IA na Prática: AI systems built and operated for your company. Learn more

PT Start a project

our own product · built and run by us

TRINTA

A public tender radar. It reads the official sources every day, reads the attached documentation, scores each tender 0 to 100 against how well it actually fits the company, and delivers what matters. This is not a case study written from the outside: TRINTA is ours, from the first line of code to the customers using it today.

1,000+ public procurement platforms mapped
~30 languages in the relevance engine
0 to 100 AI-audited score on every tender
EUR 700k the first tender it found, won in two weeks

The problem was never a shortage of tenders.

It was not seeing them in time. They sit scattered across hundreds of official portals, each with its own format, language and calendar. Some only open with JavaScript. Some bury the deadline halfway through a PDF. Whatever went unfound on a Monday morning went unbid.

how it works

Five steps, every day.

The work is not writing the first connector. It is keeping a thousand of them alive while the portals change underneath.

01

Read

A dedicated connector per portal pulls notices from the official source. Each runs isolated, with its own retries and timeout, so a portal that goes down never stops the harvest.

02

Filter

The relevance engine decides what matters, across roughly 30 languages, with CPV codes and a weak tier that lets borderline cases through for the AI to judge.

03

Enrich

Tender documents get resolved and read. The real deadline often exists only inside a PDF, so that is where we go and get it.

04

Score

Deterministic triage first, AI audit second. The audit reads the documentation and writes the final score, 0 to 100.

05

Deliver

What matters rises to the top of the board, into the 7am email and, where it earns it, onto WhatsApp. The rest stops stealing anyone’s time.

Tested against real tenders

93 regression cases taken from genuine notices. If one breaks, the build fails and nothing ships.

It runs itself

Four passes a day in the cloud, a brake against runaway cost, an email alert when a connector falls sick.

One engine, many clients

Tenant by domain, isolation verified at build time, keywords generated from each client’s own catalogue.

the score

The AI scores. The rules stop it exaggerating.

An enthusiastic model is worse than no model, because it manufactures false confidence. So the AI’s score passes through deterministic caps it cannot get around. We would rather have a low honest number than a high invented one.

Two stages

First a deterministic triage on product fit, geography, value and runway. Then the AI audit, which reads the official page and up to six attached documents and writes the final score.

Brakes against optimism

The score is capped by deterministic rules the AI cannot talk its way past. No product matches caps it at 40. Only low-confidence matches, 55. Only a high-confidence match can go past 72.

Inventing is forbidden

If no document was actually read, every match the model returned is deleted and the score is capped at 25. This rule exists because of a real case where an audit mapped products onto a tender it had never read.

Audit everything, or publish nothing

If any tender is left un-audited, the process exits with an error. Since publishing comes after, an un-audited tender can never reach the site. The rule lives in code, not in procedure.

beyond finding

Finding is half of it. Winning is the other half.

Who wins, and for how much

We harvest contract award notices carrying a named winner and a value. Out of those come incumbents per buyer, price bands, expected bidder counts and a read on win probability.

Before the tender exists

European prior information notices are harvested as signals. And a framework contract getting old is itself a signal that a re-tender is coming.

A portrait of the buyer

Every contracting authority gets its own page, with history and the suppliers it habitually works with.

A bid draft

From the tender and its audit comes a compliance matrix, requirement by requirement. Anything without evidence is marked as a gap, not filled in with good intentions.

Scored opportunities list
opportunities, scored
Tender detail with its audit
the audit, per tender
Pre-tender signals
signals, before the tender

the proof

EUR 700,000 in the first week.

TRINTA was born inside Ultra Controlo, a 40-year-old Portuguese medical-gas manufacturer serving more than 80 countries. In its first week it found a EUR 700,000 tender the company had never seen. It won it two weeks later. In month one the radar surfaced more than EUR 30 million in qualified opportunities.

We say this plainly: Ultra Controlo is the founder’s family company. That is where the system proved itself, on a real pipeline, before it was sold to anyone.

Want one of these for your operation?

TRINTA is what we build when the problem is our own. If you have a problem shaped like that, give us fifteen minutes and we will tell you honestly whether it is worth doing.