Onboarding

Onboarding runs automatically on first launch. It has three steps. Complete all three — each step sets context the rest of the product uses.

​

Step 1 — Set your mission

The first screen has one field: First initiative. Enter a plain-language description of what this org is pursuing first. This becomes the first initiative in the system and gives agents context for how to interpret their work. A clear, specific directive produces better agent behavior than a vague one. Example: Build the leading autonomous AI research platform for model training optimization and reach $1M ARR in 12 months

​

Step 2 — Set up your first agent

The second step creates the first autonomous worker. Choose a coding agent / runtime. The options available in the onboarding wizard are: Depending on the runtime, the wizard asks for a local path, a model, or both. Choose the runtime your machine already has installed and configured. The goal is getting one reliable agent to complete one real issue. Runtime selection can be refined later from the agent’s Configuration tab.

​

Step 3 — Set the first issue

The final step creates the first issue so the agent has work ready immediately after onboarding completes. The step has two fields:

• Title — the short directive the agent will work against
• Description — additional context, instructions, or acceptance criteria

A good first issue is:

• Small — completable in a single run
• Concrete — success is obvious when the work is done
• Real — the output should actually matter, not be a test

Write the title as a clear directive, not a vague label.

​

After onboarding

When onboarding completes the board lands on Dashboard. From here:

• Dashboard — check that the agent is active and the issue appears in the work queue
• Inbox — review failures, approvals, and agent activity once the first run starts
• Agents — inspect the first agent’s overview, configuration, and run history
• Issues — create more issues or adjust the first one