The Scheduled Agents We Run, With the Prompts
How RunWhen uses RunWhen, part two: the scheduled Agents behind our vulnerability, certificate, PR review, environment health, storage and test-failure reports, with the prompts that drive them.
sre
11 posts with the tag “sre”
Find the leaks before you build the agents
Automating operations has no natural starting point, so most teams rank by intuition. We read a ticket estate instead. Three patterns show up again and again: hand-offs cost 5.6x, answering beats fixing four to one, and it is never one automation but thousands of small ones.
Safe by Design
Giving an agent production access is the easy part. Making it safe is a set of design decisions: a reviewed skill registry, RBAC through scoped assistants, read-only by default, human-in-the-loop, the Agent-Runner pattern, and a complete audit trail. 500,000+ production hours, zero AI-caused incidents.
Safe-for-Prod Harness: The Agent-Runner Pattern
Agents shouldn’t hold credentials. The Agent-Runner pattern separates the reasoning plane from the execution plane. Blast radius gets scoped per network boundary, and agent load on your infrastructure becomes a setting.
How RunWhen Uses RunWhen
A screenshots-first tour of how our own team — SRE, platform, developers, QA and the CEO — actually uses RunWhen Agents day to day. Daily newsletters instead of alerts, Slack root-cause answers, FinOps in minutes, and release readiness before standup.
Don't Make Your Best Model Grep
Production troubleshooting is where agents get handed a haystack. Let code do the searching, and spend the model on judgment — with reviewed, shared skills instead of code improvised at runtime.
New whitepaper: Safe For Prod — Building Operational Agents
A new whitepaper by Kyle Forster on why agents with freeform skills will never be safe for production, and why the durable investment is a library of narrow, scoped safe skills that every later agent reuses. Free PDF download.
What Changed? The Slash Command for Catching Up
You were out for a few days. A deploy went out, SHAs moved, a couple of things shipped. What actually changed? /dev-whats-changed answers the catching-up question with three ordered layers — code that’s live, commits since the last release, and only then a deeper dive — so the story leads with cause, not with infra alerts.
Our Favorite Slash Commands — A Series on How We Actually Operate
We built 22 slash commands for our own workspace. This series walks through the ones we use most, starting with how we decide whether to ship a release.
Release Readiness: The Slash Command That Replaced Our Pre-Release Checklist
We run /mgr-release-readiness before every release. Here is what it checks, how it works, and what it told us today — with live results from our actual environment.
NOT A DEMO — Be a Guest SRE in Our Real Environment
Drop into the same workspace our team uses every day. Real clusters, real agents, real remediations. No sandbox. About 45 minutes.