Trust But Verify: My Solo Developer AI Agent Workflow for Shipping Without Regrets

Description and use

A solo developer uses AI agents for building tasks but independently verifies all changes to prevent failures caused by agents reporting completion without truth.

Problem

Solo developers risk deploying incorrect changes because AI agents report completion without independent verification.

Outcome

The workflow prevents undetected failures, ensures all changes are verified independently, and maintains a clear audit trail.

Workflow

• Write a brief with outcome, constraints, and a clear check
• Build small, single‑direction changes
• Verify against the live system: fetch remote tree, run full test suite, open live URL
• Ship in batches on a controlled schedule
• Log each completed task with date and link

Evidence

I learned that the hard way, more than once. The workflow below is the one I use now: agents do the building, and I do the verifying.

Source

That is the central danger of a solo developer AI agent workflow: agents report completion, not truth.

Source

If the agent pushed a file, I check the remote tree. If the agent ran tests, I run the full suite. If the agent says a page is live, I open the live URL.

Source

I batch small pushes to save automation minutes, and I never let an agent start a new task to fix a failed one without me seeing the failure first.

Source

The definition of "tests pass" is written in the brief, and it means the full suite, every time, run by someone — or some step — other than the one that wrote the code.

Source