Skip to content
Guides/Design

Build Loops with Hypothesis, MVP, Validation, and Feedback

Short answer

Use this four-part design loop before you automate: state the hypothesis, run the smallest useful version, collect validation evidence, then decide what to change before the next pass.

Why it matters

Agent workflows become risky when teams try to design the perfect system before seeing a real run. A small loop makes the risk visible early: the discovery source may be weak, the checker may be vague, or the stop rule may be too soft. That is useful information, not failure.

The four-part design loop

The four-part design loop
PartQuestionGood answer
HypothesisWhat are we trying to learn?This small loop can safely fix one reproducible CI failure
MVPWhat is the smallest useful run?One pass on the latest failed job
ValidationWhat evidence proves it worked?Same failure passes, full checks pass, no shortcuts
FeedbackWhat changes next time?Tighten boundaries, improve checker, or stop
4 of 4 rows

Before you run

  1. 01Can the hypothesis be false?If not, rewrite it
  2. 02Can the first run stay small?If not, narrow the source
  3. 03Can validation be observed?If not, add evidence
  4. 04Can feedback change the next run?If not, it is not a loop yet

Practical checklist

  • Write one testable hypothesis before the loop runs
  • Choose the smallest useful run that could prove or disprove it
  • Name the evidence that counts as validation
  • Record actual evidence after the run
  • Decide whether to stop, adjust, or schedule the next pass
  • Do not expand scope during the validation run

Example

Hypothesis: a CI loop can fix one failing test safely. MVP: run it once against the newest failed job. Validation: failing test passes, full suite is green, no tests are deleted. Feedback: if the loop touched unrelated files, tighten the boundaries before another run.

Common failure modes

Starting with a broad automation plan instead of one testable loop
Treating an impressive output as validation even when no evidence was captured
Changing the hypothesis mid-run so every result looks like success
Running again without writing down what the first run taught you

Related templates

FAQ

It is related. Here it is adapted for agent loops: build the smallest useful loop, measure the evidence, learn what to change before the agent repeats.

Sources & further reading