---
title: "A product-data loop for your agent"
url: https://www.datawebot.com/blog/agentic-workflows-inventory-pricing
description: "Answer a product question from a bounded extraction. The saved example reports availability, not inventory quantity. Reordering, schedules and price changes require your own systems and authorization."
updated: 2026-09-14
author: datawebot team
---

Extraction guide

# A product-data loop for your agent

Answer a product question from a bounded extraction.

Updated September 14, 2026 · datawebot team

[← All guides](https://www.datawebot.com/blog)Field map ↓Try the workflow ↗

01 / INPUT**Product URL + 2-credit ceiling**

02 / YOUR WORKFLOW**Estimate → submit → wait → retrieve**

03 / OUTPUT**Variants + prices + source evidence**

## Keep the right fields.

Workflow field map

| Field / step | Input | Rule |
| --- | --- | --- |
| Task identity | run.id + idempotency key | Save both before yielding. |
| Result pages | products + next_cursor | Continue until the cursor is null. |
| Answer | variants + provenance | Cite the observation; preserve unknown values. |

Synthetic catalog data · not a retrieval result

01 / Example record Fictional product

### Cotton Crewneck T-Shirt

`No source URL`

Products

1

Variants

4

Record origin

Synthetic

Page visits

Not applicable

[Field definitions](https://www.datawebot.com/docs/data)

02 / Inspect the example

Example answer · calculated from fictional values

### Which variants does this example mark available?

Small / Navy, Medium / Navy are marked available in this synthetic example. 1 example value is unknown.

**USD 32.00****USD 34.00**fictional example prices

No live source, price observation or inventory state is represented.

Illustrative schema · synthetic records

[Example CSV](https://www.datawebot.com/samples/catalogue-example.csv) · [Example JSON](https://www.datawebot.com/samples/catalogue-example.json) · [Use with an agent](https://www.datawebot.com/docs/agents)

## Before you use the output

The saved example reports availability, not inventory quantity. Reordering, schedules and price changes require your own systems and authorization.

## Check one record first.

Start with the smallest useful scope. Compare the returned record with its source, confirm variant identity and inspect missing fields before applying the mapping to a larger dataset.

Keep extraction warnings and the retrieval timestamp with downstream output. When a required field is missing, leave it unresolved or return to the source; do not fill it from an assumption.

Working references [Product and variant schema ↗](https://www.datawebot.com/docs/data) · [Supported endpoints ↗](https://www.datawebot.com/scraper) · [Incomplete or unavailable results ↗](https://www.datawebot.com/docs/troubleshooting)

01 **Copy the setup prompt**Paste it into your coding agent[02 **Approve the email**Free sign-in, no key in chat](https://mcp.datawebot.com/setup.md) · [03 **Ask for products**Search shops, compare sellers](https://www.datawebot.com/docs/agents)

Agent setup prompt

Setup prompt · contains no credentials

```
set up https://mcp.datawebot.com/setup.md

What this does: your coding agent reads the setup page, asks for your email, waits while you approve the sign-in email from datawebot, saves its key to a private file and connects to the MCP server at https://mcp.datawebot.com/mcp. You never paste a key into the chat.

Then ask, for example: "Find Sony WH-1000XM5 prices in the US and list the sellers with links."
The agent uses search_products to find products across online shops, then get_product_offers for each seller's price and a direct link to the shop.
Results are best-effort snapshots with a retrieval time. They are not verified or live prices.
```

[Continue this workflow](https://www.datawebot.com/docs/agents)