Free English AI School · 20 lessons

Understand AI.
Teach it well.

Start with fluent answers and their limits. Finish with bounded agents, visible memory, tests, accountability and portable workflows. No account required.

CLASSROOM PRINCIPLEThe agent is the student.Evidence before confidence.People retain judgment.Public lessons · primary sources · reusable exercises
TTC-108practitioner

Teach one agent a bounded role

Teach one repeatable role with explicit inputs, outputs, sources, exclusions, escalation, and tests before adding tools or broader autonomy.

After TTC-102, TTC-105Learn →
TTC-109practitioner

Knowledge and provenance

Store each usable fact or rule with its origin, owner, date, scope, status, and relationship to the source so it can be challenged and retired.

After TTC-103, TTC-108Learn →
TTC-111practitioner

Visible memory and forgetting

Durable agent memory should be inspectable, attributable, editable, versioned, and removable—and it affects behavior only when a workflow brings it into context.

After TTC-109, TTC-110Learn →
TTC-112practitioner

Structured rules, YAML, and AGENTS.md

Use AGENTS.md as a readable instruction map and structured YAML for narrow machine-checkable rules; keep authority, scope, defaults, and tests explicit in both.

After TTC-105, TTC-111Learn →
TTC-113practitioner

Version history and rollback

Version every behavioral change with a focused diff, rationale, tests, and an exact recovery path to a known approved state.

After TTC-111, TTC-112Learn →
TTC-114practitioner

Creative collaboration

Use AI to widen and vary creative options, while a human sets intent, checks provenance, selects, edits, and accepts responsibility for the final work.

After TTC-102, TTC-103, TTC-105Learn →
TTC-115practitioner

Workplace task design

Redesign a workplace task as explicit inputs, transformations, checks, decisions, and handoffs before deciding which bounded steps AI should assist.

After TTC-102, TTC-103, TTC-105Learn →
Suggested paths

A route, not
a pile of pages.

Each preset expands its prerequisites. Or choose exactly what matters and generate an instruction pack for your own agent.

RECOMMENDED PATH

Safe start

Understand limits, write clearer briefs, verify claims and protect ordinary data.

Compose this path →
RECOMMENDED PATH

Teach one agent

Build a bounded, reviewable agent using provenance, examples, memory and tests.

Compose this path →
RECOMMENDED PATH

Responsible deployment

Design least-privilege workflows, evaluations, accountability and rollback.

Compose this path →
Living curriculum

Current because
changes are reviewed.

Scheduled source checks can detect changed primary documentation. They prepare evidence for editorial review; they never turn external text into authority or publish claims automatically.

See freshness and review status → · Suggest a correction →