Trace a worked example

You operate an employee handbook assistant. A teammate proposes a change that sounds beneficial, but you require a trace connecting configuration to evidence. Here is the observed run:

A leave-policy answer spans the final sentence of “Eligibility” and first list under “Exceptions.” With 400-token non-overlapping windows, recall@5 is 71%. Adding 60-token overlap raises it to 86% but duplicates 28% of results. Heading-aware 250-token clauses with parent expansion reach 91% recall and only 7% duplicates.

First identify the input and scope. Which user, segment, document, image, query, hardware profile, or task was involved? Next record the exact configuration: model or checkpoint, prompt, index, context policy, sampler, thresholds, and tool versions that matter for chunking for RAG. Then preserve the intermediate artifact that explains the result. Finally attach the user-visible output and measured consequence.

Write the trace as a sequence rather than a conclusion:

request + configuration
  -> intermediate evidence
  -> model or policy decision
  -> validation / fusion / routing
  -> user-visible action
  -> measured outcome

This format prevents hindsight from collapsing several stages into “AI error.” It also exposes where a deterministic check could have stopped propagation.

Use absolute counts alongside percentages. If success falls from 78 of 100 to 62 of 100, that is a 16 percentage-point decrease, not merely “16% worse.” If cost rises from $0.006 to $0.018 for one million requests, variable spend rises from $6,000 to $18,000. If a sample contains only ten cases from a critical language, one miss moves its rate by ten points; collect more evidence before claiming stability.

Measure retrieval recall@k against evidence spans, precision or nDCG, answer groundedness, citation correctness, duplicate rate, average retrieved tokens, and latency. Build queries that require facts near boundaries and compare chunking variants while holding the embedder and generator fixed. Pick one primary metric and list gates separately. Do not average a privacy breach, severe unsafe action, or failed authorization with stylistic quality.

Generate at least three explanations: input mix changed; a component configuration changed; or measurement changed. Then propose a discriminating test for each. Replay the same cases on old and new configurations, compare intermediate artifacts, and rescore both with the same rubric. This controls more variables than debating outputs by eye.

Fixed character cuts split sentences or tables, headers become detached, boilerplate dominates embeddings, OCR artifacts create nonsense chunks, and overlap returns near-duplicates. Updating only part of a document can leave stale chunks. One global size rarely serves prose, code, and tables equally. The likely failure should match the earliest divergent artifact. If it does not, revise the hypothesis.

Choose among keep, roll back, canary, route, or collect more data. State the owner and deadline. A rollback restores safety but does not explain root cause; preserve the failed configuration for offline reproduction. A successful fix adds the case to a regression set and updates the runbook.

The expert habit is modest: claim only what the trace supports. One run can demonstrate a mechanism, not a universal advantage. A coherent sequence with inspectable evidence teaches more than a polished before-and-after screenshot.