Playbook
Agentic workflow for coding
Autonomy without a loop is chaos. This is the process shape that keeps multi-step agents shipping software you can defend.
Default loop
Specify → plan → implement → verify → review → merge. Every arrow is a place an agent can fail. Verification is the only arrow that must never be owned by the author-agent alone.
The loop in practice
-
01
Specify
Acceptance tests, out-of-scope edges, and risk files named up front.
-
02
Plan
Read-only scout produces a bounded plan with file list.
-
03
Implement
Builder edits in a worktree or branch. Keep diffs reviewable.
-
04
Verify
Real build and test commands. Exit non-zero means continue with evidence.
-
05
Review
Different model or human on auth, data, and deploy surfaces.
-
06
Merge
Only after gates pass. Checkpoint so rewind is cheap.
Patterns worth knowing
Fan-out
Parallel independent tasks. Fails when files collide.
Pipeline
Same stages across many similar items.
Reviewer-gate
Different lab reviews. Gate needs teeth.
Loop-until-dry
Exhaustive hunts with an objective empty state.
Full pattern writeupAI agent orchestration patterns. Team rolesmulti-agent field guide.
Tools that run the loop
- Claude Code — strong single-stack agent seat
- Codex CLI — OpenAI terminal agent seat
- OpenCode — multi-provider open CLI
- Aider — git-native pair loop
- AI coding harness — multi-CLI crew + verify
- Context engineering — what agents see
- Enterprise vibe coding — governance at scale
FAQ
What is an agentic workflow?
An agentic workflow is a defined multi-step loop where AI agents act with tools toward a goal, and humans set scope plus verification. Typical stages, plan, implement, test, review, merge.
What are common agentic workflow patterns?
Fan-out for independent tasks, pipeline for staged processing, reviewer-gate with a different model, and loop-until-dry for exhaustive cleanups. All need external verification.
How is this different from vibe coding?
Vibe coding is the intent style. An agentic workflow is the process that keeps autonomous steps coherent and shippable.
Do I need multiple models?
Not always. A different model as reviewer is high leverage. Multi-model crews help when labs share blind spots or price/performance differs by role.
Where does a harness fit?
A harness runs the workflow across CLIs, roles, isolation, shared memory, and a verify gate that is not the author-agent’s self-report.
The app behind this research
TheVibeFather is the multi-CLI AI coding harness
Run Claude Code, Codex CLI, OpenCode, Grok Build and other agents as one crew — shared project memory, roles, and a verify gate so your tests decide what ships. Bring your own keys.