Methodology
Every factual claim in a Note carries a label telling you exactly how well-supported it is. This isn't decoration — the labels are load-bearing. If you're deciding whether to commit bid-team hours off the back of a claim, you should know whether it's a fact from an official filing or a judgment call, and how confident that judgment call is.
The four tiers
Stated directly in an official record — a TED notice, a national contract register, a company registry entry. No interpretation. If it's OBSERVED, the source document says it in those terms.
A mechanical computation over OBSERVED facts — a sum, a count, a share, a date difference. No judgment involved, but coverage matters: a sum over 2 of 5 known values is disclosed as a partial sum, not silently presented as the whole picture.
An interpretation that goes beyond what the records state outright — what a pattern probably means. Every inference carries an explicit confidence level (HIGH / MEDIUM-HIGH / MEDIUM / MEDIUM-LOW / LOW) and, where the evidence is genuinely ambiguous, the competing explanations we didn't rule out.
A concrete next step — a specific register, filing, or document — that would let you confirm or overturn the inference yourself, before you rely on it for a bid decision.
Sources
- TED (Tenders Electronic Daily) — EU/EEA contract-award notices. © EU, reused under CC BY 4.0.
- National procurement and company registers — e.g. Czech Registr smluv / or.justice.cz, Dutch KvK, Bulgarian Commercial Register — used to resolve buyer and winner identities where a national ID is available. More national registers are being added; a country not listed here can still often be covered directly from TED, just without that extra identity-resolution layer.
Every source is official and open-licensed. We don't scrape paywalled databases, and we don't represent third-party commercial data as our own.
Independent review, not self-check
Before a Note reaches a human for sign-off, it's checked by more than one AI model, from more than one provider, working independently of the model that drafted it and of each other. Each reviewer scores the Note and can flag it as not ready — a Note doesn't advance on the drafting model's own say-so. That's a structural check, not a single model marking its own work.
What we don't do
- We don't give bid advice or legal advice — a Note tells you what the records show and what it plausibly means, not what to do about it.
- We don't paper over gaps. Where a record is missing, unresolved, or a value looks implausible (some notices carry obvious placeholder values), that's flagged as an explicit data gap, not silently excluded or silently included.
- We don't upgrade a confidence level to make a finding sound more decisive than the evidence supports.
When we're wrong
If a later review finds a Note got something wrong, the correction is published in the Note itself, in place, not quietly edited away. Note #001 has a live example — an earlier version treated "1 tender received" as evidence of low competitor interest; a later review caught that this is a structural artifact of how a certain framework type reports call-offs, not a sign of an uncontested market. The correction is printed directly in the Note, with what changed and why.
Who checks the work
The full account of how much of this is automated and where analyst sign-off happens is on the Transparency page.