CONCEPT Cited by 2 sources
Agent as first-pass investigator¶
Definition¶
Agent as first-pass investigator is the operational model in which an AI agent is delegated investigation, diagnosis, and a proposed fix as its bounded scope of authority — the agent prepares a draft PR / report / proposed change, but a human reviews and merges. The agent is not authorised to merge, release, or otherwise commit the change to production state.
Atlassian's 2026-06-01 Jira-team post gives the canonical wiki articulation:
"The key is that the agent handles the repetitive first pass: investigation, diagnosis, and a proposed fix. Engineers validate the change before it is merged. What used to require hours of manual investigation can now become minutes of review." (Source: sources/2026-06-01-atlassian-how-we-cut-up-to-80-of-engineering-chores-using-ai-agents-in)
The three-stage scope of authority¶
The agent's bounded scope, as defined by Atlassian's KTLO workflow:
- Investigation — read the work item, fetch logs / call stacks / failing-test outputs, query the codebase. Pure-read operations. No state mutation.
- Diagnosis — classify the issue (real vs false positive, unit vs integration vs visual flake, repo with skill vs without, …). Decision recorded as a comment on the work item.
- Proposed fix — apply the relevant skill's fix pattern, commit changes to a branch, open a draft PR. PR contains the diff and an explanation; PR is draft so it cannot be merged without human action.
Out of scope: merge, deploy, close ticket, configure-flag-state in production, modify CI / repo settings.
Why human-in-the-loop is the load-bearing constraint¶
The cost economics of KTLO automation depend on the first-pass investigation cost being collapsed from hours to minutes while the review remains human. Atlassian's framing is explicit:
"What used to require hours of manual investigation can now become minutes of review."
If the human were removed (agent merges its own PRs), the saving would be larger but:
- Review-fatigue protection vanishes — the agent's failure modes (false-positive triage, stale skill applied to wrong repo, regression introduced by fix-pattern misuse) ship to production silently.
- Merge gate becomes the only safety net. Merge queue CI catches some classes of regression but not all (semantic bugs, unintended behaviour changes, partial refactors).
- Authorship ambiguity. A revert / post-mortem becomes harder when no human was on the merge.
The "first-pass investigator" framing is the explicit choice to trade some agent throughput for review accountability.
Agent's exit conditions per stage¶
Atlassian's flaky-test workflow exemplifies bounded exits:
| Stage | Exit options |
|---|---|
| Triage | (a) False positive → comment on work item, STOP. No PR. (b) Reproducible → enter fix stage. |
| Fix | (a) Fix produced → open draft PR, comment on work item linking PR. (b) Could not reproduce / could not fix → comment on work item with diagnosis, STOP. No PR. |
"If it looks like a false positive, the agent can stop and summarise that outcome, commenting on the original Jira work item. That way the engineer reviewing the ticket can quickly get a sense of what the agent did and what the agent discovered without digging." (Source: sources/2026-06-01-atlassian-how-we-cut-up-to-80-of-engineering-chores-using-ai-agents-in)
The bounded-comment exit is doing two things: (a) preventing "agent opens a PR for a false positive" failure; (b) returning diagnostic value to the human even when the agent can't act.
Sibling pre-human-review patterns¶
This concept composes with several wiki primitives that thicken the pre-human review step:
- patterns/pre-human-agent-review (Atlassian Fireworks, 2026-04-24) — three-tier stack: adversarial sub-agent → CI / merge-queue gate → human architect. This concept names the first-pass / merge-gate split; pre-human-agent-review fills in the "adversarial sub-agent" stage between agent and human.
- patterns/ci-as-agent-quality-gate — CI is the automated half of the gate. Agent reads CI output and patches before requesting review.
- patterns/agentic-pr-triage (Fly.io / Phoenix.new) — the greenfield-issue-triage variant; same agent-drafts-PR shape but applied to feature work rather than KTLO.
Distinction from fully-autonomous agent¶
The "first-pass investigator" posture is deliberately less ambitious than fully-autonomous coding agents:
| Dimension | First-pass investigator (this concept) | Fully-autonomous agent |
|---|---|---|
| Scope | Investigate + diagnose + draft fix | Investigate + diagnose + fix + merge + deploy |
| Merge gate | Human review of draft PR | None / agent-self-approves |
| Failure containment | Human catches at PR review | Merge queue + canary + revert |
| Throughput | Review-bound | Compute-bound |
| Best fit | KTLO categories with high pre-existing pattern recognition | Greenfield work with novel design risk |
| Risk profile | Conservative; mistakes caught before production | Aggressive; mistakes caught after production |
For KTLO categories where the team already has years of pattern recognition, the first-pass-investigator model is the right posture — review is cheap (the team knows what good looks like), so the human-gate cost is low and the merge accountability is preserved.
Why "minutes of review" is the load-bearing economic claim¶
The 80% time-reduction claim only works if review of a draft PR really is minutes, not hours. That requires:
- The agent's fix follows a known good pattern the reviewer recognises.
- The agent's commit message / PR description explains the diagnosis clearly.
- The agent doesn't open false-positive PRs — review fatigue is the failure mode that destroys the economics.
The triage-vs-fix split, the bounded false-positive exit, and the specialist-skill dispatch are all in service of keeping review-time low.
Seen in¶
- sources/2026-06-01-atlassian-how-we-cut-up-to-80-of-engineering-chores-using-ai-agents-in — canonical wiki source. Names the "first pass: investigation, diagnosis, and a proposed fix" contract; documents the bounded-comment exit on false-positive triage; reports the "hours of manual investigation … minutes of review" economic claim.
- sources/2026-04-24-atlassian-rovo-dev-driven-development — greenfield-side instance: Fireworks team uses pre-human agent review with adversarial sub-agent + CI gate + human architect; the human-architect stage is the first-pass-investigator pattern applied to whole-feature work rather than per-KTLO-task.
Related¶
- concepts/ktlo-engineering-chores — the primary use case for this operational model.
- concepts/work-item-as-agent-prompt — the substrate framing.
- concepts/agent-orchestration-skill — what the agent loads to actually do the first pass.
- concepts/agentic-development-loop — the inner loop the agent runs while doing the first pass.
- patterns/agentic-pr-triage — sibling on the agent-drafts-PRs axis (greenfield work).
- patterns/jira-status-transition-triggers-agent-workflow — triggers the first pass.
- patterns/agent-skill-with-fallback-chain — fallback when the agent doesn't have a repo-specific skill for the work.
- patterns/test-category-classifier-then-specialist-skill — flaky-test variant of the dispatch step.
- patterns/pre-human-agent-review — adversarial-sub-agent + CI + human stack that thickens the pre-human review step.
- patterns/ci-as-agent-quality-gate — the automated half of the gate.
- systems/rovo-dev — likely first-party agent surface for this pattern at Atlassian.