When should an agent be allowed to fix code?
A finding is not permission to edit. A practical policy for bounded automatic fixes, grounded in the PR reviewer’s disabled-by-default fixer primitives.
-
-
Operating an agent workflow: status, evidence, and failure visibility
A practical look at the PR reviewer’s operations CLI, why a successful process is not a successful workflow, and which failures a simple health summary can miss.
-
Testing agent workflows without calling a model
Use deterministic fixtures to test validation, orchestration, and failure policy. Save live model calls for the questions those tests cannot answer.
-
A webhook is not a durable queue
What happens when a PR review worker is busy or crashes? A look at the gap between accepting a webhook and reliably completing the work it triggers.
-
Memory, skills, or files? Where agent context belongs
A practical policy for agent context: stable preferences in memory, reusable procedures in skills, task evidence in files, and earlier decisions in session history.
-
Agentic workflows need boring guardrails
A practical approach to agent guardrails: narrow permissions, revision-specific reviews, validated outputs, visible failures, and explicit stopping conditions.
-
From OpenClaw to Hermes: why I rebuilt my agent workflow
Why I moved my personal agent workflow from OpenClaw to Hermes, and why repeatable work mattered more to me than another impressive demo.
-
Hermes as a personal agent runtime
Hermes can be used as a personal agent runtime: a CLI and messaging-based environment with tools, memory, skills, cron jobs, session search, and subagents for practical engineering workflows. This second post builds on the Hermes/OpenClaw introduction.
-
What are Hermes and OpenClaw?
A practical introduction to Hermes and OpenClaw: how OpenClaw helped prove the value of agents close to real engineering work, and how Hermes provides the runtime foundation for durable agent workflows.