Here is how the machine works.
A single prompt gives you a plausible summary. Verdict works the way an analyst actually works: divide the company into the questions that matter, investigate each one separately, cross-check the claims, then conclude.
One orchestrator model runs that division of labour across a team of research agents.
Divide · investigate · cross-check · conclude · the same path an analyst runs by hand
One orchestrator. Ten investigations.
The orchestrator model assigns each report section to its own research agent. Each agent reasons between its tool calls, pulling sources, weighing them, and cross-checking, rather than answering in one pass. It is the same architecture Anthropic published for its own multi-agent research system.
The discipline, in three numbers.
Gates every draft passes before delivery: an adversarial critique, a machine-checked claim table, a consistency linter.
Dimensions investigated separately, one research agent per report section, briefed by the orchestrator.
Of material claims sourced or flagged as inference. Where a signal is thin, the report says so.
Built to surface what the data room hides.
An in-house tool tells you what you already have. Verdict reads a company from the outside in, from public sources, built to find the red flags that never make it into the data room.
Four passes carry it to investor grade. Open each one.
From a name to a verdict, in four steps.
What happens between the moment you send a company over and the report landing in your inbox. No call required at any point.
Tell us what you're deciding
The company name, its website, and the decision you're making. Optionally, the concerns you want prioritized and any documents you can share. Under two minutes, and the only step that needs you.
Each dimension, investigated
The orchestrator briefs a research agent per section. Each one investigates its dimension on its own, pulling sources and cross-checking claims against them as it reasons.
The high-stakes facts, checked by hand
Before any report ships, the claims that would change your decision, funding, ownership, the top red flags, are verified by hand. The pipeline does the research; a person signs off on what matters most.
A report you can act on
The finished report arrives as a PDF, an editable Word file, a one-page brief, and an IC-ready memo. Verdict on page one, ranked red flags, every claim cited.
Ten dimensions in. One verdict out.
Verdict · Method
How we plug into your deal without touching it.
You never send us anything the seller did not already give you, and we never contact the seller at all. Access runs through you, under the NDA you already signed. The same structure every diligence firm uses.
You sign the NDA as normal and receive the financials
Nothing about your process changes. You are the principal on the NDA; we never appear in it.
Your NDA almost certainly already covers us
Standard M&A confidentiality agreements carry a representatives clause permitting disclosure to your accountants, consultants, and advisers. Brokers read an outside reviewer as a serious-buyer signal, not a breach.
If the seller wants paper, we sign it the same day
A one-page confidentiality undertaking, kept ready, signed toward you or countersigned toward the seller, whichever the language requires. No negotiation, no delay.
Documents in, report back in 48 hours
P&Ls, tax returns, bank statements, the aging schedule, whatever the data room gave you. The report comes back as a written document you can forward to your lender, attorney, or co-investor exactly as received.
Why the 48 hours is the point. Full financials usually open after an accepted LOI, and the review window inside most purchase timelines is two to three weeks. A three-to-four-week engagement consumes it.
A 48-hour turnaround leaves you the rest of the window to renegotiate, verify, or walk. The pricing page shows what that window costs everywhere else.
What we never do: contact the seller, the broker, or the platform about your deal. Ask for logins or direct system access. Share, retain rights to, or reuse anything you send. Materials serve your report and nothing else, destroyed on request.
A prompt gives you a summary. This gives you discipline.
Running the AI yourself
A plausible summary in one breath. Confident, fluent, and unexamined.
- One pass over everything, no division of labour
- Claims stated, not checked against sources
- Optimized to sound helpful, so red flags get smoothed over
- A paragraph you can't cite to anyone
Structure, sourcing, and the discipline to look for what's wrong
Each dimension researched separately, claims checked against sources, the whole thing built to surface red flags rather than smooth them over.
- Ten dimensions, one research agent each
- Every material claim sourced or labelled as inference
- An adversarial pass paid to argue the deal fails
- A citable artifact, not a paragraph
The same machine, four seats.
Every service below runs on this pipeline. Due diligence is the anchor; the sourcing discipline is identical from the first listing to the final price.
Have a company you're evaluating?
Send it over. You'll have a confirmed quote and delivery date within one business day, and the report by the end of the week, or in 48 hours on Express.
Backtest it on a deal you've already closed · questions