An AI due diligence analyst that shows its sources

Diligence is reading 40 tabs and remembering what each one said

A pre-investment screen or a vendor check starts the same way: a name, a website, and four hours of opening Crunchbase, Companies House, the trade press, an old interview write-up, and a court records portal, then trying to reconcile a founding date that three sources disagree on. The work isn't hard. It's the volume of tabs and the discipline to write down where each fact came from.

The agent runs that pass for you. Give it a company and the questions you care about, and it searches the open web, browses the pages that matter (including the JS-heavy ones that block scrapers), pulls structured data from APIs like a registry or a funding database with your own keys, and writes it up as a brief where every line traces back to a URL.

What a single run pulls together:

• Corporate basics: legal entity, incorporation date, registered address, directors, and ownership where it's public
• Funding and investors from press and database APIs, with round dates and lead investors cited
• Founders and key people, prior companies, and anything notable in their public track record
• Red flags: litigation mentions, regulatory actions, layoffs, negative press, or domain/site signals that don't add up
• A confidence note on each section, so you know what's confirmed versus what's a single uncorroborated source

It is not a verdict. It's the reading and the bookkeeping done in minutes instead of an afternoon, with the citations intact so a partner or compliance reviewer can check the work instead of taking it on faith.

Related pages in this workflow

These pages cover the adjacent jobs buyers usually compare before choosing an AI agent.

• AI Equity Research Analyst — Hand it a ticker, get a cited brief — built from the 10-K, the latest call, and live multiples, every claim linked to its source.
• AI Data Analyst Agent — A data team without the headcount: point it at a CSV or Sheet and ask in plain language — it cleans, charts, and answers, with full undo.
• AI Research Agent — Hours of digging, back in minutes: it reads the full sources and hands you a structured report with every claim cited.
• AI Research Analyst — Hand it a question and a deadline, get a brief that shows its work — figures, links, and the page each number came from.
• AI Grant Research Analyst — Finds the grants you actually qualify for: it reads the RFP, checks your eligibility, and hands you a sourced one-pager with the ask and deadline.
• AI Competitive Intelligence Analyst — The whole market, read for you: it watches competitor pricing, changelogs, and job boards and drops a cited brief the moment something moves.
• AI Healthcare Research Analyst — Ask a clinical question, get an answer you can defend: a structured brief where every claim links to the paper, trial, or guideline.
• AI Brand Monitoring Analyst — Reads the whole thread, not the headline: it checks the sites you watch each morning and briefs you on what actually changed overnight.

Frequently asked questions

How is this different from just asking ChatGPT about a company?

A general chatbot answers from training data and will confidently state a funding round or director that's two years stale, with no source. This agent searches and browses live pages at the moment you ask, and attaches the URL behind each claim so you can check it. The point of diligence is verifiable provenance, not a fluent guess.

Can it use paid data sources we already subscribe to?

If the source has an API, yes. You connect it as a REST call with your own credentials and the agent pulls structured data from it — a company registry, a funding database, a sanctions or watchlist API. It uses your keys; we don't resell or store the data.

Does it make a buy or pass recommendation?

No, and that's deliberate. It assembles and cites the evidence so a human makes the call. It will flag thin or contradictory evidence with a confidence note, but it won't pretend a single blog post is a confirmed fact or hand you a verdict you'd then have to defend.

How does it handle conflicting information across sources?

When sources disagree — say, two founding dates or two different CEOs — it surfaces both with their citations rather than silently picking one. Its memory also flags contradictions across runs, so if last month's brief said one thing and this month's says another, you'll see it.

Can it screen a list of targets, not just one?

Yes. Drop a Sheet of company names and it works through them, writing the brief or a row of key fields back next to each one. Useful for a sourcing funnel or a vendor batch where you need the same five questions answered across thirty names.

How much does it cost?

$49/month or $490/year — cancel anytime. That covers the agent, its inbox, scheduled re-checks, and connected APIs — you bring your own keys for any paid data sources. Setup takes about four minutes, and Fasrad is in public beta.

AI research analysts by field

One research agent that searches, reads, and cites — pointed at the sources and questions your field cares about.

• AI Research Analyst (hub) — Hand it a question and a deadline, get a brief that shows its work — figures, links, and the page each number came from.
• AI Academic Research Analyst — It reads the papers, not just the abstracts — a synthesized brief with inline citations, source links, and the contradictions flagged.
• AI Brand Monitoring Analyst — Reads the whole thread, not the headline: it checks the sites you watch each morning and briefs you on what actually changed overnight.
• AI Competitive Intelligence Analyst — The whole market, read for you: it watches competitor pricing, changelogs, and job boards and drops a cited brief the moment something moves.
• AI Data Analyst Agent — A data team without the headcount: point it at a CSV or Sheet and ask in plain language — it cleans, charts, and answers, with full undo.
• AI Equity Research Analyst — Hand it a ticker, get a cited brief — built from the 10-K, the latest call, and live multiples, every claim linked to its source.
• AI Grant Research Analyst — Finds the grants you actually qualify for: it reads the RFP, checks your eligibility, and hands you a sourced one-pager with the ask and deadline.
• AI Healthcare Research Analyst — Ask a clinical question, get an answer you can defend: a structured brief where every claim links to the paper, trial, or guideline.
• AI Junior Consultant — Brief to deliverable in a single session: it runs the research, organizes the findings, and builds the deck and the client-ready PDF.
• AI Legal Research Analyst — A memo where every claim has a link you can check: it searches the open web and reads the actual opinions and filings.
• AI Market Research Agent — A cited competitive briefing in your inbox on the cadence you set — competitors watched, trends tracked, a source behind every line.
• AI Market Sizing Analyst — TAM/SAM/SOM that shows its work — top-down and bottom-up, every figure traced back to the source it came from.
• AI News Briefing Agent — One briefing every morning, built around your world: your industry, your tickers, your topics — scanned, summarized, and waiting in your inbox.
• AI Policy Research Analyst — It reads the actual bill, not the press release — a sourced brief with section citations, agency dates, and the dissenting view.
• AI Procurement Research Analyst — A sourcing request, back as a cited supplier brief: shortlisted vendors, pricing signals, and lead times, with a source behind each.
• AI Real Estate Market Analyst — A neighborhood read in one sourced doc — comps, days-on-market, price per square foot, inventory trends — instead of twelve open tabs.
• AI Research Agent — Hours of digging, back in minutes: it reads the full sources and hands you a structured report with every claim cited.