FREE · INTERACTIVE · NO SIGNUP

Run your first
Agentic OS.

See a task pass through planning, drafting, verification, rules, and human approval. This working browser sandbox shows the control flow with realistic failure handling—without connecting to a model or sending your notes anywhere.

Runs in your browserZero API chargesReview before export

Use invented notes only. This demonstration is not Claude, not a production agent, and not a security sandbox. Source excerpts can look plausible even when facts are wrong; check them yourself.

Illustrative editorial photograph of a notebook, laptop and clock on a work desk
Illustrative image, not a screenshot of an AI action.
STEP 01 · INPUT AND RULES

Choose a practice task

Each line represents one untrusted source note. Use the good example first, then try the hostile example and see which gate stops the result.

Rulebook: read-only input, at most six notes, exact-quote checks, no external actions, no auto-approval.

STEP 02 · CONTROL-PLANE TRACE

Inspect all six gates

No run yet.

    Approval here is a local practice decision by the learner. It never sends or publishes a message.

    STEP 03 · RESULT

    Proposed internal draft

    The local draft appears after a practice run.

    STEP 04 · EVIDENCE

    Trace claims to sources

    Original quotations and verifier checks appear here.

    NEXT STEP · CONNECT A REAL MODEL, SAFELY

    Ready for a real Claude-generated draft?

    Download the optional Python runner and follow the nine-step setup guide. It uses your private API key on your own machine, requires explicit paid-call confirmation, and keeps all generated output draft-only until a human reviews it. The website never collects your API key.

    python3 agentic_os_claude.py --state ./live-state plan --task demo-safe.json
    python3 agentic_os_claude.py --state ./live-state run --task demo-safe.json --confirm-paid-api-use
    python3 agentic_os_claude.py --state ./live-state report

    Supervised pilot only: no authenticated external connectors, automated posting, remote execution or production autonomy are provided by this teaching kit.