Understanding your results

After the analysis finishes, you get a structured report. Here's how to read it.

Strategic briefing

This is at the top of the results page. It gives you three things:

1. A recommendation - one of four levels:

   • Strong Submit - the proposal looks solid, minor or no issues found
   • Submit with Improvements - the proposal is decent but has gaps that should be addressed
   • Significant Revision Needed - serious problems were found, submitting as-is is risky
   • Do Not Submit - critical compliance failures, likely to be rejected

2. Concern counts - how many findings at each severity level (e.g., 2 Critical, 5 Major, 8 Minor, 3 Notes, 4 Strengths)

3. Summary - a few paragraphs explaining the overall assessment in plain language

Start here. If the recommendation is "Strong Submit" and you only see minor findings, you might not need to dig into every detail. If it's "Significant Revision Needed", you'll want to read every critical and major finding carefully.

Findings

Below the briefing, you'll see a list of individual findings, sorted by severity. Each finding includes:

Description

What the AI found. For example: "The proposal does not include the required ISO 9001 certification. The RFP states this is a mandatory requirement in Section 3.2."

Severity

Critical, Major, Minor, Note, or Strength. See key concepts for what each means and how to respond.

Evidence

This is what makes the findings useful. For each issue, you get exact quotes from the documents:

• From the RFP: the requirement being checked (e.g., "The bidder must hold a valid ISO 9001:2015 certification")
• From the proposal: what the vendor actually said (e.g., "Our company is currently pursuing ISO 9001 certification and expects to achieve it by Q3 2026")

The evidence lets you verify the AI's reasoning yourself. If the quotes don't support the finding, you know to disregard it.

Verification status

For Critical and Major findings, the verification agent weighs in:

• Verified - a second AI confirmed the finding. Higher confidence.
• Downgraded - the verifier thinks it's less severe than initially assessed. The severity gets adjusted.
• Removed - the verifier concluded it's a false positive. You'll still see it, but it's marked accordingly.

Verification doesn't happen for Minor findings, Notes, or Strengths - those are lower-stakes and don't need the extra check.

Criterion values

If you configured evaluation criteria before running the analysis, you'll see a separate tab with extracted values:

Each value comes with its own evidence - the specific passage in the proposal that the AI used to determine the score.

This data powers the bid comparison feature.

Captured entities

The analysis picks up people and companies mentioned in the documents. You'll see them listed with:

• Name and role (e.g., "J. Smith - Project Manager")
• Type (person, company, organization)
• Registry match (for Latvian procurements) - if the company is in the official business register, you'll see its registration number, beneficial owners, and shareholders

This is useful for due diligence. You can check if a subcontractor is a real registered company, or spot potential conflicts of interest.

Tabs overview

The procurement page has several tabs collecting different aspects of the data:

Acting on results

Here's a practical approach:

1. Read the strategic briefing first for the big picture
2. Review all Critical findings - these are potential deal-breakers
3. Go through Major findings - these need attention but aren't necessarily fatal
4. Check the evidence for anything surprising - make sure the AI interpreted it correctly
5. Scan Minor findings and Notes for anything you care about
6. Note the Strengths - useful for your final evaluation