AI-assisted SQL for event analytics

How it works

How to set it up

Give the question enough context

Name the table and explain how to calculate the metric. Specify the time range, grouping, and columns you want back.

Check the query logic

Check field types, joins, denominators, null handling, and time boundaries before trusting the chart.

Review before saving

Save the query after you have checked its results. Add a clear name so a teammate can find and reuse it.

Generating an editable query with AI

Ask a question and review the generated SQL in the editor.

Boundaries

What this does not replace

Generated SQL is a starting point, not an authoritative metric definition or security decision.
The agent only has the context you give it in the schema, prompt, and event definitions.
Check fields, joins, denominators, null handling, and time windows before using a query in a dashboard or alert.

Try the example

Read the schema, SQL, and sample result

This example includes the schema, read-only SQL, and synthetic results. Use it to check how the query works. It does not measure customer results.

1. Event schema

One row in agent_events, with the types used by the query made explicit.

timestamp_utc: Timestamp
event_name: Utf8
data.tool_name: Utf8
data.status: Utf8
data.args.operation: Utf8
data.latency_ms: Float64

Browse event contracts

2. Read-only SQL

Which AI tools and arguments are associated with the most failed calls?

SELECT
  "data.tool_name" AS tool_name,
  "data.args.operation" AS operation,
  COUNT(*) AS calls,
  SUM(CASE
    WHEN "data.status" = 'failed' THEN 1 ELSE 0
  END) AS failures,
  100.0 * SUM(CASE
    WHEN "data.status" = 'failed' THEN 1 ELSE 0
  END) / NULLIF(COUNT(*), 0) AS failure_rate_pct,
  approx_percentile_cont("data.latency_ms", 0.95) AS p95_latency_ms
FROM agent_events
WHERE event_name = 'agent_tool_called'
  AND timestamp_utc >= now() - INTERVAL '7 days'
GROUP BY "data.tool_name", "data.args.operation"
HAVING COUNT(*) >= 20
ORDER BY failure_rate_pct DESC, calls DESC;

3. Synthetic result

CRM lookup is both the least reliable tool operation and the slowest at p95.

tool_name	operation	calls
crm_lookup	search_contact	842
order_api	fetch_order	2210
knowledge_search	semantic_search	4510

Inspect query, result, and caveats

Capabilities

What is included

Schema-aware SQL generation

Prompt-to-visualization assistance

Generated SQL remains editable in the Query workspace

Works with the same tables, dashboards, and alerts as human-written analysis

Agent skill and prompt pack for repository-level instrumentation

Documentation

AI-assisted SQL guide Agent prompt pack Query API

See the analysis

SQL recipes that use this capability

Query nested AI tool-call events

Filter dotted nested fields and rank failing tools without flattening the original event payload.

Open recipe

Measure accepted AI outputs per dollar

Connect model spend to accepted, saved, or otherwise useful product outcomes.

Open recipe

Calculate weekly cohort retention

Group users by first activity week and measure the percentage returning in later weeks.

Open recipe

Customer evidence

How teams use this workflow

"Telemetry is my go-to for dumping logs and tracking events. It's straightforward, the SQL workbench is fast, and I don't have to worry about the schema upfront. Running SQL over a REST API lets me fetch data and dump reports straight to Slack. It's the essentials of what Sentry did for me."

Prem Viswanathan, SwiftCX

Read the customer story

Related capabilities