ChatGPT

How to Use ChatGPT Work’s Data Agent for Marketing

Evan WeberBy Evan WeberPublished Updated 3 min read
Analyst pointing to a printed line chart beside a spreadsheet

Start with the decision you need to make, then ask the Data agent for the evidence. 'Build a dashboard' can produce a lot of attractive charts. 'Did fewer orders or smaller baskets cause last week's revenue decline?' gives the analysis a job.

OpenAI describes the Data agent as a way to investigate approved company data and create interactive views. Its usefulness depends on which sources your workspace can actually access and whether the figures mean what your team thinks they mean.

Work through one question

In this fictional example, a store recorded 100 orders at an $80 average order value in week one: $8,000. Week two had 90 orders averaging $70: $6,300. Revenue fell $1,700.

Holding the old basket value constant, ten fewer orders account for $800 of the change. The $10 lower basket value across the remaining 90 orders accounts for another $900. The two pieces reconcile to $1,700. That tells the team to investigate both order volume and basket mix.

It does not show why either changed. A promotion, stock shortage, refund treatment or different customer mix could matter. The next query should test those possibilities rather than announce that the advertising failed.

Give the agent a usable brief

Try: 'Compare the two complete weeks in the approved order data. Define orders and revenue, exclude or show cancellations consistently, split revenue change into order count and average order value, and show the supporting query or source. List explanations separately as hypotheses.'

Specify time zone, currency, date field and whether revenue includes shipping, tax and refunds. Use the same definitions as the finance or ecommerce report you will compare against. A disagreement over gross and net revenue is a definition problem before it is an AI problem.

Check the connection and the numbers

OpenAI's Data agent announcement explains the product and supported data workflows. Verify the actual plugin, source permissions and business definitions in your workspace. A connector appearing in an announcement doesn't mean your account can query it.

Reconcile the two revenue totals and order counts to the source system. Then inspect a known segment and one excluded case, such as a cancelled order. If the data isn't fresh or a source is missing, show that limit beside the conclusion.

Make the dashboard earn its space

For this question, begin with revenue, orders and average order value for the two periods. Add a category or device split only when it helps investigate the change. Keep dates and definitions visible so the next reader can challenge the comparison.

A useful meeting note would say: 'Both fewer orders and smaller baskets contributed. Next check whether the basket decline is concentrated in the promoted category.' That gives someone a specific follow-up. 'Optimize performance' doesn't.

Use the finding before expanding the setup

Have the business owner review the evidence before changing spend or the live store. Save the brief, reconciled totals and unresolved questions with the dashboard. Repeat the analysis on another period to see whether it remains useful.

Our AI work review guide covers the final check. Bring one question with a real decision attached, and keep the first dashboard small enough that someone can explain every chart.

Once the figures reconcile, use the worked marketing reporting example to see how an analysis becomes a decision note.

Key takeaways

  • Define the decision and reconcile the headline totals.
  • Separate the size of a change from its possible cause.
  • Add charts only when they answer the next useful question.

Frequently asked questions

Can we trust a plausible dashboard?

Reconcile its totals, definitions, dates and exclusions to trusted sources before relying on it.

Does a revenue decline prove the ads failed?

No. Investigate orders, basket value, customer mix, stock and other relevant factors before assigning a cause.

Evan Weber
Evan Weber
AI Productivity Trainer & Digital Marketing Consultant

Evan is a 25-year digital marketing veteran, founder of Experience Advertising, and a daily Claude Cowork and Codex user who trains business teams to use agentic AI fluently in their real workflows.

More about Evan

Practice with ChatGPT Work

Bring a reporting question and an approved export. We can check the inputs, run the analysis and reconcile the result against the original data.

Explore ChatGPT Work training

Keep reading

AI Workflow Training

How to Turn Meeting Notes Into Action Items With AI

Give the AI a place to put uncertainty. Then check each owner, date and task against the meeting notes before it lands in your team’s tracker.

AI Workflow Training

How to Document an AI Workflow for Team Handoff

Turn a useful AI task into a repeatable team process with a clear brief, sample inputs, review checks and a real handoff test.

Team AI Workflows

How to Review AI-Generated Work Before Sharing It

A repeatable review process for checking AI research, numbers, documents and code before colleagues rely on the finished work.

AI Tool Comparison

Claude Cowork vs. ChatGPT Work: Which Should You Use?

Compare Claude Cowork and ChatGPT Work on a completed assignment, setup effort, corrections and approved access instead of a feature checklist.

Team AI Training

How to Build an AI Training Plan for Your Team

Choose one useful task, test it with a completed example and teach the team to review and repeat the work.

AI Agents

How to Build a Business Workflow with OpenAI’s Agents API

Use a completed affiliate-research example to scope an Agents API pilot, define failure handling and measure the cost of an accepted result.

ChatGPT

GPT-6 Astra for Business: When to Use It

See a completed campaign-brief example and a practical way to decide when GPT-6 Astra earns its additional cost or usage.

ChatGPT

What Is ChatGPT Work? A Beginner’s Guide

Understand ChatGPT Work through a completed meeting-brief example, with a clear distinction between Work, Chat, Codex and available access.

Claude Cowork

What Is Claude Cowork? A Beginner’s Guide

Learn Claude Cowork through a completed document-comparison example, current access requirements and the checks that make the result useful.

Codex

What Is the Codex App? A Beginner’s Guide

Understand the Codex app through a worked calculator bug, including repository context, tests, local or cloud execution and release verification.

Comparison

Claude Cowork vs. Codex: Which Tool Should You Use?

Use two completed assignment briefs to choose between Cowork and Codex without outdated local-versus-cloud assumptions.

Productivity

How to Measure AI Time Savings at Work

Calculate AI time savings with a completed example that includes preparation, review, corrections and setup cost instead of assumed percentages.

Career

Can AI Do My Job? How to Evaluate Your Tasks

Use a practical account-manager example to assess AI assistance without promises about job security, replacement or guaranteed productivity.

AI Search

AEO vs. GEO: What They Mean for AI Search

A practical guide to AI search visibility that starts with crawlable pages, useful answers and measurement, without citation guarantees or special-file myths.

ChatGPT

How to Roll Out ChatGPT Work for Teams

Use a completed team-rollout example to plan access, practice, review and a repeatable handoff without promising instant adoption.

ChatGPT

How to Use ChatGPT Work as a Solo Professional

Build a practical solo workflow from a completed proposal brief, with review checks and a realistic way to judge the time saved.