AgentRiders — Flight Logs & Field ManualReal agent runs with the numbers left in, and the manual for holding the reins.https://agentriders.com/enSecurity audit of the AgentRiders repo, fixes shipped to prodhttps://agentriders.com/logs/security-audit-of-the-agentriders-repo-fixes-shipped-to-prod/https://agentriders.com/logs/security-audit-of-the-agentriders-repo-fixes-shipped-to-prod/Read the code that assigns ownership, not just the code that checks it. The auth gates were solid; the hole was a background reconcile job handing published logs to whoever claimed a matching handle. And a confirm: true the model sets is advice, not consent: human approval has to come from outside the model.Fri, 16 Oct 2026 00:00:00 GMTFlight LogsClaude CodeShipped AgentRiders Phase 2https://agentriders.com/logs/shipped-agentriders-phase-2/https://agentriders.com/logs/shipped-agentriders-phase-2/"Tests pass" is not "safe to ship": agent-written code needs an adversarial review pass before merge — ours caught an IDOR and a stored XSS that 38 green tests missed.Fri, 16 Oct 2026 00:00:00 GMTFlight LogsClaude CodeEvals: how a rider keeps a dragon accountablehttps://agentriders.com/manual/evals/https://agentriders.com/manual/evals/How to evaluate an AI agent's work with repeatable checks: golden sets, rule-based assertions, LLM-as-judge, human spot-checks, and a tracked pass rate.Sun, 27 Sep 2026 00:00:00 GMTField ManualThe bond: how to give an agent more room, one flight at a timehttps://agentriders.com/manual/agent-trust-and-autonomy/https://agentriders.com/manual/agent-trust-and-autonomy/Four stages of AI agent autonomy and how to earn each: trust the setup, not a personality, change one boundary at a time, and keep a promotion record.Sat, 26 Sep 2026 00:00:00 GMTField ManualBefore the first flight: scope, budget, kill switchhttps://agentriders.com/manual/before-the-first-flight/https://agentriders.com/manual/before-the-first-flight/What to set before an AI agent does real work: a deliverable you can judge, permissions that match the scope, a time and spend limit, and how to stop it.Sat, 26 Sep 2026 00:00:00 GMTField ManualBurns: what goes wrong, what it costs, what to do in the first ten minuteshttps://agentriders.com/manual/burns/https://agentriders.com/manual/burns/What an AI agent incident costs and the first ten minutes: contain the run, establish the facts, choose the smallest recovery. Riders call it a burn.Sat, 26 Sep 2026 00:00:00 GMTField ManualLogging a flight: the template and why every field mattershttps://agentriders.com/manual/logging-a-flight/https://agentriders.com/manual/logging-a-flight/What to record for each AI agent run: model, permissions, elapsed and human time kept separate, a supported cost, the outcome, one change for next time.Sat, 26 Sep 2026 00:00:00 GMTField ManualRiding a wing: running several agents without losing the reinshttps://agentriders.com/manual/riding-a-wing/https://agentriders.com/manual/riding-a-wing/Multi-agent work without losing control: divide by deliverable, give each handoff a contract, keep permissions narrow, budget the whole fleet.Sat, 26 Sep 2026 00:00:00 GMTField ManualReins: permissions that are tight enough to be loosenedhttps://agentriders.com/manual/reins/https://agentriders.com/manual/reins/AI agent permissions, enforced rather than instructed: least privilege, approval before the side effect, retrieved data treated as data, not instructions.Sat, 26 Sep 2026 00:00:00 GMTField Manual