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.

Verdict pipeline · multi-agent Running

01 · Orchestrate

Plan the diligence

02 · Research

Investigate each dimension

03 · Cross-check

Source every claim

04 · Conclude

Deliver the verdict

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.

Verdict pipeline · multi-agent Running
01 · Orchestrate Plan the diligence

The orchestrator splits the company into the report's ten dimensions and briefs an agent for each.

02 · Research Investigate each dimension

Each agent reasons between its tool calls, pulling sources and weighing them as it goes, not answering in a single pass.

03 · Cross-check Source every claim

Material claims are cited or flagged as inference. Thin signals are surfaced, not smoothed over.

04 · Conclude Deliver the verdict

A ranked risk register and a clear call land on page one, with the evidence behind it.

Every report runs a multi-pass adversarial loop: an independent critique pass challenges each finding, a machine-checked claim table verifies every load-bearing fact against its cited source, and a consistency linter blocks delivery until the numbers agree. Single-pass generation can't do that.
3

Gates every draft passes before delivery: an adversarial critique, a machine-checked claim table, a consistency linter.

10

Dimensions investigated separately, one research agent per report section, briefed by the orchestrator.

100%

Of material claims sourced or flagged as inference. Where a signal is thin, the report says so.

An independent, outside-in read, 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, and is built to find the red flags that never make it into the data room. Four passes carry it to investor grade.

01
Quantitative-anomaly pass
Per-unit economics checked against named peer benchmarks, so the numbers that don't add up get caught.
02
Adversarial short-seller pass
A dedicated pass builds the bear case on purpose, the argument for why this fails, so you never get a brochure.
03
Critique and revise
The draft is critiqued against its own evidence and rewritten, not shipped on the first pass.
04
Calibrated verdict
A credible, unresolved red flag forces a cautious call. The verdict is weighted toward the cost of being wrong.

Every estimate is labeled. We tell you what we couldn't verify, too.

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.

1

Intake

Tell me 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.

~2 min · no call

2

Multi-agent research

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.

10 dimensions · sources cross-checked

3

Human QA

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.

Manual review · before delivery

4

Delivery

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. Five days on Standard, or 48 hours on Express.

PDF + Word + brief · 5 days Standard / 48h Express

A slim Verdict report with an emerald ribbon and flagged pages resting on a long desk in soft window light

The output

Ten dimensions in. One verdict out.

Sourced, or flagged. Never invented.

A report is only useful if you can trust what's in it, and check it. Every material claim is either cited to a source or marked as inference, so you always know which is which. Where the public signal is thin, the report says so plainly rather than dressing a guess up as a finding. The confidence you read is the confidence that's actually there. In practice that evidence spans the company's own disclosures and product and engineering footprint, major press coverage, analyst and market-research estimates, funding data, and developer-survey signal, the same classes cited throughout the published sample.

01
Every claim, traceable
Material claims are cited to a source you can open and verify yourself.
02
Inference, labelled as inference
Where a conclusion is reasoned rather than sourced, it's marked, not passed off as fact.
03
Thin signals, surfaced
If the public record is sparse on a dimension, the report says so rather than inventing confidence.
04
Confidence you can read
A per-report confidence level, grounded in how much evidence actually backs the verdict.

Before selling a single report, we ran Verdict head-to-head against three published investigations and published the finding-by-finding comparison, misses included. Read it and disagree.

A single prompt gives you a plausible summary. This gives you structure, sourcing, and the discipline to look for what's wrong.

Each dimension is researched separately, claims are checked against sources, and the whole thing is built to surface red flags rather than smooth them over. You get a citable artifact, not a paragraph.

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.

First 3 to reach out: first report free · questions