIR/STTR topics, NIH/HHS funding opportunities, and Grants.gov.

Mission driven editions

Each edition tracks one government demand vertical: its own solicitations, its own awards, and a daily summary ranked by relevance to disruptive technology.