Telemetry
Prompts for Claude Code, Codex, Cursor, and custom agents

Agent Telemetry Prompt Pack

Paste one of these prompts into your coding agent to add structured telemetry for product growth, retention, AI costs, revenue, APIs, and jobs. Each prompt is designed to produce event data you can query later.

Built for future questions

Copy the right prompt

Start from the product, AI cost, revenue, API, or background-job prompt instead of writing analytics requirements from scratch.

Let the agent instrument

Each prompt asks the agent to find important code paths, add structured events, avoid sensitive payloads, and verify ingestion.

Ask better questions later

The event coverage is shaped around activation, retention, reliability, cost, and revenue questions.

full-project

Instrument the core product

Use when you want an agent to find the important product workflows, add structured events, and create a first dashboard.

full-project

Instrument the core product

text
Instrument this project with structured logs using /skill.md.

Use this Telemetry API key: YOUR_API_KEY

Please:
1. Find the most important user-facing flows, background jobs, and AI/tooling workflows.
2. Add structured logging with pragmatic snake_case tables and fields.
3. Capture the key signals for each workflow, including status, latency, identifiers, and error context when relevant.
4. Send test events to Telemetry and verify that ingestion works.
5. Create a high-level dashboard with charts and tables that summarize the most important signals in this project.
6. Tell me what you instrumented, which tables you created, and which dashboard views I should review first.

Prefer small, composable events over giant payloads, and optimize for dashboards that humans can scan quickly.

ai-costs

Track OpenAI and LLM costs

Use when the most important unknown is model usage, token spend, latency, tool calls, and failed AI requests.

ai-costs

Track OpenAI and LLM costs

text
Instrument this project with Telemetry so we can understand OpenAI and LLM usage.

Use /skill.md and this Telemetry API key: YOUR_API_KEY

Please log:
1. Every model request with model, provider, route, feature, input_tokens, output_tokens, total_tokens, estimated_cost_usd, latency_ms, status, and error_type when relevant.
2. Tool calls made by the agent or assistant, including tool_name, status, latency_ms, and result_category.
3. User-facing AI workflow outcomes, including feature, status, retry_count, and whether the user accepted, copied, saved, or discarded the result.
4. A dashboard with daily cost, cost by feature, failures by model, p95 latency, and accepted output rate.

Keep prompts and raw completions out of telemetry unless I explicitly approve storing them.

checkout

Track signup to paid conversion

Use when you need a clean funnel from landing-page visitor to registration, onboarding, checkout, and paid team activity.

checkout

Track signup to paid conversion

text
Instrument the acquisition and revenue funnel with Telemetry.

Use /skill.md and this Telemetry API key: YOUR_API_KEY

Please add structured events for:
1. Marketing page views, CTA clicks, pricing plan selection, docs CTA clicks, and prompt copies.
2. Registration attempts, successful registrations, onboarding steps, team creation, first API key creation, and first telemetry event received.
3. Checkout start, checkout success, plan changes, billing portal opens, and payment failures.
4. Activation milestones: first table created, first query run, first dashboard created, first alert created, and second active day.

Create a dashboard for visitor to signup, signup to activated team, activated team to paid, and weekly retention by activation milestone.

api-reliability

Track API reliability

Use when product quality depends on understanding request volume, latency, errors, and customer-impacting incidents.

api-reliability

Track API reliability

text
Add Telemetry instrumentation for API reliability.

Use /skill.md and this Telemetry API key: YOUR_API_KEY

Please log each important API endpoint with route_template, method, status_code, status, latency_ms, user_id or team_id when available, request_size_bytes, response_size_bytes, and error_type.

Create:
1. A table for API request events.
2. Charts for request volume, error rate, p50 and p95 latency, and top failing endpoints.
3. Alerts for elevated 5xx rate, slow p95 latency, and sudden traffic drops.

Do not log request bodies, auth headers, cookies, secrets, or raw user content.

background-jobs

Track background jobs

Use when queues, cron tasks, imports, billing syncs, or webhooks need operational visibility.

background-jobs

Track background jobs

text
Instrument background jobs and async workers with Telemetry.

Use /skill.md and this Telemetry API key: YOUR_API_KEY

Please log job_started, job_completed, and job_failed events with job_name, queue_name, attempt, status, duration_ms, scheduled_at, started_at, completed_at, item_count, retry_count, and error_type.

Create a dashboard showing throughput by job, failures by job, p95 duration, retry volume, oldest pending job, and dead-letter events. Add alerts for stalled jobs and repeated failures.

retention

Track product usage and retention

Use when you need to understand activation, repeated usage, feature adoption, and which actions correlate with retained accounts.

retention

Track product usage and retention

text
Instrument product usage and retention with Telemetry.

Use /skill.md and this Telemetry API key: YOUR_API_KEY

Please add structured events for:
1. Signup, onboarding step completion, team creation, first successful integration, and first meaningful product action.
2. Core feature usage with feature_name, action, surface, team_id, user_id, status, latency_ms, and error_type when relevant.
3. Retention milestones: second active day, first saved dashboard, first shared artifact, first alert created, and first return after seven days.
4. Expansion signals: invited teammate, upgraded plan intent, billing page viewed, usage limit reached, and support requested.

Create a dashboard for activation rate, weekly active teams, feature adoption, retained teams by first action, and upgrade-intent events.

Templates

Copy a workflow-specific brief

Integrations

Attach Telemetry to the stack users already have

OpenAI Agent Telemetry

Log OpenAI agent runs, tool calls, model usage, latency, cost, and final outcomes with structured events.

Open guide

Browser JavaScript and Web Vitals Telemetry

Collect Core Web Vitals and bounded frontend outcomes through a rate-limited server proxy without exposing a Telemetry API key.

Open guide

Vercel AI SDK Telemetry

Track streaming completions, token usage, retries, latency, and accepted results from AI SDK workflows.

Open guide

Inngest And Trigger.dev Job Telemetry

Instrument async workers, scheduled jobs, retries, failures, and dead-letter events with SQL-ready logs.

Open guide

Stripe Webhook Telemetry

Debug payment, subscription, invoice, retry, and downstream billing sync behavior without storing webhook bodies.

Open guide

Supabase And Postgres App Telemetry

Track product workflows, database-adjacent jobs, API routes, and customer-facing failures from server code.

Open guide

Cloudflare Worker Telemetry

Log edge request status, latency, provider failures, cron runs, and queue workers from Cloudflare Workers.

Open guide

Node.js and Express Structured Logging

Instrument Express route outcomes with stable route templates, status codes, request latency, and safe correlation fields.

Open guide

Next.js Server Event Analytics

Send SQL-ready events from Next.js route handlers and server actions without exposing an ingestion key to the browser.

Open guide

Python and FastAPI Structured Logging

Capture FastAPI request outcomes and latency with the asynchronous Telemetry client and normalized route names.

Open guide

OpenTelemetry Context in Structured Events

Connect Telemetry business events to existing OpenTelemetry traces by recording safe trace and span identifiers at workflow boundaries.

Open guide

AWS Lambda Structured Event Monitoring

Track Lambda invocations, cold starts, duration, retries, and business outcomes with compact structured events.

Open guide

Go HTTP Server Structured Logging

Add typed request-outcome events to Go HTTP services for route error rates, latency percentiles, and release comparisons.

Open guide

Ruby on Rails Structured Event Analytics

Record Rails controller and background-workflow outcomes through Telemetry's HTTP API with safe, queryable fields.

Open guide

Django and Celery Structured Event Monitoring

Connect Django request outcomes and Celery task lifecycles with safe identifiers, latency, retries, and terminal status.

Open guide

Laravel Structured Logging and Queue Analytics

Send Laravel request, command, queue, and billing outcomes as typed events without exposing application secrets or payloads.

Open guide

.NET and Serilog Structured Event Analytics

Add a focused Telemetry outcome event beside Serilog diagnostics for ASP.NET request latency, failures, releases, and customer impact.

Open guide

Spring Boot Structured Event Monitoring

Record Spring MVC and scheduled-workflow outcomes through Telemetry's HTTP API with stable routes, latency, status, and trace context.

Open guide

Temporal Workflow Observability

Track Temporal workflow outcomes, activity retries, schedule-to-start latency, and business milestones without recording workflow payloads.

Open guide

BullMQ Queue Monitoring

Measure BullMQ queue wait, execution duration, retries, failures, and dead-letter growth with SQL-ready lifecycle events.

Open guide

AWS SQS Queue Observability

Track SQS message age, receive attempts, processing outcomes, batch behavior, and dead-letter routing without storing message bodies.

Open guide

Kafka Consumer Lag and Processing Analytics

Monitor Kafka consumer outcomes, partition lag, processing latency, retries, and poison-message handling with structured events.

Open guide

Anthropic Claude API Telemetry

Track Claude API token usage, model, latency, stop reason, errors, cost context, and reviewed product outcomes without storing prompts.

Open guide

LangGraph Agent Observability

Measure LangGraph run outcomes, node and tool failures, retries, checkpoints, human handoffs, latency, and reviewed task quality.

Open guide

node-postgres Pool and Query Telemetry

Instrument node-postgres query fingerprints, connection acquisition, pool pressure, timeouts, transaction outcomes, and database errors without logging SQL parameters.

Open guide

Prisma ORM Database Telemetry

Measure Prisma operation fingerprints, model and method latency, failures, result counts, releases, and database-dependent workflows without collecting raw query parameters.

Open guide

Kubernetes Workload Telemetry

Send bounded Kubernetes restart, readiness, and rollout observations to Telemetry for workload-level SQL analysis.

Open guide

Google Gemini API Telemetry

Track Gemini request latency, model usage, tokens, finish reason, errors, and reviewed product outcomes without storing prompts or generated content.

Open guide

Amazon Bedrock Model Telemetry

Measure Bedrock Converse requests by model or inference profile, token usage, latency, stop reason, retries, and business outcome.

Open guide

Azure OpenAI Responses Telemetry

Track Azure OpenAI deployment usage, token cost, latency, failures, and product outcomes with editable SQL-ready events.

Open guide

LangChain Agent Outcome Telemetry

Connect LangChain agent runs and tool outcomes to product-facing cost, reliability, handoff, and acceptance metrics without duplicating raw traces.

Open guide

Pino Structured Event Analytics

Pair Pino diagnostic logs with bounded Telemetry outcome events for Node.js request, job, and product reliability analysis.

Open guide

Winston Structured Event Analytics

Connect Winston application diagnostics to small SQL-ready request, workflow, and job outcomes without duplicating the entire log stream.

Open guide

NestJS Request and Workflow Telemetry

Instrument NestJS controllers and providers with normalized route outcomes, latency, errors, releases, and approved account context.

Open guide

Flask and SQLAlchemy Telemetry

Measure Flask request outcomes and SQLAlchemy transaction behavior with bounded Python events, stable route templates, and safe error categories.

Open guide

Sidekiq Job Telemetry

Track Sidekiq execution outcomes, attempts, queue wait, errors, and releases from server middleware without copying job arguments.

Open guide

Redis and node-redis Telemetry

Measure Redis command outcomes, latency, cache behavior, reconnects, and bounded error categories alongside node-redis.

Open guide

Claude Agent SDK Telemetry

Track Claude Agent SDK run outcomes, duration, tool activity, turns, cost, and approved product signals without storing prompts or tool payloads.

Open guide

Pydantic AI Agent Telemetry

Measure Pydantic AI run outcomes, validated outputs, retries, tool activity, latency, usage, and product acceptance with safe structured events.

Open guide

CrewAI Workflow Telemetry

Track CrewAI crew and flow outcomes, task counts, handoffs, retries, latency, cost, and accepted results without retaining agent conversations.

Open guide

Google ADK Agent Telemetry

Measure Google Agent Development Kit sessions, run outcomes, tool activity, handoffs, latency, and approved product signals with SQL-ready events.

Open guide

Mastra Agent Telemetry

Track Mastra agent and workflow outcomes, tool activity, latency, retries, cost, and product acceptance alongside built-in traces and evals.

Open guide

LlamaIndex Agent Telemetry

Track LlamaIndex agent and workflow outcomes, tool activity, latency, retrieval versions, cost, and reviewed quality with structured events.

Open guide

DSPy Program Evaluation Telemetry

Measure DSPy program latency, failures, metric scores, optimizer versions, model cost, and accepted outcomes across releases with SQL-ready events.

Open guide

AutoGen Timeout and Multi-Agent Telemetry

Track AutoGen task-flow state, timeouts, team and agent outcomes, tool activity, handoffs, latency, failures, cost, and releases with compact structured events.

Open guide

Semantic Kernel Agent Telemetry

Measure Semantic Kernel function and agent outcomes, tool activity, model usage, latency, cost, and releases alongside OpenTelemetry traces.

Open guide

MCP Server and Tool Telemetry

Track Model Context Protocol tool outcomes, latency, errors, approvals, retries, clients, and releases without storing arguments or returned content.

Open guide

RabbitMQ Queue Telemetry

Track RabbitMQ publish confirmation, delivery, acknowledgement, redelivery, queue wait, retries, and dead-letter outcomes with structured events.

Open guide

MySQL Query and Pool Telemetry

Track normalized MySQL operations, pool wait, transaction outcomes, controlled error categories, and release regressions without storing raw SQL or parameters.

Open guide

MongoDB Operation Telemetry

Track named MongoDB operations, latency, result counts, retries, transaction outcomes, and release regressions without collecting documents or query values.

Open guide

Google Cloud Run Telemetry

Track Cloud Run request and job outcomes, cold-start context, instance concurrency, retries, latency, and releases with application-owned structured events.

Open guide

Google Cloud Pub/Sub Telemetry

Track Pub/Sub publish, delivery, acknowledgement, redelivery, ordering, queue age, and dead-letter outcomes with stable message identifiers.

Open guide

Azure Functions Telemetry

Track Azure Functions HTTP, timer, queue, and event-trigger outcomes with invocation, retry, latency, release, and customer-impact context.

Open guide

Azure Service Bus Telemetry

Track Azure Service Bus sends, receives, lock renewal, settlement, redelivery, deferral, and dead-letter outcomes without collecting message bodies.

Open guide

OpenAI Responses API Telemetry

Measure OpenAI Responses API latency, token usage, tool activity, failures, and downstream outcomes without collecting prompts or generated content.

Open guide

LiteLLM Gateway and SDK Telemetry

Track LiteLLM provider routing, retries, fallbacks, token usage, latency, cost estimates, and accepted outcomes across a controlled model gateway.

Open guide

Elixir Phoenix Telemetry Integration

Attach to Phoenix request lifecycle events and forward a bounded terminal request outcome without copying connection data, parameters, or exception text.

Open guide

AWS ECS and Fargate Telemetry Integration

Add ECS task family, revision, availability zone, and release context to application outcomes using the local task metadata endpoint.

Open guide

GitHub Actions Workflow Telemetry Integration

Send a bounded terminal workflow outcome from GitHub Actions with run, attempt, job, conclusion, duration, and release context.

Open guide

n8n Workflow Telemetry

Send n8n workflow completion, failure, retry, item-count, and downstream delivery outcomes to a bounded Telemetry event through the HTTP Request node.

Open guide

Use cases

Send high-intent visitors to a focused setup page

View pricing

Claude Code Observability

Give Claude Code a prompt that makes telemetry part of the implementation pass instead of a separate cleanup project.

Open setup page

Cursor Telemetry Setup

A copyable setup prompt for adding event tables, funnel tracking, and dashboards from inside Cursor.

Open setup page

Codex Instrumentation Prompt

A focused prompt that asks Codex to instrument the rest of the product, verify events, and summarize coverage gaps.

Open setup page

OpenAI Cost Monitoring

Monitor OpenAI and LLM spend by model, feature, customer, latency, error rate, and outcome with SQL dashboards and budget alerts.

Open setup page

Product Analytics for Retention

Use agent-installed structured events to learn which early actions create returning users and revenue-ready teams.

Open setup page

AI Agent Telemetry and Observability

Instrument AI agent telemetry for runs, tool calls, retries, latency, model cost, failures, and accepted outcomes in SQL-ready event tables.

Open setup page

Background Job Monitoring

Use structured events to see job throughput, retries, failures, dead letters, queue health, and p95 duration.

Open setup page

Webhook Debugging

Track webhook delivery, processing, retries, deduplication, downstream jobs, and failures without storing raw payloads.

Open setup page

API Reliability Monitoring

Track API request volume, status codes, latency, timeouts, customer impact, and failed endpoints with SQL.

Open setup page

Crypto And Onchain Automation Monitoring

Track indexed events, agent actions, transaction costs, wallet workflows, tool calls, and failed automation jobs.

Open setup page

Infrastructure Metrics With SQL

Send structured infrastructure events when you need queryable host and container history without a large monitoring rollout.

Open setup page

Usage-Based Billing Analytics

Build a defensible usage ledger, quota dashboard, overage workflow, and billing reconciliation from idempotent structured events.

Open setup page

Security and Audit-Log Analytics

Design privacy-aware security events for authentication failures, access changes, privileged actions, and incident timelines.

Open setup page

AI Agent Security Monitoring

Monitor tool authorization, policy denials, approval queues, risky action classes, and release changes without storing prompts, credentials, or tool payloads.

Open setup page

AI Agent Quality and Evaluation

Connect agent runs, reviewer outcomes, human handoffs, cost, and release changes to a repeatable quality-evaluation workflow.

Open setup page

Database Reliability Monitoring with SQL

Track safe query fingerprints, pool pressure, transaction rollbacks, lock contention, replication lag, and migration outcomes without collecting raw SQL parameters.

Open setup page

Frontend Performance Monitoring with SQL

Track typed LCP, INP, and CLS samples by stable route and release, then use SQL to find frontend regressions without collecting raw URLs or page content.

Open setup page

Kubernetes Reliability Monitoring with SQL

Track Kubernetes workload transitions and application outcomes together so SQL can separate planned rollout activity from repeated restarts and serving impact.

Open setup page

SaaS Revenue Analytics with SQL

Build an auditable SaaS revenue model from subscription movements, invoices, entitlements, and product outcomes instead of relying on disconnected billing snapshots.

Open setup page

Telemetry Data Quality Monitoring with SQL

Monitor event freshness, required fields, types, duplicates, schema versions, and volume so broken instrumentation is found before it becomes a misleading business or reliability metric.

Open setup page

Comparisons

PostHog For Backend Events

PostHog is a broad product stack with product analytics, funnels, retention, SQL, and a data warehouse. Telemetry is the narrower choice when the main job is structured backend event capture, inspectable SQL, and agent-installed operational dashboards.

Read comparison

Datadog Alternative For Startups

Datadog is a broad observability and security platform. Telemetry is a focused alternative when a small team wants structured application events, SQL dashboards, and threshold alerts without first adopting a full infrastructure and APM suite.

Read comparison

ClickHouse Logging API Without Running ClickHouse

ClickHouse and ClickStack provide a powerful, scalable analytics and observability foundation. Telemetry is the smaller managed workflow when you want structured event querying without designing or operating the surrounding database and observability stack.

Read comparison

Axiom Alternative For Structured Event Analytics

Axiom is a mature cloud-native telemetry platform with ingestion, search, APL queries, dashboards, monitors, and broad observability workflows. Telemetry is the narrower option when a small team specifically wants typed application events, familiar SQL, and coding-agent-installed operational analysis.

Read comparison

Better Stack Logs Alternative For SQL Event Analytics

Better Stack combines logs, dashboards, alerting, incident management, and uptime workflows. Telemetry is the more focused choice when the core requirement is structured application outcomes queried with SQL and installed from codebase-aware prompts.

Read comparison

Honeycomb Alternative For Lightweight Wide Events

Honeycomb is built for high-cardinality observability and debugging distributed systems with wide events and traces. Telemetry is a lighter alternative when the first need is custom application and business events, SQL analysis, and simple dashboards or alerts.

Read comparison

Grafana Loki Alternative For Structured Log SQL

Grafana Cloud and Loki provide a broad logs, metrics, traces, dashboards, and alerting ecosystem. Telemetry is the focused alternative when a team wants managed JSON event tables and SQL without assembling or operating the surrounding observability stack.

Read comparison

Sentry Alternative For Structured Events and SQL

Sentry combines error monitoring, tracing, profiling, session replay, and logs around application health. Telemetry is the narrower alternative when a team's first requirement is custom structured workflow events and SQL analysis rather than exception-centric debugging.

Read comparison

Splunk Alternative for Structured Events

Splunk provides broad search, security, log analytics, infrastructure monitoring, APM, real-user monitoring, and OpenTelemetry-based collection. Telemetry is the narrower option when a team wants purpose-built application events, SQL, and a smaller operating surface.

Read comparison

Elastic Alternative for Structured Event SQL

Elastic Observability combines Elasticsearch, Kibana, logs, metrics, APM, profiling, and OpenTelemetry collection. Telemetry is the focused alternative when the main job is managed application-event ingestion and SQL analysis without operating or modeling a broader Elastic deployment.

Read comparison

New Relic Alternative for Structured Events

New Relic is a broad observability platform spanning APM, infrastructure, logs, browser, mobile, synthetics, errors, and NRQL. Telemetry is the narrower choice when a team wants custom structured outcomes, SQL, and a lightweight event-analysis workflow.

Read comparison

Telemetry vs Langfuse for AI Observability

Langfuse is an LLM engineering platform for traces, prompt management, evaluation, datasets, and experiments. Telemetry is the narrower SQL-first option for compact agent, cost, reliability, and product-outcome events.

Read comparison

Telemetry vs LangSmith for AI Observability

LangSmith provides tracing, evaluation, datasets, experiments, and deployment options for LLM applications. Telemetry focuses on compact outcome events and SQL across AI and application workflows.

Read comparison

Telemetry vs Arize Phoenix

Arize Phoenix is an open-source AI observability and evaluation platform built around traces, prompts, datasets, and experiments. Telemetry focuses on compact structured outcomes and SQL.

Read comparison

Telemetry vs Pydantic Logfire

Pydantic Logfire combines OpenTelemetry-based application observability with AI tracing and conversation views. Telemetry is a narrower structured-event and SQL outcome layer.

Read comparison

Telemetry vs Mixpanel

Mixpanel is a product and digital analytics platform built around behavioral reports such as insights, funnels, flows, retention, and cohorts. Telemetry is the narrower choice for SQL over application-owned product and operational events.

Read comparison

Telemetry vs Amplitude

Amplitude is a digital analytics platform with product-analysis workflows for events, funnels, retention, journeys, cohorts, and experimentation. Telemetry focuses on compact structured events and explicit SQL.

Read comparison

Telemetry vs Braintrust

Braintrust is an AI evaluation and observability platform built around experiments, datasets, scorers, prompts, and production traces. Telemetry focuses on SQL over selected AI and product outcomes.

Read comparison

Telemetry vs Helicone

Helicone combines an AI gateway with LLM request observability, sessions, cost analytics, caching, and alerts. Telemetry is a provider-neutral SQL layer for selected AI and application outcomes.

Read comparison

Telemetry vs Opik

Opik is an open-source LLM evaluation and observability platform with traces, datasets, metrics, experiments, and test suites. Telemetry focuses on SQL over bounded AI and application outcomes.

Read comparison

Telemetry vs W&B Weave

W&B Weave is an AI observability and evaluation platform with traces, datasets, scorers, versioning, feedback, and production monitoring. Telemetry focuses on SQL over selected AI and product outcomes.

Read comparison

Telemetry vs MLflow for GenAI

MLflow provides OpenTelemetry-compatible GenAI tracing, evaluations, prompt versioning, experiments, and production monitoring. Telemetry focuses on bounded outcome events and SQL across the application.

Read comparison

Telemetry vs OpenLIT

OpenLIT is an open-source, OpenTelemetry-native AI engineering platform with auto-instrumentation, traces, evaluations, prompts, experiments, dashboards, and collectors. Telemetry focuses on SQL outcome events.

Read comparison