What to do when customer interviews for AI code review tools contradict each other

Contradictory interviews can reveal different segments, incentives, definitions, or contexts. Preserve the disagreement before trying to average it away. Two people can accurately describe different workflows while using the same label for their problem.

Start with the decision

Sort observations by role, company situation, current alternative, and triggering event. Revisit the exact episode behind each statement. Design a follow-up that distinguishes the competing explanations rather than asking which person was right.

The illustrative scenario

This is an educational workbook. The company or fund and all numerical inputs below are fictional. They are not ADIN results, customer claims, market benchmarks, or a forecast.

The fictional service suggests review comments on pull requests for an engineering team. Maintainers remain responsible for accepting a finding and deciding whether a change is ready. Review traffic varies with release cycles.

Too many plausible but unhelpful comments can increase reviewer work. A severity label has little meaning unless the team agrees which findings require action.

Turn the scenario into an evidence decision

Consider a review of AI code review tools in which a confident explanation arrives before the supporting records. Start with the first question in the table. Write down what an answer would change: the next interview, the experiment's scope, a request for specialist review, or a decision to wait. A question without a consequence can produce a longer document while adding little understanding.

Next, inspect the record named in the table and record its date, owner, permission boundary, and limitations. Keep a labeled sample of true defects, false alarms, dismissed suggestions, and defects missed by both workflows. Record repository and change type so aggregate numbers remain interpretable. If the record contradicts the explanation, preserve both accounts and ask which definition, period, or workflow differs. Do not silently select the version that makes the opportunity look strongest.

Finish with a conditional statement: if the specified evidence supports the claim under these conditions, take the named next step; otherwise investigate the unresolved question. A useful conclusion explains where each statement holds. If the conflict disappears after segmenting by workflow, update the target segment. If it remains unexplained, keep it as an open question rather than choosing the more flattering answer. This worked exercise is about the decision process. It does not assert that a fictional company has met a real diligence standard or that a template can authorize an investment.

Use this worksheet

Answer the questions with a source, date, owner, and next action. Mark an unknown as unknown. Use public or permissioned information and involve a qualified specialist when a question requires expertise beyond the team’s competence.

1. Are the respondents doing the same task?
2. Do they use the same definition?
3. Who bears the cost?
4. Which constraint differs?
5. What observation separates the explanations?

Questions specific to this scenario

• What makes a finding actionable?
• Which changes are excluded?
• Who adjudicates reviewer disagreement?

Keep a labeled sample of true defects, false alarms, dismissed suggestions, and defects missed by both workflows. Record repository and change type so aggregate numbers remain interpretable.

A concrete next test

Ask two maintainers to label the same permissioned set independently before looking at the tool's findings. Investigate disagreements about severity and actionability. A shared rubric gives the next comparison more meaning than counting comments that nobody would act on.

Interpret the result

A useful conclusion explains where each statement holds. If the conflict disappears after segmenting by workflow, update the target segment. If it remains unexplained, keep it as an open question rather than choosing the more flattering answer.

Compare actionable findings and reviewer effort on similar changes. A tool that produces more comments is not automatically finding more consequential problems.

Sources and method

These primary resources provide background for the concepts. The fictional scenario, calculations, and worksheet are ADIN educational examples; the sources do not report or validate those invented results. Reviewed October 11, 2026.

• a16z: A Framework for Finding a Design Partner
• NIST: AI Risk Management Framework