Essential guidelines

Good and weak instructions

The same job, written two ways. The difference is almost never length. It is whether a second person could check the result.

Name one artifact and one completion event

WeakBetter
Improve our operationsReconcile the April invoice export against the ledger, explain every mismatch, and return a corrected workbook for approval
Look into the pipelineFlag deals with no next step, a close date in the past, or a departed owner, and post the list to #revops with record links
Research this marketReturn a cited brief on the freight TMS mid-market, with an unresolved-claims section for anything a source cannot carry
Fix the failing testsDiagnose the webhook suite failure, apply a fix, run the suite plus a 1,000-request soak, and open a PR with the diff summarized

The failures that produce weak runs

FailureBetter operating choice
The request describes a broad goalName one artifact and one completion event
The source of truth is unclearIdentify the authoritative system or file
The agent is asked to make it betterDefine the quality checks and give examples
Too many agents edit the same surfaceRecut the work around independent outputs
A run returns a confident summary without proofRequire citations, checks, receipts, or a recording
Every correction is pasted into the next promptStore stable facts in Knowledge and procedures in Skills
The automation runs too oftenAdd conditions, limits, and a failure owner
Review becomes a rubber stampRoute exceptions and consequential decisions explicitly

Length is not the variable

A long prompt that never says how the work will be checked is weaker than three sentences that do. If your prompt keeps growing run over run, that is a signal that some of it is reusable operating context in the wrong place. Move the stable parts into Knowledge or a Skill and let the prompt describe today's job.