Incident Scribe Agent with OpenCode
Incident comms is low volume and high consequence, which is the opposite of most agent workloads. OpenCode lets you choose the model, so this is the one template where paying for a stronger one is easy to justify: a handful of runs a week, each read by people who are not engineers. Your runbook notes and cadence carry over whatever you pick.
Watch it work before it's live
Run a staged conversation — no account needed. The agent handles it for real while a simulated world answers its tool calls; nothing touches real accounts, and nothing is actually sent.
P1: Checkout API error rate 11% for 6 minutes
TriggeredMonitor checkout-api 5xx ratio triggered at 14:02 UTC against a 2% threshold, currently 11.4%, with 340 of the last 2,980 requests returning 502 from the payments upstream. Two alerts merged into this incident, both from eu-west-1. Escalation policy Payments Primary, nobody has acknowledged yet.
Set up in minutes
Using this template drops you into a guided setup. It asks exactly this, nothing else:
Connect PagerDuty
One sign-in. The agent acts through your account, scoped to what this template uses.
Connect Slack
One sign-in. The agent acts through your account, scoped to what this template uses.
Runbook notes
What your team needs said about each service - what it does, who feels it when it breaks, and any standing context you want repeated in an update.
Comms style
How your incident updates should read and how often - the tone, who is reading, and the cadence that sets the next update time, for example every 30 minutes while a P1 is open.
Runs on OpenCode
Preselected for this page — connect your OpenCode account during setup, or switch to NoClick's built-in models with one click.
Watch it handle a test run
A staged conversation against a simulated world — then it’s live.
Why OpenCode for this agent
Low volume, high stakes
A few incidents a week means the model cost is small and the cost of a confusing update is not, so this choice should not be made on price.
Tune the writing, not the code
The comms style variable sets tone and cadence. The model is what decides how closely that instruction is followed when an alert payload is ugly.
Before you fork
Does a stronger model actually read differently here?
It mostly shows in the impact and what we know sections, where the job is to say what the alert data supports in a sentence a non-engineer can act on. Compare on the staged third party degradation, since that is the one where accurate and alarming are a word apart. The other sections are close to templated and rarely separate two models.
Run it with a different agent
Put Incident Scribe Agent to work on OpenCode
Free to start. Guided setup, a test run against staged conversations, and it's live.