Build a repeatable workflow

Use this topic-specific sequence: describe → draft → test → explain → fill. Give each stage one input, one output, and one gate. The first run should be narrow and reversible. Later automation is earned by measured reliability, not by how easy it is to connect tools.

For build and validate a June regional-revenue formula in Excel 365, begin with the job card and sanitized packet. Run the constrained prompt:

Excel 365, comma separators. A=Date, B=Customer, C=Region, D=Revenue; F2 contains a region. In G2, total D where C=F2 and A is in June 2026. Give one formula, explain every condition, and provide normal, boundary, and blank/error tests. Do not invent columns.

Save the response beside its prompt and input version. Then apply the quality rubric and calculate a tiny hand-checked table, test June 1 and June 30, inspect dates stored as text, confirm absolute references, and compare the total with a filtered sum. A failed check returns to the smallest responsible stage; do not regenerate everything. If the source was missing, repair context. If the instruction was ambiguous, repair the prompt. If the candidate violates policy, stop and escalate rather than prompt around the policy.

Name an owner for source approval, generation, verification, and release. One person may hold several roles on a small project, but the role changes should remain visible. The reviewer needs the evidence packet, not merely the final artifact.

Define operational states: draft, needs evidence, blocked, approved, released, and rolled back. This vocabulary prevents a plausible draft from being mistaken for an approved result. Attach timeouts, retry limits, and an off switch to any automated stage.

Log the defect category rather than just “bad output.” This chapter's recurring defects are wrong locale separators; text dates; shifted ranges; hidden filters; formulas filled down with relative criteria cells. Track their rate on representative cases. Review false positives and false negatives separately when classification is involved; track factual, continuity, or rights defects when producing media.

The end product is a formula test card containing schema, formula, expected rows, edge cases, and a safe-fill checklist. Keep raw columns untouched. Use helper columns for cleanup so every transformation is reversible, and never accept a formula whose result you cannot reproduce on five known rows. Periodically rerun a stable set of cases after changing models, prompts, source material, formulas, or settings.

Imagine the independent check fails after release. Identify how to stop distribution, identify affected outputs, restore the last approved version, notify the owner, and preserve enough evidence to learn. A workflow without rollback is only a happy-path demo.