Named agent - company research

The AI company research agent.

Everything on the record about one company, in one place, dated. What it filed, what it announced, who it named, what it is hiring for, and what is open against it - each line opening the document behind it.

The problem

Researching a single company before a meeting means eleven browser tabs and twenty minutes, and the result lives in somebody’s notes until it goes stale. Doing it for forty companies on a watchlist, repeatedly, is not a thing a person does.

The second problem is trust. A company profile assembled from a database is only as current as the last time somebody refreshed it, and it rarely says when that was. A profile where every line carries its own date and its own source can be checked line by line, which is what somebody does before putting a number in front of a board.

What arrives
  • Accounts - Fit and momentum per company, with the evidence behind both.
  • Round history - Every disclosed round on a timeline, from the filing that disclosed it.
  • Ownership changes - Stake acquisitions and disposals, from beneficial-ownership filings.
  • Risk register - What is open against a company, how severe and how fresh - including proceedings it disclosed itself.
  • Decision-makers - Who a document names, and the document that named them.
Who does the work

The agents on this job, and how each one proves itself

Each line is the agent's own description from the roster the product runs on, not a paraphrase written for this page.

  1. 01 · Scout

    Finds what is on the record. Thirty credible sources, read for every company you watch. The list of sources, and their licences, is on the Trust page.

  2. 02 · Regulator

    Tracks filings and rules. SEC filings and US Federal Register documents, each one opening the filing itself.

  3. 03 · Mapper

    Keeps the decision-makers current. People named only where a document names them, and the document is always linked. Nothing is bought, and nothing is guessed about anybody.

  4. 04 · Historian

    Reads the archive backwards. Ninety days read backwards, with near-duplicate coverage of one story merged into one story.

  5. 05 · Verifier

    Counts how many independent sources actually say it. Every signal carries a verdict: how many independent sources have it, which ones, and how many copies of the same text were discounted. Confirmed, on the record, one source reprinted, or single source - and the sentence explaining which.

    It counts agreement, not truth. Two independent sources can both be wrong, and the verdict says "reported independently", never "verified as fact". It also cannot see a shared origin it has no evidence of: two outlets briefed privately by the same person, who then write their own sentences, read as two voices here.

  6. 06 · Analyst

    Writes the brief. The brief, written from the shortlisted signals, with every line tracing to a dated source.

What it reads

Named sources, every one of them something you could open yourself

Nothing is bought from a data broker. The full source list, and the licence for each, is on the Trust page.

SEC EDGARNamed in SEC filingsUS Federal RegisterGLEIF legal entityWikidataWikipediaGoogle NewsCompany newsroom (RSS)Greenhouse jobsLever jobsOfficers and directorsUS federal awards
What it does not do
  • Filing coverage is strongest where filing is mandatory. A US-listed company has a deep record; a private company in a jurisdiction with light disclosure has a shallow one, and the profile shows which.
  • A company’s own risk disclosures are its own account of its risks. They are reported as disclosures, with the filing linked, not as findings.
  • People are named only where a document names them, and nothing about a person is inferred.
  • It does not value a company, and it does not estimate revenue that was never disclosed.
Which plan

Available on every plan. The number of companies watched, and how often each is re-read, is what the plans differ on.

Questions

What people ask

Which registers does it read?
SEC EDGAR including full-text search, the US Federal Register, the GLEIF legal entity register, US federal award records, UK contract notices, Wikidata, and the company’s own newsroom and job boards. Each line in a profile links the record it came from.
Does it cover companies outside the United States?
Partly, and the profile is explicit about it. Hiring, newsroom, pricing pages, open-source activity and GLEIF entity data are global; the deepest filing coverage is US, and the industry pages say where that leaves each sector.
How current is a profile?
As current as the last collection run for that company - weekly on Starter, every six hours on Growth and Enterprise - and every line carries its own date so you can see what is fresh and what is not.

See it on your own market.

A working run against the companies you actually care about, not a recorded video.