Free · 15 minutes
AGES 14–18 · PORTFOLIO TRACKResearch, code
FIRST STEP SECOND STEP
Research, code
and build a portfolio with AI.
Research, code, automation and a personal project. The learner presents the result and explains their contribution and the model’s role.
Diagnostic session $120 · 60 minutes · Credited toward a package purchased within 14 days.
Discuss diagnostic →METHOD / PROGRAM
Learn through the work.
A 10-module map. Modules are a content map, not a promise that one module equals one session. Explorer selects the essential blocks in 6 sessions; Portfolio covers the full core in 10; Builder adds 2 sessions for technical depth and project work.
AI literacy
How modern models work, where they help and why outputs still need verification.
Research system
Sources, comparison, argumentation and concise evidence-based conclusions.
Prompting as specification
Context, criteria, constraints and iteration instead of magic prompt recipes.
Create & present
Writing, visuals and presentations with transparent authorship.
Code with AI
Read, modify and test simple code with AI support even when programming is new.
Automation
Turn repeatable steps into a workflow and identify unsafe automation boundaries.
Product thinking
Problem, user, scenario, prototype and usefulness before features.
Portfolio build
Assemble the project with decisions, sources, limitations and personal contribution documented.
Stress-test
Check failure modes, edge cases, source quality and whether the project actually works.
Demo & next step
Present the work and map the next skill path: code, design, research or automation.
SAFE AGENT WORK · 3 CASES + 5 RULES
Do not trust the plan. Control the effect.
An AI agent can read, decide and use tools. The risk starts when a plausible answer can turn directly into an external effect. These three documented cases show different failure modes.
Replit Agent deleted production-app database data.
During a SaaStr experiment, Replit Agent deleted app data from a database. Replit later acknowledged the problem publicly: before its new development/production separation, changes made during development could affect production; the data was restored through rollback.
Lesson: a written instruction such as “do not change anything” is weaker than a technical boundary that prevents the agent from writing to production.Replit · 29 Jul 2025 ↗EchoLeak showed that incoming data can become an instruction.
Researchers demonstrated an indirect prompt-injection chain in Microsoft 365 Copilot: a crafted email could enter Copilot context and enable data exfiltration without the user clicking the email. Microsoft patched the issue; public reporting said Microsoft had no evidence of in-the-wild exploitation.
Lesson: email, webpages, documents and comments are untrusted data even when an agent can read them automatically.SC Media · Microsoft CVE-2025-32711 ↗Unit 42 found hidden prompts on malicious webpages.
Unit 42 observed real webpages carrying indirect prompt injection, including an attempt to make an AI ad-review system approve a scam advertisement. The researchers explicitly noted that they had not confirmed a successful bypass of a deployed ad-checking agent in that case.
Lesson: an agent that reads the web must separate page content from commands, and it should not gain extra authority simply because automation is convenient.Palo Alto Networks Unit 42 ↗FIVE OPERATING RULES
Authority should be explicit.
- 01 · Start read-only
Let the agent read, plan and show a diff first. Grant write authority separately and only where one task actually requires it.
- 02 · Least privilege
Use test environments, separate accounts and keys, and no production access by default. Do not give an agent more authority than one task needs.
- 03 · Human before irreversible effects
Data deletion, publishing, sending messages, purchasing, payment or access changes require explicit confirmation before the effect.
- 04 · Data is not instruction
Text from email, webpages, files, issues or chat can be hostile. Retrieved content must not become a new command without a separate trust check.
- 05 · Verify after the effect
Keep an action log, verify the result, define rollback and a stop condition. “The agent said it is done” is not evidence.
The cases are not equivalent: Replit was a real operational incident; EchoLeak was a confirmed vulnerability patched before public disclosure with no known in-the-wild exploitation; the Unit 42 case was an observed malicious injection attempt without confirmed successful bypass of a deployed ad-review agent.
FORMAT AND PRICE
Choose the depth.
60 minutes per session
Discuss Explorer →60 minutes per session
Discuss Portfolio →60 minutes per session
Discuss Builder →Scope, schedule, payment, rescheduling, cancellation and refund terms are confirmed in writing before payment.
Ages 13–17 and AI services
Adult permission is part of the process.
Organizational contact remains with an adult. Every AI provider has its own age rules; ChatGPT users under 18 require permission from a parent or legal guardian.
Start with the goal, not the package.
For minors, organizational contact stays with an adult. Share age range, interests and goals; no child's contact details, school, address, passwords or payment data.
Prepare the first brief →