Give your agent tools — and let it act, not just talk.

A talking agent can plan; a connected one can do. This lesson gives your agent hands — search, files, email, spreadsheets, your apps — and chains them into a workflow that moves work forward, all while keeping you safely in control.

The mental model

An agent is only as capable as the tools it can reach. Tools are its hands.

A talking agent can plan and summarize but can't change anything in your world. Give it tools — search, your files, email, a calendar, a spreadsheet, an API — and it goes from advising you to acting for you. The skill is connecting the right tools, safely, and chaining steps into a real workflow.

The reframeStart read-only. The fastest way to trust an agent is to let it look before it touches. Give read access first; add the ability to write, send, or change only once it's proven on read-only.

Step 01 · Connect tools safely

Tools, roughly in order of safety: search & web → your files & docs → email & calendar → a spreadsheet/database → an API or app. Every connection is a trust decision. Make the safe call on each:

Connecting your inbox for triage

Which inbox / folder does it get?

Step 02 · Chain a real workflow

Real value comes from sequencing tools: gather → process → produce → place. Press run to watch the chain — it pauses before placing anything, for your OK.

1 · gather read source, pulled 14 records ✓

2 · process summarized + categorized each item ✓

3 · produce built a 14-row table ✓

4 · place ready to write to destination — waiting for your OK ⏸

It stopped before placing the result — exactly right. Reading and producing are safe; writing to the outside world waits for you. "If a step fails or returns nothing, stop and tell me rather than guessing."

Workflow promptRun this workflow: 1) Read [source] and pull [the data]. 2) For each item, [summarize / categorize / score]. 3) Produce [a table / draft / report]. 4) Put the result in [destination], but show it to me first. If a step fails or returns nothing, stop and tell me rather than guessing.

Step 03 · Patterns for reliable tool use

Name the tool for the job — "use search for current facts, use the file for our internal numbers."
Say what to do on failure — stop and report, don't improvise.
Ask before leaving the building — anything that sends, posts, pays, or deletes gets a confirmation.

The expensive mistake is granting send/write/delete access early. Keep a human in the loop for anything that leaves your control — emails sent, money moved, records deleted. Reading is safe; acting on the outside world is where you stay in the loop.

Your challenge: build a connected workflow

Connect one source the agent can read (folder, sheet, or inbox), read-only.
Define a gather → process → produce → place workflow.
Have it show the result before placing it anywhere.
Run it on real data and check each step held up.

✓

Lesson complete

You can pick tools in order of safety, connect them read-before-write with least access, chain a gather → process → produce → place workflow, and keep a human in the loop for actions that leave your control.

Up next

Lesson 3 · Reliable agents — guardrails, testing & running unattended

Continue to Lesson 3 →

Open the Playground Back to Build an AI Agent