Examples
AI loop examples
The best AI loop examples are repetitive work patterns with clear evidence and a stop condition: code repair, source QA, browser testing, support follow-up, and pre-publish checks.
Current library snapshot
43total loop patterns
10categories
17engineering loops
10operating domains
Full referenceAll examples
| Loop | Category | Difficulty | Cadence | Verification |
|---|---|---|---|---|
| One Post a Week Experiment | Content | Beginner | Weekly for six weeks | Winner is supported by comparable replies, saves, and questions, not just likes. |
| Pre-Publish Source Check | Content | Intermediate | Before publishing factual work | Every checkable claim is supported by a current source or visibly flagged for an editor. |
| Social Source to Insight | Content | Intermediate | After saving a high-signal source | Source captured, takeaways extracted, draft angles written, and no public post is published without approval. |
| Accessibility Repair | Design | Advanced | Before launch or when audits fail | No confirmed accessibility blocker remains in the agreed pages, components, or tasks. |
| Error Message Rewrite | Design | Intermediate | When users hit confusing errors | Every in-scope user-visible error is accounted for, rewritten or blocked, and verified in a reachable state. |
| Visual Feedback Repair | Design | Beginner | After AI-generated UI changes or visual bug reports | Before/after screenshots, console state, and responsive checks show the visual issue is fixed without breaking adjacent states. |
| API Contract Drift | Engineering | Intermediate | After API changes or SDK releases | Server behavior, client types, examples, and docs agree on request/response contracts. |
| Acceptance Scenario Lockstep | Engineering | Intermediate | Before and during ambiguous feature work | The same scenarios written before implementation pass after the change, and any scope expansion is explicitly approved. |
| Agent Instructions After-Action | Engineering | Beginner | After a successful or painful agent coding session | Repo instructions contain only reusable, source-grounded lessons and the next similar task can start without rediscovering the same trap. |
| Architecture Rubric Refactor | Engineering | Advanced | When architecture work has a defined scope | Scoped module meets the written rubric, tests pass, and unresolved objections are explicit. |
| Behavior Ladder TDD | Engineering | Intermediate | When implementing logic-heavy features | Each behavior test fails before implementation, passes after the smallest change, and remains green through final refactor. |
| CI Optimization | Engineering | Advanced | Monthly or when CI is painful | CI p50/p95 improves against the same workflow without weakening tests or hiding failures. |
| Claude Code Repo Readiness | Engineering | Beginner | Before major agent work | Repo has agent instructions, documented commands, architecture notes, risk areas, and a docs/loops scaffold. |
| Cold Load Trim | Engineering | Advanced | When first visit feels heavy | Initial screen downloads fewer bytes while screenshots and behavior remain unchanged. |
| Completion Promise Loop | Engineering | Intermediate | For scoped implementation tasks where half-finished output is the main risk | Every acceptance criterion is checked with tests, browser evidence, logs, screenshots, or a clear blocker report before the agent stops. |
| Fresh Clone Onboarding | Engineering | Intermediate | Before onboarding | A clean machine reaches the documented ready state using only the README. |
| Parallel Agent Worktree Sweep | Engineering | Advanced | When several independent repo improvements can run at once | Each agent branch has isolated scope, passing checks, a summary, and no conflicting files before integration review. |
| Project Docs Freshness | Engineering | Beginner | Nightly or after meaningful code changes | Changed behavior, APIs, CLI commands, config, and workflows are reflected in docs. Docs checks pass. |
| Reference Oracle Implementation | Engineering | Advanced | Before implementing tricky behavior with an external source of truth | Generated outputs match the reference oracle across the agreed fixture set, with tolerances documented for legitimate differences. |
| Spec to Task Shards | Engineering | Intermediate | Before multi-file feature work or migrations | A written spec, non-goals, acceptance checks, and ordered task shards exist before implementation begins. |
| Test Flake Stabilizer | Engineering | Intermediate | When tests are inconsistent | The repaired test and full suite pass for the required consecutive-run streak. |
| Test and Logging Coverage | Engineering | Intermediate | Weekly or before release | Critical flows have useful tests and structured logs for representative success and failure paths. |
| Trace-First Debugging | Engineering | Intermediate | When an agent is tempted to patch a bug from a hunch | The bug is reproduced, the root cause is evidenced by traces or tests, and the fix includes a regression check. |
| Adversarial PR Review | Evaluation | Advanced | For meaningful PRs | An independent critic approves the unchanged version or only accepted findings remain. |
| Agent Merge Queue Review | Evaluation | Advanced | After multiple agent-generated PRs or branches accumulate | Only branches with passing checks, clear intent, non-conflicting scope, and human-readable evidence are merged or promoted. |
| Browser Quality Streak | Evaluation | Intermediate | Before release | N realistic scenarios pass consecutively, and earlier failures have regression coverage. |
| Promise to Proof | Growth | Intermediate | Before launch or campaign refresh | Every high-risk customer promise is supported, narrowed, or awaiting an explicit decision. |
| SEO/GEO Visibility | Growth | Intermediate | Monthly | Priority pages are indexable, answer-ready, internally linked, and no high-impact benchmark gaps remain. |
| Talk to Five Buyers | Growth | Intermediate | Before major landing-page rewrite | Proposed copy traces to repeated anonymized buyer objections across approved interviews. |
| Memory Bank Continuity | Knowledge | Beginner | At the start and end of multi-session agent work | Project brief, active context, decisions, tech constraints, and progress are current enough for a fresh agent to continue safely. |
| Open Loop and Stale Memory Cleanup | Knowledge | Beginner | Weekly | No current open loop is contradicted by recent daily or project notes. |
| Research to Artifact | Knowledge | Intermediate | Whenever research must support a decision | The artifact meets acceptance criteria, traces important claims to sources, and states uncertainty plainly. |
| Source Library Ingestion QA | Knowledge | Intermediate | After each source capture | Metadata complete, transcript/article state honest, useful takeaways present, and qmd retrieval verified or refreshed. |
| Agent Handoff Continuity | Operations | Intermediate | Before pausing or switching agents | A new agent can state goal, current state, proof, blockers, and next action without reading the whole transcript. |
| Agent Toolchain Health Check | Operations | Beginner | Weekly or before a heavy agent run | Critical tools authenticate, return sane output, and have a known fallback or blocker owner. |
| Living Story | Operations | Intermediate | Weekly or per project window | Every prior thread is carried forward, closed with evidence, or flagged stale/needs-review. |
| Production Error Sweep | Operations | Advanced | Daily or after incident | Actionable errors are fixed with reproduction or tests, or explicitly classified as noise. |
| Calendar Promise Proof | Personal Ops | Beginner | Daily or before week planning | Every calendar-derived promise has an owner, due date, evidence, or explicit drop decision. |
| Inbox Decision Triage | Personal Ops | Beginner | Daily or before deep work | Every sampled message is archived, labeled, delegated, converted to a task, or left with a drafted reply; no external message is sent without approval. |
| Support Refund Follow-Up | Personal Ops | Beginner | Until terminal state | Refund is received, or no approved next step remains and a blocker is named. |
| Dependency CVE Burndown | Security | Advanced | After security scan | No exploitable high or critical CVE remains without an explicit risk decision. |
| Sandboxed YOLO Probe | Security | Advanced | Before allowing autonomous shell-heavy agent runs | The agent can run needed commands inside the sandbox, cannot reach forbidden files/secrets, and produces a replayable diff or report before host-side changes. |
| Loop Hiring Manager | Strategy | Intermediate | When a project accumulates recurring chores | At most three candidates fill proven recurring gaps, with one recommended safe manual trial. |
How to choose
| If the work is… | Start with… |
|---|---|
| Code or repo maintenance | Coding agent loops |
| Fact checking or research | Pre-Publish Source Check or Research to Artifact |
| Quality assurance | Verification loops |
| Recurring personal follow-up | Calendar Promise Proof |