BoardBrain
Request a briefing
Why it’s true

The difference between directionally right and decision-grade.

Most AI reading of a public company is directionally right. A boardroom needs more than direction — it needs facts it can act on, and a way to check them. This page is how BoardBrain earns that trust: by construction, not by promise.

01 — No invented facts

No fact touches the model.

Every fact, quote, number and name in a BoardBrain file is extracted and verified first, and locked. The language model is used only to interpret and narrate around those locked facts — it never generates them. A missing fact fails the build; it is never invented.

A general assistant uses the model far more broadly — to find, to summarise, to phrase — which lets it take shortcuts and produce fluent text that can be confidently wrong. We removed that exposure by design. That is the scientific reason BoardBrain does not hallucinate on facts, and a general assistant can.

How a fact reaches the page
1

Extract. The fact is pulled from the filing, transcript or note — with its exact location kept.

2

Verify. Checked against the source, and against the company’s own record and its peers.

3

Lock. The verified fact becomes immutable. The model can reference it, never rewrite it.

4

Narrate. Only now does the model write — around the locked facts, citing each one.

Click any figure in the product and the source opens: the filing line, the transcript page, the note.

02 — The corpus

Reading a general assistant cannot do — and will not pay for.

Behind each company file sit thousands of documents — the company and every peer, roughly a decade deep — assembled in three tiers. The sector is pre-digested before the company is read, so the file knows best-in-class economics and exactly where the company sits against them.

Tier 1 · Public

Filings across every exchange the company touches; earnings wires, transcripts and capital-markets-day material; the trade press.

Tier 2 · Behind paywalls

Licensed sell-side research, premium press, industry and regulatory material, specialist pricing data — paid sources a general assistant cannot access at all.

Tier 3 · Proprietary

The activist and precedent library, the management-commitment database, the theme-classification grid, the ownership and control map — built by us, per company.

That reading is paid for once, up front. A general model must keep the work behind each answer small, because every query is priced on demand — so it answers from a thin slice. BoardBrain answers every question from the full, verified asset, in seconds.

Corpus scale: 1,000–5,000 documents per company, order of magnitude, varying by sector and peer-set size.
03 — The worked example

What the board pack didn’t say.

A European carmaker, from a live BoardBrain file, anonymised. Management’s story, against the record — and the disclosures the board never received.

 NARRATIVE GAP · STORY vs RECORD
MANAGEMENT’S STORY
“Strong progress on our electrification roadmap.”
THE RECORD BOARDBRAIN SURFACES
Missed the stated fully-electric target by a wide margin, then recast progress as “electrified” — a broader definition that lifts the figure. Shareholder return deeply negative against dividend-paying peers over the same period.
7
MET
2
DELAYED
3
ABANDONED
MANAGEMENT-COMMITMENT TRACKER · 12 PROMISES SCORED

What management left out

No regional margin split — although the two closest premium peers disclose it.

No electric-vs-combustion profitability — although the pure-play leaders report it quarterly.

No capital-return policy, despite substantial and recurring free cash flow.

No platform economics and no return-on-investment for the autonomous-driving programme.

The director walks in knowing what was recast, what was missed, and what was never disclosed — and asks the question that follows. In product, every line above carries its source.

Worked example from a live file, anonymised for publication. Figures shown in product are source-traced.

04 — The benchmark

Same question. Different class of answer.

We put identical board questions to a general assistant and to BoardBrain, and scored the answers on the dimensions a boardroom actually needs: fiduciary tension, accountability framing, governance depth, decision-grade questions. The gap is 3–6 points where it counts.

Our own benchmark, on worked examples — which is why we’d rather you ran the test yourself: name a company you know, and judge the file against your own knowledge of it.

Run the test
Scored out of 10 · general assistant vs BoardBrain
FIDUCIARY TENSION ACCOUNTABILITY FRAMING GOVERNANCE DEPTH DECISION-GRADE QUESTIONS
BoardBrain benchmark, 2026 · worked examples · grey: general assistant, red: BoardBrain
05 — Human judgement on top

Reviewed by people who spent careers being wrong expensively.

The method — and the files it produces — are reviewed by a senior circle: former investors, equity-research leadership from a leading investment bank, and practitioners from the strategy and activist worlds. Nothing ships unread: every file is challenged and signed off by a senior reviewer before a director sees it.

The system is deliberately constrained to what the evidence supports: a general model is built to please and to be fluent; this one is built to be checkable.

Nothing is asserted that cannot be shown. If a claim on this site reads confident, it is because the file behind it can be opened.

The standing checklist for any reading of your company
01

Can every number be traced to a source you can open?

02

Was the company read against its full peer set, or in isolation?

03

Are management’s past commitments scored against outcomes?

04

Does it end in questions a board can actually put to the CEO?

05

Who is accountable for it being right — a person, or a prompt?

Apply it to anything you are handed — including us.

The strongest proof is a company you already know.

Name it. Judge the file against twenty years of your own knowledge.

Request a briefing