Make the goal the measure of good work.

An agent can finish a run without finishing the job. airis keeps the acceptance criteria, the recorded evidence and the review decision in one view, so a team reads what was met, what is still pending and what was only claimed.

Faster CI/CD · Dependency caching Sample

Defined before it is claimed.

Acceptance pack · v1 Implement dependency caching
Goal · Ship changes faster and safelyOwner · FrankReviewer · William
Median CI run under 8 minutesCandidate branch only · Satisfied by CI timing
Required
All 248 suites retained, exit 0Final suite after the last edit · Satisfied by suite run
Required
Peer review and rollout planA person decides · No check can satisfy this row
Not reviewed

Every condition names the evidence that can satisfy it before work starts · Sample data

Agent report Complete Self-reported at handoff · shown, not counted
Recorded checks 2 of 2 7m 42s median run · 248 / 248 suites
Review decision Pending William reviews next · a person decides this row
Not accepted yet. Two conditions are met by recorded checks. The third waits for a person, so the task stays open and nothing is filled in.

A report is a claim · A check is evidence for one condition · A review is a decision · Sample data

12 paired CI tasks Concept data
Current practice 7 of 12 accepted Time to decision (unfinished at cap) 2h 29m
Prepared change 10 of 12 accepted Time to decision (unfinished at cap) 1h 44m

Compared, not applied · A comparison changes nothing until a person applies the change

01 / 04 The measure

Done means the goal was met, not that the run ended.

  • 01 Every task carries an acceptance pack: named conditions, the evidence that can satisfy each one and the person who decides.
  • 02 Agent reports, recorded checks and human review are kept as separate rows, each with its capture source attached.
  • 03 A comparison holds the input, revision, environment and criteria constant, and keeps unfinished and held-out cases in the result.

02 / 04 Define, inspect, compare

Three questions, answered separately.

What must be true, what the evidence shows and whether a change is better are different questions. airis keeps their answers apart, so no one has to infer one from another.

01 Define acceptance

Say what done requires before the work starts.

An acceptance pack turns the goal into conditions a team can check. Each condition names the evidence that can satisfy it and the person who decides when evidence is not enough. The pack is versioned and travels with the task, so every retry starts from the same definition.

  • Conditions written from the goal, not from the diff
  • An evidence source declared for every condition
  • One named reviewer for what a check cannot prove
Goals & work
Faster CI/CD · Acceptance pack Sample
Implement dependency cachingPack v1 · Owner Frank · Reviewer William
Condition Satisfied by Decides
Median CI run under 8 minutes Recorded CI timing on the candidate branch Check
All 248 suites retained, exit 0 Final suite run after the last edit Check
Peer review, then rollout William reviews; Mike decides rollout William · Mike
Agent reports do not satisfy a condition.They are shown beside the evidence so the claim and the proof can be read together.

Goal · Ship changes faster and safely · Pack reused for every retry of this task · Sample data

02 Inspect the evidence

Read the claim, the checks and the decision as three things.

At handoff the agent says the task is complete. airis shows that report, but counts only what was recorded: the CI timing captured on the candidate branch, the exit code of the final suite run and the reviewer’s decision. Two of three conditions met is the honest state, and it stays visible until William decides.

  • The agent report sits beside the evidence, never inside it
  • Each recorded check carries its scope and capture source
  • Pending rows stay pending; nothing is filled in
Delivery speed
Faster CI/CD · Evidence at handoff Sample
Agent report Complete Written by the agent at handoff. Shown, not counted.
Recorded evidence 2 of 3 conditions met Captured by CI and the review queue.
7m 42s median CI runTarget under 8 min · candidate branch · CI timing log
Met
248 / 248 suites retainedExit 0 · final suite after the last edit · suite run
Met
Peer review and rollout planWilliam reviews next · a person decides this row
Pending

A passing check proves its own condition, not the whole change · Sample data

03 Compare on equal terms

Judge a change by the terms it will be held to.

A prepared change runs against the same twelve CI tasks as current practice: same input, same revision, same environment, same acceptance pack. Unfinished tasks stay in the denominator and four held-out cases are never used during preparation. The result is a comparison a reviewer can trust, not a highlight reel.

  • Paired tasks, with unfinished attempts retained
  • Held-out cases kept apart from preparation
  • Acceptance judged by the same pack and the same reviewer
Team playbooks
Comparison guardrail · 12 tasks Concept data
Term Held constant across both arms
Input The same 12 CI tasks, paired one to one
Revision One pinned commit
Environment One runner image, cold cache
Acceptance Pack v1, judged by the same reviewer
Unfinished tasks Retained in the denominator
Held-out cases 4, kept out of preparation
Tasks accepted
7 / 12 10 / 12

Compared, not applied · A concept comparison, not a measured airis result

03 / 04 Rules of evidence

What counts as evidence. What is only shown.

Every row says what kind of thing it is. That is what makes an acceptance rate readable, and what keeps an illustrative example from being mistaken for a measured one.

Rule 01 · Reports

A report is a claim.

The agent’s own summary is displayed next to the evidence. It never satisfies a condition and never moves an acceptance count.

Sample “Complete” shown beside 2 of 3 conditions met

Rule 02 · Checks

A check proves one condition.

A recorded command result satisfies the row it was captured for, with its scope and source attached. It does not prove the change is correct.

Sample 7m 42s median run · candidate branch only

Rule 03 · Review

A review is a decision.

Human acceptance is its own row with a named reviewer. Until it is recorded the task is pending, and pending is shown as pending.

Sample William reviews next · human review pending

Rule 04 · Comparisons

A comparison keeps its terms.

Input, revision, environment and criteria stay constant. Unfinished tasks and held-out cases remain in the result, which stays concept data until measured on your own work.

Concept data 7 → 10 of 12 accepted · 4 held-out cases retained

See it with your own acceptance criteria

See which conditions
your agents met.

A guided look at acceptance, evidence and comparison for a sample cohort, and a conversation about how your teams define done.