Create a Make agent for stock and price lookups
A Make agent can answer item stock and cost questions from a data store without changing any records.
- What they did
- The author built a basic inventory helper in Make on the Free plan. They connected an AI agent to a single tool scenario that queried a Make Data store with three made-up products, then returned the matching item’s stock level and price. The agent was limited to reading data only, so it could not hold items, place an order, or update inventory.
- How it went
- It handled six test questions successfully, with each answer using about 1.08 to 1.30 credits, or roughly 1.1 to 1.3 credits per question. The setup also exposed a few operational hiccups: the tool scenario needed to remain enabled, a leftover placeholder module prevented the trigger from firing, and plural product names did not match.
- Tips
- Make sure the lookup scenario stays switched on, since the agent depends on it. Test both singular and plural product wording, because matching was inconsistent.
Try it yourself with Make
Help me build a Make agent that answers read-only questions such as “Does [product name] have stock, and what does it cost?” using my Make Data store named [data store name]. Set up a helper scenario that finds the product by name and sends back only its stock count and price. Tell the agent to read records only, and to stop and ask for my approval before any action that would change, delete, reserve, order, or submit anything. When it’s ready, I want to try it with three sample products and see an estimate of credit use per answer.
Fill in the [brackets]. Agents can make mistakes, so review anything before it is sent, paid or deleted.
Get 3 agent uses like this every morning
With the day's top AI news. Free, and one click to unsubscribe.
Related agent uses
Use Make to refresh material costs and draft POs
A Make.com workflow checked payables each night and kept estimating formulas updated with the latest material prices.
Audit onboarding before you automate it
An agency reviewed a client’s onboarding flow, then built a Make scenario and Slack channel instead of the AI agent they first planned.
Automate daily ClickUp status emails for stakeholders
They used Make to compile unfinished ClickUp tasks into daily email updates for stakeholders who do not use ClickUp.
Sort unread email and hold replies for approval
They set up an email workflow that reviews new unread messages, organizes them, and waits for approval before any reply goes out.
Route Slack commands to email, calendar, and tasks
Set up a Slack-triggered agent to check Gmail, review Google Calendar, and add tasks in Notion with approval before anything is sent or deleted.
Auto-file supplier invoices from Drive into monday.com
Make can watch a Drive location for invoice PDFs, extract key fields, and add them to a monday.com board.