OiOi

Team Kit

Triage the incident, ship the fix, keep the knowledge.

Oi gives engineering teams a connected crew of AI contexts, workflows, and guardrails that pulls runbooks, past incidents, and traces to triage live issues fast, then writes the resolution back to team memory — all with read-only production access.

Team Kit

Engineering

An on-call suite that triages incidents fast and writes the fix back to the team's runbooks — with read-only production safety.

Includes:

  • Incident Investigator
  • PR & Deploy Context
  • Incident Triage
  • Post-Incident Write-Back
ConnectsGitHubLinearFigma
GuardrailsRead-Only Production · Approved Repos
Explore Engineering

Triage in minutes

On an incident alert, gather the runbook, past fixes, and recent traces into a triage summary — so on-call starts from context, not a blank page.

Ship with context

Summarise recent PRs, deploy notes, and Linear issues for a service, so the engineer shipping the fix knows exactly what changed and why.

Read-only production

A hard guardrail lets the agent inspect any system but never deploy, merge, or modify production — and restricts access to approved repos only.

What drives the business: Engineering velocity is throttled by two hidden taxes: the time it takes to triage an incident, and the knowledge that evaporates once it's resolved. Every minute of an outage is user trust and revenue; every fix that lives only in one engineer's head is the same incident debugged from scratch next quarter. The economics are about compounding — triage faster by pulling the runbook, history, and traces automatically, and write the resolution back so the team gets faster every time, without ever handing an agent write access to production.

Inside the kit

Contexts, workflows, and guardrails that work together.

The Incident Investigator pulls the context, Incident Triage turns an alert into a summary, Post-Incident Write-Back saves the fix to memory, and the read-only and approved-repos guardrails keep every action safe — so the team triages faster and gets smarter after every incident, without touching production.

Contexts

Context

Incident Investigator

Retrieve runbooks and past incident fixes to debug live issues fast.

Context

PR & Deploy Context

Summarise recent PRs, deploy notes, and traces for a service.

Context

Runbook Librarian

Retrieves and keeps the team's runbooks current, surfacing the right procedure for a service and flagging steps that have gone stale.

Context

Release Notes Writer

Turns merged GitHub PRs and closed Linear issues into clear release notes and a changelog entry, ready to review and publish.

Workflows

Workflow

Incident Triage

On an incident alert, gather runbook, history, and traces, then draft a triage summary.

Workflow

Post-Incident Write-Back

Save the resolved fix back to team runbooks and memory.

Workflow

PR Review Digest

New PR opened → related issues, prior changes, and design context gathered from GitHub, Linear, and Figma → a review-ready summary posted for the team.

Guardrails

Guardrail

Read-Only Production Access

The agent may inspect systems but never deploy, merge, or modify production.

Guardrail

Approved Repos & Systems Only

Restrict access to whitelisted repos and connected systems.

Guardrail

Secret & Credential Guard

Blocks any output that would surface API keys, tokens, or credentials from code or logs — secrets never leave the systems that hold them.

The numbers it moves

Pointed at the metrics that decide the job.

Faster time-to-triage

On-call starts with the runbook, history, and traces in hand.

Knowledge that compounds

Every fix written back to team memory.

Reviews with full context

PRs summarised against issues and prior changes.

Production stays safe

Read-only access enforced on every action.

Connects to

Grounded in the systems you already run.

GitHubGitHub

Repos, PRs, and issues through GitHub MCP — the change history behind every incident and release.

LinearLinear

Issues and projects through Linear MCP — the work context for triage and review.

FigmaFigma

Design files and handoff through Figma MCP — the intended behaviour behind a change.

SentrySentry

Live errors, traces, and release health to ground incident triage in what's actually breaking in production.

Ready-made for Engineering

Give your team a shared AI crew from day one.

Install the kit, connect your tools, and put every context, workflow, and guardrail to work — tailored to how your team actually operates.