Browse the library
Use cases
Claude Code Observability
Give Claude Code a prompt that makes telemetry part of the implementation pass instead of a separate cleanup project.
Open use caseCursor Telemetry Setup
A copyable setup prompt for adding event tables, funnel tracking, and dashboards from inside Cursor.
Open use caseCodex Instrumentation Prompt
A focused prompt that asks Codex to instrument the rest of the product, verify events, and summarize coverage gaps.
Open use caseOpenAI Cost Tracking
Track LLM calls by model, feature, user, cost, latency, error rate, and outcome so growth does not hide margin problems.
Open use caseDatadog Alternative for Startups
Use structured event tables and SQL dashboards when you want clear product answers without a heavyweight observability rollout.
Open use caseProduct Analytics for Retention
Use agent-installed structured events to learn which early actions create returning users and revenue-ready teams.
Open use caseAI Agent Observability
Track agent runs, tool calls, retries, latency, model cost, failures, and accepted outcomes in SQL-ready event tables.
Open use caseBackground Job Monitoring
Use structured events to see job throughput, retries, failures, dead letters, queue health, and p95 duration.
Open use caseWebhook Debugging
Track webhook delivery, processing, retries, deduplication, downstream jobs, and failures without storing raw payloads.
Open use caseAPI Reliability Monitoring
Track API request volume, status codes, latency, timeouts, customer impact, and failed endpoints with SQL.
Open use caseCrypto And Onchain Automation Monitoring
Track indexed events, agent actions, transaction costs, wallet workflows, tool calls, and failed automation jobs.
Open use caseInfrastructure Metrics With SQL
Send structured infrastructure events when you need queryable host and container history without a large monitoring rollout.
Open use caseStart with one workflow
Give your coding agent the context and verify real events
Create a free API key, choose the closest resource, and ask the agent to run the flow before it considers the instrumentation done.