Field notes

How unattended agents fail in practice, with sources, and the check that catches each one.

Agents that check on agents: refusing to build on an unproven run (MCP)

How a morning agent verifies the nightly agent's run over MCP before it consumes the output, and refuses when the run is missing, failed or unproven.

2026-11-09

A daily cost cap for OpenClaw in five minutes

OpenClaw shows spend but never stops it. Install one skill, set cap_day_cost, and get a Telegram alert that pauses the agent. Honest about where the number comes from.

2026-11-02

Scheduled LLM jobs in GitHub Actions: exit 0 is not done

Cron in Actions, artifacts as evidence, an rv run step and cost reporting: how to know a scheduled LLM job ran, produced output and stayed on budget.

2026-10-26

Your agent didn't fail, it drifted. Detecting output and duration drift with a 7-run baseline

Agents that exit 0 and write the wrong thing. How a 7-run median plus MAD baseline catches output and duration drift, and why mean and stdev miss it.

2026-10-19

Set a hard budget per scheduled agent run (Anthropic, OpenAI, OpenRouter)

Provider spend limits are monthly and account-wide. How to cap one scheduled agent run and one day, and pause the agent before the next run starts.

2026-10-05

Langfuse vs a watchdog: you don't need tracing to know your nightly agent is broken

Tracing tells you why a run went wrong. It cannot tell you the run never happened. Where Langfuse fits, where a watchdog fits, and how to run both.

2026-09-28

Our deploy job reported success for three days. The site stood still.

A brake counter, set -e and grep -c that exits 1 on zero matches killed our deploy three lines before it deployed. No error, no failed run, three days of a stale site, and one duration alert we ignored.

2026-09-16

n8n AI workflows: catch the failures your Error Workflow never sees

n8n's Error Workflow only fires when a node errors. Catch missed schedules, green runs that did nothing, and AI cost per run with two HTTP nodes.

2026-09-14

Cronitor for AI agents: what changes when the job is an LLM

A cron monitor tells you the job ran. An AI agent also needs a cost cap, loop detection and an outcome check. What to keep and what to add.

2026-09-07

Monitoring a headless claude -p job: hooks, exit codes, cost and alerts

A full tutorial for monitoring headless claude -p cron jobs with SessionStart, PostToolUse and Stop hooks: transcript cost, evidence checks and alerts.

2026-08-31

Prove what your AI agent did: an audit trail for unattended agents

A real, tamper-evident proof of one agent run: hashed record, public daily Merkle chain, Bitcoin anchor. How to verify it with a stdlib script, and what it cannot prove.

2026-08-26

My Claude Code cron ran up $1,800 in two nights. The watchdog that stops it at $2

Four documented runaway agent bills ($1,818, $6,000, $437, $150), why per-call metrics hide the loop, and per-run/per-day caps with rv.

2026-08-25

Claude Code Routine failed silently? How to know your scheduled agent actually ran

Green does not mean done. The 4 ways a scheduled Claude Code run fails with no error, and heartbeat plus evidence checks that catch each one.

2026-08-25

The dead man's switch for AI agents (and why a ping isn't enough)

A ping monitor knows a job ran. For an agent that is the least interesting fact. What a dead man's switch has to check when the job is an LLM.

2026-08-25

OpenClaw stuck in a polling loop: $150, a crash, and no alert. Detect it in 60 seconds

An OpenClaw agent called the same tool 1,535 times in two hours. Every call looked fine. How a retry-storm rule and a daily cap catch this before the bill.

2026-08-25

7 ways unattended AI agents fail silently, and one check for each

Seven ways a scheduled AI agent fails without an error, from a run that never starts to a run that does nothing, and the one detector that catches each.

2026-08-25

Coming up