Agent Telemetry Prompt Pack

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.

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.

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.

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.

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.

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.