07Operations and finance · Data collectionexample setup · demo data

Regular data from permitted sources, in one table.

An example setup for an operations team tracking supplier prices, open data or listings on its own sites: the sources and the pace are yours, the table is fresh every morning.

It runs on your own server: work files and records are stored on your infrastructure; content processed by AI goes to the model provider you choose, and data sent to external tools goes to the connections you set up.

demo data
01Workflowfrom the chat or the editor

Supplier price tracking

A setup that needs no AI: an HTTP request, a transform and schema validation. If you like, you add an agent step that reads the pages.

demo data

Last run · 07:00 · 214 products · 9 changed

02Setup and flowData collection

Setup and flow

An operations team that tracks supplier prices, open data sets or listings on its own sites.

Setup

Network
An allow-list: only addresses you are allowed to collect from. Requests leave from your worker; local network and metadata addresses are always blocked.
Two ways, your pace
The agent reads the pages and turns them into a table, or a workflow without AI does the same with an HTTP request, a loop and schema validation. Concurrent requests, waits and runs per hour are values you set.

What a day looks like

  1. 01

    Every morning at 07:00 the automation fetches the product pages of three allow-listed suppliers in turn, with at most two requests at a time.

  2. 02

    The agent, or a transform step, pulls product name, price and stock into a table and compares it with the previous run’s table.

  3. 03

    Products whose price changed arrive by email; the current prices.csv opens as a table in the Outputs screen.

What changes

Price lists copied by hand update themselves every morning, and you hear about it when something changes.

How it connects

You add the sources you want to collect from to the allow-list; where there is an official API, you connect to it with the HTTP step and set the fields to fit your own setup. You set the request rate and frequency to suit each source’s terms.

We don’t impose a ready-made flow; design your own, either with AI (describe it in the chat) or yourself (in the workflow editor).

Good to know

  • You work with permitted sources such as your own sites, open data, official APIs and contracted suppliers, in line with their terms of use and data protection law.
  • Every network decision is logged; the audit log shows which address was reached and when.
demo dataWorkflow editor: nodes on the canvas, with the selected step’s settings on the right.
A screen from the console · The real console: the workflow editor, with steps, conditions and loops on one canvas.
03Other use cases

Another team’s recurring work

All use cases and the connection process

Let’s fit this setup to your own work.

This example runs on the same infrastructure as all the others: Remyral on your own server, and we build your flow together in the pilot. Just describe the work you want to simplify and the tools you use in your application.