Skip to main content
AI Education for Kids
MenuClose
Parent-guided video lesson

Local AI Agents: A Parent Demonstration: Adult Demonstration

An AI agent combines a model with instructions and tools that can take actions. Running a model locally does not automatically make every connected tool private or safe. This adult-led lesson uses a paper simulation to explore planning, permission, checking, and stopping before any software installation, file access, or real-world action is attempted.

By the AI Education for Kids Editorial Team · Learning notes materially reviewed: October 13, 2026

Age: Adults; advanced 13–14 with an adultLearning goal: Explain an agent's plan, permissions, actions, and checks using a paper simulation.Parent role: Adult demonstration only. Advanced teens participate alongside an adult; no software installation or real file access is required.

Watch together

Watch: 4:02 · Activity: ~20 minutes · Cost: no payment or AI account needed for the paper activity.

Open and play this video on YouTube

Viewing and accessibility note: A source-verified transcript and manually reviewed chapter timestamps are not published yet. The notes below are an editorial learning summary, not a word-for-word transcript. If captions are available in the player, review them with an adult and verify important claims against the listed sources.

Corrected lesson notes

Three ideas to carry into the activity

Idea 1

Plan

List the steps and resources the task needs.

Idea 2

Ask permission

Do not treat a proposed action as permission to execute it.

Idea 3

Check and stop

Inspect the outcome and stop when the task or permission boundary is unclear.

Corrected lesson notes

A local model can be combined with network services, packages, plugins, databases, and cloud tools. Each component has its own data flow. Review permissions and network access instead of assuming that local means completely private. The recording's description contains unfinished repository links; this lesson does not present them as working installation instructions.

Vocabulary for the conversation

Agent
A system that uses a model and tools to pursue a task.
Tool
A capability that reads information or performs an action.
Permission
Explicit authority to perform a particular action.
Local model
A model running on your own device.
Stop condition
A rule that ends the task or requests human help.

Parent discussion prompts

  • Which resources does the task actually need?
  • What action requires permission?
  • What would make us stop?
Hands-on extension

The paper permission gate

  1. Give the agent a task: summarize the fictional lesson.txt card.
  2. List a plan that reads only lesson.txt and writes a summary on a blank card.
  3. Have the parent approve that limited plan.
  4. Offer a tempting private.txt card. Reject it because it is outside the approved task.
  5. Compare the summary with lesson.txt and stop. Record the allowed action and the rejected action.

Child reflection question

Why should an agent need permission even when it runs on our laptop?

What to correct or update

Local execution does not establish 100% privacy, zero total cost, or safe autonomy. Hardware, downloads, dependencies, and connected tools matter. A tested setup guide is not supplied here.

Limitations and safety

Do not grant agents access to credentials, purchases, messages, personal files, or system controls during this activity.

Scope: This lesson supports education and family discussion. It is not medical, mental-health, safety, or product advice, and it does not certify any tool as suitable for every child.

Sources and lesson scope

Pause, predict, and discuss

Discuss these ideas when they come up or after watching. These are prompts, not verified video chapters.

  1. Which resources does the task actually need?
  2. What action requires permission?
  3. What would make us stop?

Discussion answer guide

Try an answer before opening the explanation.

Does local mean every tool stays offline?

No. Connected services or packages may send data over a network.

May the agent read private.txt?

No. That action was outside the approved plan.

When is the task complete?

After the approved output is checked against its source and the agent stops.

Printable learning record

Materials: Paper task cards and three fictional files: picture.txt, lesson.txt, and private.txt.

My prediction or first attempt:

My evidence and what I changed:

My explanation without the helper:

Parent answer and observation guide

A short summary of lesson.txt, a plan approved by the adult, and a log showing private.txt was not read. No actual files are accessed.

Look for an explanation, a recorded test, and a limit the child can name. This is a discussion aid, not an assessment.

Your worksheet stays on paper; this page does not save answers or progress.

Check your understanding

Three practice questions about these companion notes. Choose, check, then explain. Scores are not saved or sent anywhere.

1. Does “local” automatically mean private?
2. What is a sensible agent demonstration?
3. Who should manage the setup described here?

Discuss your choices, then open the answer guide.

Quiz answer guide
  1. No; apps, downloads, and tools may still connect outside. Check network access, telemetry, permissions, model licenses, and actual settings.
  2. Use a sandbox and require approval for actions. Limit permissions and data; an agent can make consequential errors.
  3. An adult with suitable technical experience. This is an adult technical demonstration, not a beginner child-installation tutorial.
For adults · About 45 seconds

Get the free AI Family Starter Pack

Ten printable pages: five paper activities, a four-week plan, a family safety agreement, and reflection sheets. Share a few fixed-choice observations to receive the PDF. No payment, email, child name, or account.

All video lessons remain public. Optional feedback is required only for the ebook. Negative feedback and “not tried yet” answers receive the same download.

Share parent feedback & get the ebook

We store your adult role, resource, choices, submission time, and download status for about 90 days, then removed by daily cleanup. Answers help improve resources and describe aggregate self-reported outcomes. The incentive can bias results; this is not a validated assessment. Quiz answers and scores are never submitted. Privacy and withdrawal choices.

Your adult role
How far have you tried this resource?
How useful was it?
Your confidence guiding AI learning before this resource
Your confidence now
One thing you observed

For “Not yet,” choose “Not tried yet,” “Not measured” for now, and “Not observed.” There is no need to invent an outcome.

Download immediately after saving; your access receipt stays only in this open page.

This form needs JavaScript to save safely. All videos, printable lesson worksheets, and activities remain public without feedback.

Continue the learning cycle

Use one related guide, record what the child tested, and return to the Watch & Learn library for the next concept.

All Watch & Learn lessonsCoding toolsFamily AI agreement
Return to parent resources