Evaluate faster, with a ruling that holds years later.
The terms of a call become a traceable, reproducible and auditable evaluation system: an admissibility review, a matrix with mandatory evidence, fixed criteria and an integrity record that cannot be edited. The final decision remains with the evaluator.
For the body that evaluates, not for the applicant. Whoever submits never sees these screens.
Built on the frameworks and public data of
Reference base loaded today: IDB — 27,329 operations, 507 pages of standards in force, 1,030 debarred firms. The rest are on the roadmap.
A decision that cannot be reconstructed cannot be defended.
Dozens or hundreds of proposals per call, hundreds of pages each, and a ruling that a year later someone will ask to justify. The constraint is not judgement: it is volume, consistency and the record.
Hundreds of pages per proposal
Terms, annexes and supporting documents that have to be read entirely, for every one of them.
Consistency of criteria
Proposals evaluated by different people on different days have to be measured by the same standard.
Decisions without traceability
Reconstructing why a proposal was left out usually depends on the memory of whoever evaluated it.
A score without support
A number with no fragment behind it cannot be audited, appealed or defended.
Platform
Every score, with the fragment that supports it.
A single panel shows what the assistants analysed, what score they proposed and the exact fragment of the proposal that supports it. What cannot be verified is not scored: the system rejects it.
evidence
“The proposal must demonstrate a technological readiness level of at least TRL 7 at submission.”
Terms · p. 18 · verified literally
No score is saved without a verifiable quote from the document. It is not a warning: the system rejects it.
Guarantees
Rules the system always enforces, not just the screen.
A rule that only lives on the screen can be bypassed another way. These cannot.
Admissibility review
What does not meet the terms is excluded before scoring, with the failed rule on the record.
Fixed criteria
Rubric, thresholds and weights are fixed with an integrity seal before the process opens, and cannot be changed during it.
Mandatory evidence
No AI score is stored without document, page and literal quote, verified against the text.
Immutable ruling
Once signed, it is neither edited nor deleted. The integrity record only grows.
Documentation
The system's rules are public
Every rule the system applies is written down and available: which methodological framework governs, what each assistant may assert and what it is forbidden to do. And they are not enforced only by the screen, but by the system itself: a rule that only lives on the screen can be bypassed another way.
Frequently asked questions
What comes up most often in the first conversation.
Does it impose a methodology?
No. It is configured from each call's own terms: the terms are the standard. What the system does require is that every judgement carries its evidence.
Does it replace the evaluator?
No. The assistants propose a score with its evidence; the evaluator confirms it, adjusts it or rejects it. Adjusting requires a written justification; confirming does not. The ruling is signed by a person, and once signed it cannot be edited or deleted.
What happens if the AI is wrong?
It is designed to be detected: every claim carries the page it came from, so it can be checked. And nothing is issued without a person's signature.
A ruling that can be reconstructed at any time.
The terms, the proposals, and a process that leaves every decision on the record.