How it works

From upload to a clear verdict

The same shape as an EU panel: independent readings, a step where disagreement is tested, then one senior decision. Below that, how the Commission itself evaluates, because it is worth understanding before trusting any score, including ours.

Our process · about 15 minutes

What happens after you upload

  1. Your Part B is parsed against the real template headings, so every finding can point to a page and section.

  2. The call's requirements become a numbered, traceable list with source excerpts. Paste the portal link and it is fetched for you.

  3. Each seat gets its brief, the marking scheme and whole sections of your proposal. Findings come first, scores last.

  4. Where two seats are far apart on the same criterion, both see the other's evidence, for at most two rounds. Both positions stay in the report.

  5. One decision sets the criterion scores, threshold status and competitive position. Changes are suggested only after scoring.

  6. On the Expert Q&A package, put up to 15 written questions to an experienced EU evaluator, who sees your report and the passages each question is about. Answers in 2 to 3 working days.

See what comes out: the sample report →

Where the people are

The reading is automated. Deciding what counts as good is not.

They encode the marking scheme

Sub-criteria, thresholds, weightings and score-band descriptors are transcribed by hand from the published evaluation form for your type of action, and stored against the version they came from.

They write the evaluator briefs

Fifty versioned profiles: what each seat scrutinises, how strictly it reads, and what it treats as evidence. A brief can be corrected when it reads something the wrong way.

They review the output

Reports are checked for quality, and what that review finds goes back into the schemes and briefs, so a fix reaches every client.

Confidential by default

Your proposal is not marketing material

Processed for one purpose. Your documents produce your evaluation. They are never used to train models and never shared outside the job.

Access only with your say-so. Our staff open a proposal for technical support only when you have agreed to it.

Isolated per organisation. Results are never shared between accounts, even when two of them upload the same document.

Read the privacy notice →

How the Commission evaluates

Three phases, and only the last one reaches you

01

Individual evaluation

Several independent experts read the proposal separately, each recording scores and comments without seeing the others. Independence is what makes the later disagreement informative.

02

Consensus discussion

The experts compare their assessments and negotiate one agreed position per criterion. A comment that survives this stage is one at least two readers were willing to defend.

Where scores move
03

Panel review and the ESR

A panel checks consistency across all proposals, resolves ties and ranks. You receive the Evaluation Summary Report: the agreed comments and scores, and nothing about how they were reached.

The scale

Three criteria, five points each, half marks throughout

Each criterion is scored 0 to 5 in steps of 0.5. For most RIA and IA calls a criterion must reach 3.0 and the total must reach 10.0 of 15. Clearing the threshold and being funded are different questions.

Excellence 0–5.0

Clarity and pertinence of the objectives, ambition beyond the state of the art, and the soundness of the methodology.

Impact 0–5.0

The credibility of the pathway from results to the outcomes the call expects, and the measures to maximise it: dissemination, exploitation and communication.

Implementation 0–5.0

The quality of the work plan, whether effort and resources fit it, and the capacity of the partners to deliver it.

The threshold is the floor, not the target. In oversubscribed calls, proposals well above threshold go unfunded because the ranked list runs out of budget first. That is why our report separates threshold status from competitive position.

The rules that decide outcomes

What the call text does not tell you

  1. RIA and IA, CSA, COFUND, MSCA and ERC each have their own list. One fixed Excellence-Impact-Implementation prompt is wrong for a real share of proposals.

  2. Minor shortcoming, shortcoming, significant weakness. Findings are classified first; the score follows from them.

  3. Evaluators never credit a fix they imagine you could make. Neither do we.

  4. The same weakness cannot be charged against two criteria.

  5. Open science, the gender dimension, social sciences and humanities integration, and AI robustness can each lower Excellence on their own.

Try the readiness simulator →

About 15 minutes · before the panel

Evaluate
before you
submit

One proposal. One deadline. One opportunity to improve it before submission. Upload your proposal and the call, and get the score, the reasons and what to fix.

Start
Chat with us on WhatsApp