Consistent event fields
The instructions ask the agent to name events, use snake_case fields, specify units, and include identifiers for SQL joins.
Put the skill to work
Add events to one agent workflow
Start with a ready API key and agent prompt, run one representative workflow, and verify the resulting event before building a dashboard.
What the skill covers
Check the events your agent adds
Keep private data out
Raw prompts, completions, credentials, authorization headers, and private payloads stay out of the analytics path by default.
Verify that events arrive
Run the workflow, check that its events arrive, and query the results before calling the setup finished.
Telemetry wrapper examples
Tell the agent which events to send
Pass the API key from trusted server-side configuration and verify a real event with SQL. Anonymous keys support this workflow; claim the workspace before creating dashboards. Keep the Python User-Agent header so requests reach the API.
typescript
TypeScript telemetry wrapper
javascript
type TelemetryEvent = Record<string, unknown>;
export async function emitTelemetry(
apiKey: string,
table: string,
data: TelemetryEvent,
) {
const response = await fetch("https://api.telemetry.sh/log", {
method: "POST",
headers: {
Authorization: apiKey,
"Content-Type": "application/json",
},
body: JSON.stringify({ table, data }),
});
if (!response.ok) {
throw new Error(`Telemetry ingestion failed: ${response.status}`);
}
}python
Python telemetry wrapper
python
import json
from urllib.request import Request, urlopen
def emit_telemetry(api_key: str, table: str, data: dict) -> int:
request = Request(
"https://api.telemetry.sh/log",
data=json.dumps({"table": table, "data": data}).encode(),
headers={
"Authorization": api_key,
"Content-Type": "application/json",
"User-Agent": "telemetry-agent/1.0",
},
method="POST",
)
with urlopen(request, timeout=5) as response:
return response.statusStart here
Paste the setup instructions
Replace the placeholder with a server-side API key, then ask the agent to inspect the repository before choosing event boundaries.
agent prompt
AI agent observability prompt
text
Instrument this project with structured logs using /skill.md.
Use this Telemetry API key: YOUR_API_KEY
Anonymous keys support logging and synchronous SQL without signup. Claim the existing workspace at https://telemetry.sh/register with the same key before creating dashboards or alerts. If it is unclaimed, query the event to verify delivery and report which features need signup.
Please:
1. Find the most important user-facing flows, background jobs, and AI/tooling workflows.
2. Add structured logging with snake_case table and field names.
3. Capture the key signals for each workflow, including status, latency, identifiers, and error context when relevant.
4. Run one real user-facing or operational flow through the instrumented application and verify its event appears in Telemetry. Do not use telemetry_quickstart for this milestone.
5. Run a read-only query over that real event, then 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 real flow you verified, which tables you created, and which dashboard views I should review first.
Keep event payloads small and focused. Make dashboard labels and charts easy to scan.Review boundary
Have your team review the event fields
The skill helps an agent choose where to add events. Your team decides what each event means, which fields it may contain, how long to keep it, and when to alert.
- Review every new table and field before deployment.
- Use approved identifiers. Keep private payloads out of events.
- Verify success, failure, and terminal outcomes.
Continue the workflow
SQL reference
The SQL dialect, expressions, types, and functions supported by Telemetry's query engine.
Open guideAI agent telemetry dashboard template
Define the event fields first. Then build a dashboard to check runs, tool calls, latency, cost, failures, and task results.
Open guideAI agent monitoring
Choose when to record runs, tool calls, model requests, costs, failures, and task results.
Open guideAgent prompt pack
Copy focused briefs for product analytics, OpenAI costs, APIs, revenue, and jobs.
Open guideStructured logging guide
Review event design, privacy boundaries, delivery behavior, and verification.
Open guideClaude Code observability
Ask Claude Code to add events with consistent fields and verify them with SQL.
Open guideCursor telemetry setup
Ask Cursor to add activation and retention events, then check the dashboard it creates.
Open guideCodex instrumentation prompt
Tell Codex which product actions and failures to log, and ask it to verify that the events arrive.
Open guideOpenAI cost tracking guide
Build a SQL dashboard that compares model costs, token use, latency, and retries with accepted results.
Open guideAdd events, then check the results
Start free with a provisioned workspace, API key, agent prompt, and starter dashboard. Connect one real workflow, verify the event, and save the first useful query.