Four lessons from a year of running AI agents on boring tasks

Description and use

Running AI agents on routine tasks revealed that reliability hinges on clear briefs, audit trails, isolation, and automated verification.

Operating AI agents reliably over time requires more than good prompts; it needs clear briefs, audit trails, isolation, and verification.

Stable, auditable AI agent operations with clear briefs, isolated environments, and automated verification.

Define a task file with goal, constraints, stop conditions, and output location.
Run the agent using the brief; it reads its own ledger at start.
Agent logs each action to an append‑only CSV/markdown ledger.
After completion, run automated verification (curl, row count, diff).
If verification fails, investigate using the ledger and git history.
Isolate each agent with separate browser profile, tokens, and working directory.
Clean up the sandbox after each run with a simple rm -rf command.
Repeat weekly, adjusting briefs as needed.
Maintain audit trail for human review and compliance.

Every reliable agent run in my setup starts from a task file: goal, constraints, stop conditions, and where to write results.

A plain append‑only ledger — CSV or markdown, one line per action — outperformed all of them.

Separate browser profile, separate tokens, separate working directory.

Every task in my system ends with an independent check: curl the page, count the rows, diff the output.