AI Quality Assurance

Automated checks on every analysis — then your judgment on top.

We check AI quality at multiple layers: automated checks on every analysis, structured testing of the instructions behind it, and your professional judgment as the final authority.

Multi-Layer Quality Checks

Five layers between the AI and your report.

Inqura analysis result with citation traces and a Quality Confidence badge produced by the automated quality checks
Layers 2 and 3 in action: automated quality checks and citation-backed findings the investigator reviews.
1

The Evidence Evaluation Framework

Before the AI writes a single word of analysis, it’s operating under a structured framework synthesized from CIGIE, GAO, IIA, ACFE, and other professional standards. Evidence quality principles — including relevance, reliability, sufficiency, and validity — shape how every piece of evidence is assessed.

This framework wasn’t generated by AI. It was designed by an oversight professional with 25+ years of investigation experience.

2

Automated Quality Checks

After every analysis, separate automated checks run, including faithfulness verification (are claims supported by evidence?), coverage verification (does it address all parts of the question?), and retrieval quality assessment (how relevant was the evidence found?).

These aren’t the same process that generated the analysis. They’re independent evaluations.

3

Structured Investigator Review

No analysis reaches your report without passing through a structured review flow. The system requires you to expand the analysis, check at least one citation against the source evidence, and record your professional judgment.

Every review action is timestamped. Every judgment is logged. This isn’t optional.

4

Quality Confidence Scoring

All automated checks feed into a single Quality Confidence level: Established, Probable, Possible, or Insufficient. Faithfulness and coverage scores drive the primary assessment. The logic is documented, not hidden.

Retrieval quality can lower confidence by one level but can’t drag a well-supported analysis to Insufficient on its own.

5

Prompt Lifecycle Management

The instructions that guide the AI are versioned. Prompt changes run an automated check in CI against fixed test fixtures and are compared with a baseline.

Software engineering discipline applied to AI instructions. This is a regression check on structure, not a measure of accuracy.

Ongoing Testing

We test the instructions, not just the output.

The instructions that guide Inqura's evidence evaluation are tested in a structured way, and we keep testing them.

How it works

We build test cases with known answers and check how Inqura's evaluation handles them. When we change the instructions, we test the change before relying on it. We are preparing a pre-registered evaluation of Inqura's analyses against a test case with known answers, and will publish the results as measured.

Practical Impact

What quality assurance looks like when you're using Inqura.

1

The AI retrieves relevant evidence using hybrid search (meaning-based + keyword)

2

It assesses each piece of evidence for relevance and material limitations

3

It produces a structured finding with citations and a confidence level

4

Automated quality checks (faithfulness, coverage, relevancy, retrieval quality, contradictions) run in the background after the analysis is generated

5

Results appear in your quality metrics panel when the checks finish

6

You see the confidence level, faithfulness score, coverage score, and retrieval quality

7

You can expand “Evidence Considered” to see exactly what the AI looked at

8

You review the analysis, check citations, and record your judgment

9

State changes and your recorded judgment are logged in the audit trail

Report sections are drafts built from your completed analyses. Review and edit each one before you export.

Limitations

What AI quality checks can and can't do.

What automated checks catch

  • Claims not supported by retrieved evidence
  • Questions or aspects the analysis fails to address
  • Weak evidence retrieval (low relevance scores)
  • Structural problems (malformed output, missing fields)

What only you can catch

  • Whether the conclusion drawn is actually correct
  • Whether evidence was weighed appropriately
  • Connections requiring domain expertise to see
  • Whether framing is appropriate for your context

This is why the investigator review flow exists. AI checks verify the mechanics. Your expertise verifies the substance. Security, data handling, and certification questions are answered in the Trust & Security FAQ.

Trust is built on transparency, not promises.

Inqura gives you the tools to verify the AI — quality scores, citation tracing, retrieval transparency, and a structured review workflow.