> ## Documentation Index > Fetch the complete documentation index at: https://docs.tuturuuu.com/llms.txt > Use this file to discover all available pages before exploring further. # Colab team prompt workshops > Run invite-only AI learning workshops on Cloudflare with isolated mock tools. Colab at `colab.tuturuuu.com` is a standalone React application served by a Cloudflare Worker. A SQLite Durable Object owns each room. The reusable `@tuturuuu/multiplayer` package defines room policy and safe member-specific projections; the Worker owns authentication, inference, storage and WebSockets. ## Running a workshop 1. Sign in with a confirmed Tuturuuu account. Only an exact `@tuturuuu.com` account can create a room. Choose its start/end time, participant limit and number of teams. Limits are 5 minutes–8 hours, 2–100 participants including admins, and 1–12 teams. 2. In the facilitator desk, allow account emails and share the room URL. This adds an account invitation; it does not send email. Alternatively, generate a random temporary password and share it separately. The password appears once; only its SHA-256 digest is stored. Rotation removes password-only guests. 3. Each team writes and saves a system prompt. Version checks reject concurrent overwrites. Drafts remain local until saved. A teammate can explicitly load the latest saved version after a conflict. 4. Generate a single skill or let the model split the instructions into up to four focused skills. Each download contains YAML frontmatter and readable Markdown instructions. Place it in `/SKILL.md` in a compatible agent environment after reviewing it. 5. Test the generated skills against the room scenario. The journal records the prompt snapshot, scenario, actual sandbox tool inputs/results, final answer and AI coaching. Coaching is advisory, not proof of agent correctness. 6. Turn on showcase to let teams inspect one another's work. Otherwise only the team's own work and teammates are sent to that team. Admins can inspect all teams. Only staff admins can promote other signed-in accounts to room admin. 7. Close to read-only, or set private mode to restrict access to admins. At the scheduled end the room becomes read-only. Every mutation checks the clock; the Durable Object alarm also updates connected clients. Private mode and revoked memberships close affected sockets. ## Sandbox boundary The eight adapters cover Google Drive, Notion, Zalo, Messenger, Microsoft Teams, Google Calendar, Jira and Trello. They simulate searchable records and create/update actions. They are educational mockups, not replicas of the full products. No third-party app credentials, network fetch tools or real messaging connectors are available to the agent. Each team's writes affect only its own records. Admins can reset those records to the same seeded Project Lotus dataset. Workers AI generates skills, scenarios, agent decisions and feedback using `@cf/meta/llama-3.3-70b-instruct-fp8-fast`. Agent execution uses a bounded JSON tool protocol with an allowlist and runtime validation. Each run allows six decisions and a coaching call. A room allows 200 AI operations and one concurrent AI job. If room state changes while inference is running, the stale result is discarded. The system prompt, scenario, mock records and traces are sent to Workers AI; participants should use workshop examples rather than confidential real data. ## Authentication and deployment The Worker redirects to central Tuturuuu login with a nonce-bound return URL. `POST /api/v1/auth/colab/verify` consumes a Colab-targeted one-time handoff and looks up the confirmed, non-banned user in Supabase Auth. It deliberately ignores `cross_app_tokens.session_data.email`, which is caller-controlled. Colab signs its own short-lived, HttpOnly, Secure, SameSite cookie using `COLAB_SESSION_SECRET`. The Worker never receives a Supabase service key. Ship the Colab domain registration in `packages/utils/src/internal-domains.ts` and the verifier on the live web app before accepting production account logins. The new verifier is tracked as Rust migration backlog; the Rust backend does not serve production traffic. No Supabase migration or production database push is required for Colab. The Cloudflare configuration is `apps/colab/wrangler.jsonc`. It creates `tuturuuu-colab`, binds the room Durable Object and Workers AI, serves static assets, and attaches the `colab.tuturuuu.com` custom domain. Use the authorized Tuturuuu Cloudflare account. Provision a cryptographically random `COLAB_SESSION_SECRET` through Wrangler's secret input; never commit it. ```sh theme={null} cd apps/colab bun run build bun run deploy:dry-run bunx wrangler secret put COLAB_SESSION_SECRET bun run deploy ``` Rotate the session secret only intentionally: it signs out all Colab sessions. Room state persists in Durable Object SQLite storage across Worker deployments. Keep the `v1` migration and class name stable. Read-only rooms are retained; there is no automatic data deletion policy in this release. ## Verification ```sh theme={null} cd packages/multiplayer bun run test cd ../../apps/colab bun run test bun run build WRANGLER_LOG_PATH=/private/tmp/colab-wrangler.log bunx wrangler deploy --dry-run --outdir /private/tmp/colab-worker node scripts/verify-runtime.mjs cd ../.. bun check ``` The finite runtime script starts a local Worker on port 8795 with a test-only signing secret, uses isolated in-memory Durable Objects, verifies access and concurrent updates, and opens headless Chromium for desktop/mobile and Vietnamese checks. It never creates a production session. It writes screenshots to `/private/tmp/colab-*.png` and closes the browser/runtime when finished. Install the Playwright Chromium browser if it is not already available. After deployment verify `/api/health`, static asset responses, central sign-in, an invited account and temporary guest, live team updates, skill generation and an AI run. Correlate the Worker version with its source revision and inspect Wrangler logs without logging passwords, cookies or prompts. A successful Cloudflare upload alone does not establish that central sign-in is deployed. ## Automatic deployment `.github/workflows/colab-cloudflare.yaml` validates affected `main` and `production` revisions and deploys only `production`. The repository switchboard in `tuturuuu.ci.ts` controls it. Manual dispatch on `production` retries a release. The validation job tests both workspaces, builds the client, bundles the Worker, and uploads revision-specific assets. Deployment downloads those same assets, records the Git SHA in the Worker version message, and checks canonical health and every asset hash. Verification retries up to 12 times, five seconds apart, so a successful upload is not mistaken for immediate edge propagation; persistent hash mismatches still fail the job. Deployments are serialized and never cancel an active release. Configure the repository Actions secret (or environment `colab-production` secret) `COLAB_CLOUDFLARE_API_TOKEN`: Workers Scripts edit, Workers AI read, account read, and Workers Routes edit plus zone read for `tuturuuu.com`, scoped to Tuturuuu. The session signing secret stays in Cloudflare and is not regenerated by CI. An expired or incomplete login returns to a bilingual recovery panel instead of a JSON error. `/verify-token` unwraps the central portal's callback only for Colab's own `/auth/callback`; the callback still requires its original nonce cookie.