cohere-incident-runbook

name	cohere-incident-runbook
description	Execute Cohere incident response procedures with triage, mitigation, and postmortem. Use when responding to Cohere API outages, investigating errors, or running post-incident reviews for Cohere integration failures. Trigger with phrases like "cohere incident", "cohere outage", "cohere down", "cohere on-call", "cohere emergency", "cohere broken".
allowed-tools	Read, Grep, Bash(kubectl:*), Bash(curl:*)
version	1.5.0
license	MIT
author	Jeremy Longshore <[e-mail]>
tags	["saas","ai","nlp","cohere"]
compatibility	Designed for Claude Code

Cohere Incident Runbook

Overview

Rapid incident response procedures for Cohere API v2 outages. Covers triage, mitigation, communication, and postmortem for Chat, Embed, Rerank, and Classify endpoints.

Prerequisites

• Access to status.cohere.com
• kubectl access to production cluster
• Prometheus/Grafana access
• PagerDuty/Slack communication channels

Severity Levels

Level	Definition	Response Time	Example
P1	All Cohere endpoints down	< 15 min	API returning 5xx globally
P2	Degraded (rate limits, high latency)	< 1 hour	429 errors, P95 > 10s
P3	Single endpoint affected	< 4 hours	Embed works, Chat fails
P4	Non-blocking issue	Next business day	Slow response, minor errors

Quick Triage (Run These First)

# 1. Check Cohere service status
curl -s https://status.cohere.com/api/v2/status.json | jq '.status.description'

# 2. Test each endpoint directly
echo "--- Chat ---"
curl -s -o /dev/null -w "%{http_code}" \
  -X POST https://api.cohere.com/v2/chat \
  -H "Authorization: Bearer $CO_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"model":"command-r7b-12-2024","messages":[{"role":"user","content":"ping"}]}'

echo -e "\n--- Embed ---"
curl -s -o /dev/null -w "%{http_code}" \
  -X POST https://api.cohere.com/v2/embed \
  -H "Authorization: Bearer $CO_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"model":"embed-v4.0","texts":["test"],"input_type":"search_document","embedding_types":["float"]}'

echo -e "\n--- Rerank ---"
curl -s -o /dev/null -w  \
  -X POST https://api.cohere.com/v2/rerank \
  -H  \
  -H  \
  -d 


curl -sf https://api.yourapp.com/api/health | jq 


curl -s  | jq