How it works
The sandbox is a full page. On the right is a chat that helps you build and adjust the agent. On the left is everything about the agent, laid out as tabs:- Test: pick a handful of real products and run the agent on them to see live results.
- Prompt: the agent’s prompt instructions.
- Review Steps: the quality checks that hold back weak enrichments. Review Steps is an add-on module that is not enabled by default. See Review Steps.
- Options: for classification agents, the values the agent can choose from.
- Languages, Dependencies, and Advanced Settings: the rest of the agent’s configuration.
- Changes: the agent’s history. Unsaved changes lists the changes made in this session, and Saved versions lists every version of the agent that has been saved, newest first.
Why you would use this
Catch problems before they hit your catalog
Build the agent in chat, not in a prompt editor
Step back through versions
Use real products, not synthetic tests

The Agent Sandbox: the chat that builds the agent alongside the configuration tabs and live test results
Step-by-step guide
Open the sandbox
Start the agent
- Describe your intent and let the chatbot draft the agent for you. Optionally pin the agent type first.
- Use a template to start from a ready-made agent in the template library. Search it, filter by type, and click Use template; the sandbox opens with the template’s configuration staged so you can test it right away.
- Copy from existing to start a new agent from the settings of one you already have.
- Manual input to enter the name, type, and prompt yourself.
Review the configuration tabs
Pick products and run a test

Review the results
- Read the AI Reasoning to see how the agent arrived at the value.
- Click View details to open a drawer with the compiled Prompt the model received, the Source Data it used as context, and the Result in full.
- Open View live agent thinking on a card to watch the agent reason as it works, useful for longer-running External Data and Media agents.
- Open Checks to see how the agent’s review steps judged the value, if it has any.
Refine through chat
Step through versions in the Changes tab
Create or save the agent
Advanced configuration
Referencing a specific product in chat
Referencing a specific product in chat
@ mentions. Typing @ opens a list of the products in your current test run. Click one to insert it as a pill into your message. When the chat rewrites the prompt, it uses that product’s generated output, reasoning, and images as grounded feedback, not just the text you typed.Use this when one product is off but the rest look fine. Instead of rewording the entire prompt, point the chat at the outlier and describe what is wrong with it specifically.Inspecting what the model actually saw
Inspecting what the model actually saw
- Prompt: the compiled prompt sent to the model for that product, with Data Source references and product fields already filled in. If the output is surprising, check the compiled prompt first to see whether the right context made it in.
- Source Data: the product attributes the agent used as context, including the product name, images, and any referenced fields.
- Result: the generated value on its own, rendered the way the product table will render it.
Comparing versions in the Changes tab
Comparing versions in the Changes tab
Switching attribute type mid-build
Switching attribute type mid-build
What gets saved and what doesn't
What gets saved and what doesn't
- Saved with the agent: the prompt as it stands when you create or save, plus the configuration you set on the tabs. Each save adds a version under Saved versions in the Changes tab.
- Not saved: the list of test products, individual test results, and the agent chat transcript.
Frequently asked questions
Why is my sandbox output weaker than what I expected from enrichment?
Why is my sandbox output weaker than what I expected from enrichment?
- The agent has dependencies that haven’t been filled in on the test products. The sandbox doesn’t run upstream agents first. If your agent reads other attribute values, pick test products that already have those values.
- The selected products don’t represent your catalog well. Choose Select 5 random products again, or hand-pick a mix of product types and price points. Outputs can vary a lot between, say, a simple t-shirt and a technical running shoe.
How do I go back to an earlier version of the prompt?
How do I go back to an earlier version of the prompt?
Does the agent chat call the model every time I hit send?
Does the agent chat call the model every time I hit send?
Can I stop a test run that's taking too long?
Can I stop a test run that's taking too long?
Do my review steps run in the sandbox?
Do my review steps run in the sandbox?
What happens to my chat when I leave?
What happens to my chat when I leave?
