Four calls per exception, one of them an aggregate query, and the number of exceptions is entirely a function of what you point at the trigger. OpenCode puts the underlying model under your control, which is how a triage agent stays affordable on a product that throws a lot: something small for the volume, something larger only if the issues start reading thin.
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.
TypeError: t.workspaceId is undefined
at resolveWorkspace (assets/index-4f2a91.js:1:88214), at WorkspaceSwitcher (assets/index-4f2a91.js:1:91002), at renderWithHooks. Thrown on /settings/members three minutes into the session, with flag new-workspace-switcher active.
Using this template drops you into a guided setup. It asks exactly this, nothing else:
Connect PostHog
One sign-in. The agent acts through your account, scoped to what this template uses.
Connect Linear
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.
Triage rules
How you decide an exception matters and where it goes - the person and occurrence counts for each severity, the window you count over, the Linear team that receives issues, and the exceptions you already know about and want left alone.
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.
The trigger decides how many exceptions arrive and the model decides what each one costs. Two dials rather than one is why this stays manageable.
Most of the run is retrieval and layout, and only the wideness judgement leans on the model. Paying reasoning prices for the whole thing is optional.
Each exception costs a handful of reads and the aggregate is the only heavy one. A project throwing thousands of errors an hour should be filtered at the trigger rather than absorbed by the agent. On an ordinary product the extra querying sits below what a single dashboard refresh costs you.
Free to start. Guided setup, a test run against staged conversations, and it's live.