Work in the room with clarity, control, and a visible trail.

Getting started

1. Sign in. Use the email sign-in link first so the same account works in browser and desktop. If you still need recovery-code sign-in, open the recovery login page from the access screen.
2. Create or open a project. Give the room a short name that identifies the outcome.
3. Set the objective. Describe the result, constraints, and what success looks like.
4. Add context. Attach the relevant small files and open the real project URL in the Browser pane.
5. Choose the next place to work. Use Chat for conversation, Tasks for trackable work, Reviews for decisions, and Browser for live verification.
6. Send a focused request. Select a mode or agent, then review the response, tasks, files, and reviews.

Manage projects

1. Create a new project. Click New Project, then give it a real name right away so the left rail stays readable.
2. Rename from the row. Use the compact project menu to rename the project. The title should stay on one line while actions stay pinned to the right.
3. Switch projects. Click the project row to open that project. The Current label marks the project you are already in.
4. Delete safely. Open the compact project menu and choose Delete. If a project still has a generic title, rename it first so the delete prompt is clear.

Project row actions

Each project row is meant to stay compact: the name stays on the left, the status chip stays visible, and the edit/delete controls sit on the right. If the row starts to feel crowded, shorten the project name first instead of widening the actions.

Name first, then work

The project name is the label you will see in the sidebar, in the workspace header, and in support or review discussions. Give it a short, specific name before starting work so it can be renamed later without confusion.

Review the project path

1. Open Path. Use the Path tab to see the active project path and its latest objective snapshot.
2. Check the current state. Review the path status before changing the objective so you know whether it is proposed or approved.
3. Update the objective. Keep the objective short and specific. The project path should reflect the latest approved direction.
4. Use the browser beside it. The Path view is a planning surface; the live browser remains the place to verify the real app result.

Understand the workspace

Project objective

The objective is the short statement that tells the room what outcome the project should deliver. Keep it concrete, specific, and easy to verify.

Chat

The central timeline shows your messages, agent decisions, next steps, and project preview cards. It is the main record of the project conversation. Use it to ask for help, review the latest provider reply, and keep one thread of work moving forward.

Project updates

The lower project-updates drawer keeps quick status notes in one place. Use it for the latest progress, visible reminders, and handoff context that should stay easy to scan.

Tasks

Tasks turn agreed work into trackable items. Update their status as work moves from pending to complete. Keep task titles short enough that they stay readable in the list and in the project report.

Reviews

Material decisions stay visible until you approve or reject them. Opening a review only opens its details; it never records a decision.

Agents and insights

Agents shows provider runs and status. Insights combines summary statistics with a complete readable project report, decisions, findings, progress, and deliverables.

Choose how the team works

Balanced is the recommended default. It considers planning, building, and review. Use the agent chips when you want a specific perspective:

• GPT · Strategist: scope, planning, and synthesis.
• Baki · Researcher: research and supporting context.
• Codex · Builder: implementation and technical execution.
• Claude · Reviewer: critique, risk, and quality review.

Auto-route lets the orchestrator select the best specialist. Turn it off when you want manual control. The actual models available depend on the server-side providers configured by the administrator.

Use the Browser pane

1. Enter an https:// or local development URL in the address field.
2. Use refresh after the project changes.
3. Switch desktop, tablet, and mobile sizes to check responsiveness.
4. Expand the pane for close inspection or open the URL externally.

Browser controls

The browser header and footer show the current URL, refresh control, viewport size controls, and the open-external option. Use those controls to verify the live project without leaving the room.

The Browser pane is the live verification surface. Use it to confirm what the user would actually see after a change, while keeping the room visible beside it.

Production previews are sandboxed. Do not enter passwords or sensitive customer data into an unfamiliar page loaded in the preview.

Files and tasks

Use Attach to add focused context. Supported file types are plain text, Markdown, CSV, JSON, PDF, PNG, JPEG, and WebP. Each file is limited to 2 MB. Large repositories and secrets should stay in approved development systems, not browser uploads.

Tasks can be created from the workspace and associated with an agent. Keep titles action-oriented and small enough to verify.

What belongs here

• Reference files, notes, and small supporting assets.
• Task details that need to stay visible in the room.
• Agent deliverables that should be reviewed or downloaded later.

Vault snapshots and reports

If you connect a local folder, the Files tab can stage read-only vault snapshots and create reports from that folder. Use the download menu for the project archive, agent deliverables, or the desktop app package.

Build and run automation

1. Open Automation. Choose the Automation tab or the Automation item in the sidebar.
2. Create a saved automation. Give it a clear name, description, trigger, and retry limit.
3. Add ordered steps. Agent work produces a Markdown deliverable, Create task adds a project task, and Review checkpoint pauses until an owner decides.
4. Choose a trigger. Manual runs start with Run now. Schedules run at the saved interval, with a minimum of five minutes. Secure webhooks display a secret URL once; copy it into an approved secret manager.
5. Monitor the run. Open Latest run to view step state, attempts, outputs, errors, and the execution log.
6. Stay in control. Pause stops before the next step, Resume continues, Cancel ends unfinished work, and Retry failed step restarts only the failed point.

When to use automation

Use automation for repeatable project work that needs a fixed order, a clear approval point, or a reliable handoff. It is best when you want the room to keep doing the same steps the same way every time.

Limits and notifications

Each project can save up to 25 active automations. An account can have up to three active runs at once, each automation can contain 1–20 steps, and retries are limited to five. Agent steps consume Project Credits. The notification area reports reviews, failures, completed runs, skipped schedules, and low credits.

Background execution

Runs continue through the server-side job queue if you leave the Automation tab. In production, PostgreSQL stores run state and the worker leases each job so multiple server instances cannot execute the same queued step simultaneously.

Review before deciding

1. Open the Reviews tab. Each row shows its title, short description, requester, and current status.
2. Select Open review to read the full decision request. Opening it does not approve anything.
3. Compare the request with the project objective and safety checklist.
4. Read the related agent activity and download any attached deliverables.
5. Choose Approve decision only when the evidence is sufficient. Choose Reject when more work or clarification is required.

Completed decisions remain listed with their recorded status for accountability. Automation review checkpoints also appear in the execution view and continue only after an explicit review.

What to look for

Make sure the request matches the current project goal, the deliverables are complete, and any risk is clearly explained. Reject if the evidence is thin, the goal changed, or the action would create an unsafe or irreversible result.

Read and download insights

The statistics at the top of Insights are only the summary. The full report underneath contains the current objective, task progress, review decisions, agent findings and activity, and downloadable files and deliverables.

1. Open Insights from the project tabs.
2. Review the completion, review, and agent-run statistics.
3. Read the complete report sections underneath; they are generated from the current saved project record.
4. Use Download report for a readable Markdown copy.
5. Use Download project archive for the project ZIP containing the report, manifest, uploaded files, and agent outputs.

What the report is for

Use Insights when you need to check progress, review decisions, or hand the project to someone else. The report is the readable history of what was done, what remains, and what files were created along the way.

Use project memory

1. Open Project memory. Use the Brain or Project memory tab to review saved notes, checkpoints, and durable context for the project.
2. Read before changing direction. Project memory is where earlier decisions and handoff notes live, so it helps you avoid repeating work.
3. Check the latest checkpoint. Use the memory view to confirm what the team already verified and what still needs attention.
4. Keep it durable. Record only stable project facts, decisions, and next steps. Avoid secrets and transient scratch notes.

Resume or recover work

1. Open Recovery. Use the Recovery tab when you need to restore state, review recovery details, or continue after a paused or interrupted run.
2. Check what is available. Recovery content helps you see what was saved, what was resumed, and what still needs manual attention.
3. Confirm before continuing. If the project was interrupted, make sure the latest objective, path, and related notes still match before proceeding.
4. Use support if needed. If recovery content looks wrong or incomplete, capture the issue and send it through support rather than guessing.

What recovery should answer

Recovery should help you answer three questions quickly: what was saved, what needs attention, and what can safely continue. If it cannot answer those questions, stop and verify the project state before taking the next step.

Settings sections

The Settings screen now saves operational project preferences to PostgreSQL, applies ownership checks, and records audit events. Live sections include account profile, AI model selection, agent roles, automation defaults, notifications, project defaults, browser preview, security and privacy, data export and retention, integrations and webhooks, team access, and help links.

• Account & profile
• AI providers & models
• Agent roles
• Automation defaults
• Notifications
• Project defaults
• Browser & preview
• Security & privacy
• Usage & billing (read-only until live billing is approved)
• Data, export & retention
• Team & access
• Integrations & webhooks
• Desktop app (unavailable until the signed package ships)
• Help & support

How to use settings well

Use Settings to connect providers, adjust notifications, and check security or export options. If you need a new AI provider, add it here instead of hardcoding credentials. Provider secrets stay server-side and should be stored per account, not in the browser. Keep billing and desktop items in mind as release-gated features.

Use the help links in Settings when you need setup guidance, and use security/privacy options when you want to confirm what the project can store or share. If a section is marked unavailable, it is intentionally release-gated rather than broken.

Security and privacy

• Never share your recovery code, sign-in link, session token, provider key, or administrator token.
• Provider keys belong only in server secrets—never in the browser or a VITE_* variable.
• Sign out on shared devices.
• Use only project data you are authorized to process.
• Report unexpected account access through the support form below.

Each project is isolated to its claimed account. Browser sessions use HTTP-only cookies; desktop/API clients may use bearer tokens over HTTPS.

Provider setup

When you connect a model provider, keep the credential in the server settings for that account only. Do not paste it into chat, screenshots, or project notes. If the provider is unavailable, use the help links in Settings or ask support rather than inventing a temporary fix.

Troubleshooting

The browser pane is blank

Confirm the URL is reachable and uses HTTPS in production. Refresh once. If the website blocks embedding, open it externally.

The project list overlaps

Use shorter project names, rename repeated Untitled project entries, and keep the compact actions small. If the sidebar still looks stale after a change, hard refresh the page. If the row still feels crowded, the name is too long for the available space.

The project menu looks clipped or blurry

Close the compact menu and reopen it after the row is fully visible. If the row is still being squeezed, shorten the project name or widen the sidebar before judging the menu layout.

An AI run does not start

Check the Agents tab for its status. The administrator may need to configure the AI provider or the account may have reached its plan limit.

An automation run is retrying or failed

Open Latest run and inspect the failed step and execution log. Check provider configuration and Project Credits. Use Retry failed step only after correcting the cause; completed steps are preserved.

A scheduled automation did not run

Confirm the automation is Active, its next-run time is in the future, and the account has an active session and available capacity. A skipped schedule creates a notification with the reason.

A file will not upload

Confirm it is a supported type and no larger than 2 MB. Remove secrets before uploading.

I cannot sign in

Request a fresh sign-in link first. If you still need recovery-code sign-in, open the recovery login page from the access screen and use the newest access email.

Changes are not visible

Refresh the workspace and then the Browser pane. Confirm the browser points to the current project server, not an older v1.1 process or URL.

Frequently asked questions

Contact support

Use the authenticated support form below. Sign in first so the request can be securely associated with your account. Support works best when you give one clear issue and the exact step where it stopped.

Use support when the issue is account-specific, repeatable after refresh, or still unclear after checking the troubleshooting section.

What to send

Send the project name, the page you were on, the exact button or tab you used, and what you expected to happen. If the issue is visual, add a screenshot. If it is a browser or deployment issue, note whether a hard refresh changed anything.