# OpenAI published a data-agent template whose own instructions require the metric definitions, trusted queries and corrections to be supplied by the team using it

Page: https://flyvolo.ai/en/changes/ev-20260910-data-analyst-3
Date: 2026-09-10 · Stage: Capability
Can this record move a task judgement? no
Occupation: https://flyvolo.ai/en/careers/data-analyst

## Scope

A vendor walkthrough and reference implementation, not a report of use at any company — no employer is named as running it. Recorded as capability, which on this site never moves an assessment. What each task link rests on: the template's own instructions cover table discovery, read-only SQL and explaining the findings (writing queries); its step 2 has the team replace the illustrative metric definitions, trusted filters and previously reviewed queries with its own reviewed ones, and step 6 saves a correction only when a person explicitly asks for it (owning the definitions the tools rely on); and the examples it prints — filters excluding employees and test accounts and the current incomplete day, and a note that mobile checkout tracking changed on 18 August — are an analyst's knowledge of where the data lies, supplied by a person rather than found by the agent. Dated from the cookbook commit that added the example, because the showcase page carries no date.

## Source

- OpenAI Developers — Cookbook: Build a data analyst with the Agents API — https://developers.openai.com/cookbook/examples/agents_api/apps/data_analyst/readme (primary source)

## What this means

The template splits this job in the vendor's own words. Table discovery, read-only SQL and writing up the finding are the agent's steps. The metric definitions, the trusted filters and the reviewed queries are what its second step has the team add, and a correction is saved only when a person asks for it. That is this page's emerging task, described by the party with every reason to describe the tool as self-sufficient.

## What it does not show yet

It shows what the tool is built to do, not that a team runs it. No employer is named, nothing is measured, and the template's own steps leave the metric definitions, trusted filters and reviewed queries to the team using it. A template being published is not adoption, which is why this record cannot move any judgement on this page.

## How to verify it yourself

Open the template and run one question you actually answered last week. Watch what its second step asks you to supply — metric definitions, trusted filters, previously reviewed queries. Where it gets that wrong is the part of this job that is still yours; where it gets it right is the part worth stopping practising. Either answer tells you something about your own work that no forecast can.


More: https://flyvolo.ai/llms.txt