# 10. Let an agent choose a small tool.

Watch a tool-using agent calculate a fictional supplies total.

## Facilitator preflight

Bring laptops, internet, a projector and these local course files. Check tool access before the meetup. Keep samples free of personal information.

Quick win: Inspect a prepared calculator tool call and check its result.

Prerequisites: Modules 07–08. Prepared n8n and a supported tool-calling chat model.

### Tools and cost notes

- **AI Agent, supported Chat Model and Calculator sub-node.**: Prepared before the meetup.. The chosen hosted model may need API billing. A chat subscription is not an API credential.

## Run of show

| Slide | Minutes | Activity |
|---|---:|---|
| 1 | 3 | Let an agent choose a small tool. |
| 2 | 3 | Before you start. |
| 3 | 5 | Your first small win. |
| 4 | 3 | What happens between input and output? |
| 5 | 3 | Step 01. Confirm a supported model. |
| 6 | 3 | Step 02. Create the input. |
| 7 | 3 | Step 03. Add AI Agent. |
| 8 | 3 | Step 04. Give it one tool. |
| 9 | 3 | Step 05. Inspect execution. |
| 10 | 3 | Step 06. Test a boundary. |
| 11 | 4 | Make the working version. |
| 12 | 4 | Ask for a review. Then check it. |
| 13 | 6 | Prove your result works. |
| 14 | 4 | When it does not work yet. |
| 15 | 5 | Choose your next challenge. |
| 16 | 3 | Keep the result. Keep the evidence. |
| 17 | 2 | Sources you can check. |

Total: 60 minutes.

## 1. Let an agent choose a small tool.

Outcome: Watch a tool-using agent calculate a fictional supplies total. This is a 60-minute in-person laptop session after preflight. No setup-duration guarantee. Core first, extensions second.

## 2. Before you start.

The chosen hosted model may need API billing. A chat subscription is not an API credential. The facilitator verifies accounts, installed tools and model/host connections before the session. Pair up if setup is incomplete. Do not create accounts or incur costs without understanding the provider terms.

## 3. Your first small win.

Quick win: Inspect a prepared calculator tool call and check its result. Aim for a visible result in the first 15 minutes after preflight. Explain that generated code/output is untested until the learner checks it. If tools are unavailable, inspect the prepared example with a partner.

Copyable prompt: [Open prompt](index.html#10-quick-win)

```text
Work out the fictional supplies total: 12 notebooks at 3 units each, plus 8 pens at 2 units each. Show the arithmetic and state the total. This is a workshop calculation, not a real purchase.
```

## 4. What happens between input and output?

Ask a learner to explain each stage in their own words. This is a teaching model, not a promise that all tools behave identically.

## 5. Step 01. Confirm a supported model.

Perform these numbered actions on the laptop. Pause after the step and inspect the result. Keep credentials private and use the prepared workshop instance.

Source: [n8n: AI Agent](https://docs.n8n.io/integrations/builtin/cluster-nodes/root-nodes/n8n-nodes-langchain.agent/)

Source: [n8n: Supported tool-calling models](https://docs.n8n.io/integrations/builtin/cluster-nodes/root-nodes/n8n-nodes-langchain.agent/tools-agent/)

## 6. Step 02. Create the input.

Perform these numbered actions on the laptop. Pause after the step and inspect the result. Keep credentials private and use the prepared workshop instance.

Source: [n8n: AI Agent](https://docs.n8n.io/integrations/builtin/cluster-nodes/root-nodes/n8n-nodes-langchain.agent/)

Source: [n8n: Supported tool-calling models](https://docs.n8n.io/integrations/builtin/cluster-nodes/root-nodes/n8n-nodes-langchain.agent/tools-agent/)

## 7. Step 03. Add AI Agent.

Perform these numbered actions on the laptop. Pause after the step and inspect the result. Keep credentials private and use the prepared workshop instance.

Source: [n8n: AI Agent](https://docs.n8n.io/integrations/builtin/cluster-nodes/root-nodes/n8n-nodes-langchain.agent/)

Source: [n8n: Supported tool-calling models](https://docs.n8n.io/integrations/builtin/cluster-nodes/root-nodes/n8n-nodes-langchain.agent/tools-agent/)

## 8. Step 04. Give it one tool.

Perform these numbered actions on the laptop. Pause after the step and inspect the result. Keep credentials private and use the prepared workshop instance.

Source: [n8n: AI Agent](https://docs.n8n.io/integrations/builtin/cluster-nodes/root-nodes/n8n-nodes-langchain.agent/)

Source: [n8n: Supported tool-calling models](https://docs.n8n.io/integrations/builtin/cluster-nodes/root-nodes/n8n-nodes-langchain.agent/tools-agent/)

## 9. Step 05. Inspect execution.

Perform these numbered actions on the laptop. Pause after the step and inspect the result. Keep credentials private and use the prepared workshop instance.

Source: [n8n: AI Agent](https://docs.n8n.io/integrations/builtin/cluster-nodes/root-nodes/n8n-nodes-langchain.agent/)

Source: [n8n: Supported tool-calling models](https://docs.n8n.io/integrations/builtin/cluster-nodes/root-nodes/n8n-nodes-langchain.agent/tools-agent/)

## 10. Step 06. Test a boundary.

Perform these numbered actions on the laptop. Pause after the step and inspect the result. Keep credentials private and use the prepared workshop instance.

Source: [n8n: AI Agent](https://docs.n8n.io/integrations/builtin/cluster-nodes/root-nodes/n8n-nodes-langchain.agent/)

Source: [n8n: Supported tool-calling models](https://docs.n8n.io/integrations/builtin/cluster-nodes/root-nodes/n8n-nodes-langchain.agent/tools-agent/)

## 11. Make the working version.

Use fictional practice inputs. Ask learners to show their work, not just the final answer.

Copyable prompt: [Open prompt](index.html#10-build)

```text
You are a workshop supplies assistant. Use Calculator for arithmetic when appropriate. Show the expression and result. Use only supplied quantities. No purchasing, messaging or booking tools are available. Ask for missing quantities; never claim actions were completed.
```

## 12. Ask for a review. Then check it.

Use fictional practice inputs. Ask learners to show their work, not just the final answer.

Copyable prompt: [Open prompt](index.html#10-review)

```text
Inspect this recorded agent output and tool trace. Did a calculator call occur? Does the result match 12*3+8*2=52? Flag unsupported claims. Do not assume execution from answer text alone. Trace: [paste redacted trace].
```

## 13. Prove your result works.

These are manual acceptance tests for the learner to perform. No test is claimed to have run merely because it appears here. Ask pairs to demonstrate one pass and one corrected failure.

## 14. When it does not work yet.

Choose the observed symptom. Change one thing and rerun the smallest test. Avoid restarting the whole project or adding tools before diagnosing the current step.

## 15. Choose your next challenge.

Experienced learners use the extensions while beginners complete the same core outcome. An extension is optional, not a prerequisite for participating.

## 16. Keep the result. Keep the evidence.

Save the working version before leaving. Add a short note: what worked, what needed correction and what you would try next. The next module builds on the saved output.

## 17. Sources you can check.

Primary sources checked during course creation on 2026-10-08. Provider interfaces and availability can change. The examples, prompts and activities are original community teaching designs. Source links explain capabilities; they do not prove these fictional exercises were executed.

Source: [n8n: AI Agent](https://docs.n8n.io/integrations/builtin/cluster-nodes/root-nodes/n8n-nodes-langchain.agent/)

Source: [n8n: Supported tool-calling models](https://docs.n8n.io/integrations/builtin/cluster-nodes/root-nodes/n8n-nodes-langchain.agent/tools-agent/)

Source: [n8n: Calculator tool](https://docs.n8n.io/integrations/builtin/cluster-nodes/sub-nodes/n8n-nodes-langchain.toolcalculator/)

## Extensions

- Add one bounded read-only lookup tool.
- Compare agent tool choice with a fixed workflow call.

## Delivery notes

Arrow keys, Space, Home and End navigate slides. N opens notes. Read all slides creates a scrolling lesson. Every prompt has a real Copy prompt button with an honest manual fallback if the browser blocks clipboard access. Keep the whole curriculum folder together: PPTX prompt links open the companion index.html at the same prompt anchor. PowerPoint does not copy directly. For sharing online, rebuild with --companion-base-url set to the published curriculum URL.

Motion illustrates input, agent, tool, human review and output. Pause flow stops it; system reduced-motion is respected. PDF contains a static diagram. PPTX uses an animated GIF where available; playback varies by viewer.

Original teaching content, synthesized from learning objectives. Public source decks remain separate in library/. No one-to-one rebranding or permission to republish is implied.
