Verifiable AI Coding Workflow

A small agent-assisted coding workflow where the useful artifact is not generated code, but a checked path from idea to tests, diff, review, and handoff.

Buildability
B2 engineer-repeatable
Status
candidate
Time
1-2 hours in a prepared repository
Cost
Low to medium, depending on model and test loop length
Human approval
Local file edits only; commits and deploys remain explicit approvals
Last verified
Jul 21, 2026

Outcome demo

  • Turn an implementation idea into a bounded coding task with checks and reviewable evidence.
  • Wow moment: The agent does not just produce a patch; it leaves commands, changed files, acceptance checks, and a human-readable handoff.
  • Current bottleneck: Requires a repo with runnable checks and a human willing to enforce task boundaries.

Can I build this?

Code level
Developer or technical operator
Data touched
Repository source, tests, local command output
Write actions
Local file edits only; commits and deploys remain explicit approvals
Sources
1 public receipt

System map

Human
Defines scope, approves write actions, reviews output.
Agent
Plans, edits, verifies, and reports with evidence.
Data
Repository source, tests, local command output
Actions
Local file edits only; commits and deploys remain explicit approvals

Fork with an agent

Use the Markdown route as the build brief and the JSON route for constraints, status, and evidence pointers.

Minimal build

  1. Write a task brief with files in scope, non-goals, and acceptance checks.
  2. Give the agent repo-specific operating instructions.
  3. Let it inspect before editing.
  4. Require a focused diff and a real check command.
  5. Keep commit, push, deploy, and external writes as separate approvals.

Evidence

The current site update itself is a candidate use case: post content, docs, production drift, and build checks had to be kept separate instead of collapsed into one “make website better” prompt.