Quick start
Codelit starts with one conversation instead of a mode picker. Describe the outcome once, and Codelit routes the request to the right Product Plan, Architecture, Agent Team, or Plan & Ship path while keeping specialist editors available for direct control.
Start from an outcome
Open Codelit and describe what should be true when the work is finished. Codelit chooses what to create, asks one focused question only when the destination is genuinely ambiguous, and keeps every result in the same Thread.
- Describe the result in one message, including a URL, destination, or schedule only when the work needs one.
- Review the result in the conversation. Ask for a correction, another artifact, or the next step without starting over.
- Open the specialist editor only when you want direct control. Agent Teams keep Flow, run options, Apps, and advanced settings available there.
Prove an Agent Team safely
Choose Try agent first. It starts a Sample with committed example inputs, evidence, and approvals without calling a model or external App. When the receipt is ready, choose Use my data to continue through one guided setup path.
- Read the terminal timeline at the bottom.
- Approve or reject the sample checkpoint to see the real supervision flow.
- Choose Use my data only after the sample outcome is useful.
Use your data, then go live
Ask Codelit carries your request from proof to live work. Codelit reuses a healthy App and the Team's previous resource when it remains valid, automatically selects a sole safe resource, and asks one compact question only when several choices are plausible. A private personalized proof runs in the open tab; after it succeeds, you can automate it or use the separately gated managed runtime.
- Connector writes and browser actions stay simulated during the personalized proof.
- Trigger Hub chooses the safest compatible starting mode and keeps schedules, limits, health, and receipts together.