Kimi Advanced tutorial

Advanced · step 1 of 7

Decompose and chain

1. Split a big job into steps with a clear output each.
2. Feed each step's output into the next.
3. Check the output between steps, not just at the end.

Why this step matters: Small steps with a checked output each fail visibly and early, instead of one big answer that is wrong somewhere.

Advanced · step 2 of 7

Structured output

Ask for a fixed table or JSON so you can check and reuse it.

Return only JSON: [{"claim": "...", "source_url": "...", "quote": "...", "confidence": "high|medium|low"}]

Why this step matters: A fixed format can be checked by eye or by code and reused without retyping.

Advanced · step 3 of 7

Automation and agents

On Pro and above, Goal Mode and Kimi Claw can carry out longer, multi-step jobs. Ask for the plan first, approve it, and set a stopping point. Anything that sends, buys or deletes should need your yes.

Why this step matters: Automation repeats mistakes at scale, so you need to know exactly what is run and what is checked.

Advanced · step 4 of 7

Failure modes to watch

• Long summaries that blend two sections. Ask for page numbers.
• Agents that take a confident wrong turn early. Review the plan.
• Credit-hungry runs on big files. Test on a sample first.

Why this step matters: Knowing how it typically fails tells you where to look when you review its work.

Advanced · step 5 of 7

Cost control

• Free: basic use.
• Plus: $19/month or $180/year.
• Pro: $39/month or $372/year; adds Goal Mode and Kimi Claw.
• Max: $99/month or $948/year.
• Ultra: $199/month or $1,908/year.

Paid plans draw from one shared monthly credit pool that does not roll over. Kimi Code has a rolling 5-hour limit (Kimi membership pricing page).

Paid plans share one monthly credit pool with no rollover; Kimi Code has a rolling 5-hour limit (Kimi membership pricing).

Why this step matters: Paying for features you don't use is the most common waste. Knowing the limits first tells you if the free tier is enough.

Advanced · step 6 of 7

Privacy and team rules

• Don't paste passwords, ID numbers, card numbers or other people's private details.
• Assume the company can read and keep your chats unless its official policy says otherwise.
• For health, money or legal decisions, confirm with a professional or an official source.
• Agent features can open sites and take steps for you. Don’t give them logins or payment details.
• Write down which data is allowed in which tool, and who approves paid plans.

Why this step matters: Anything you paste may be stored and read. Deciding what never goes in is easier than undoing a leak.

Advanced · step 7 of 7

Build a 10-task test set

1. Collect 10 real tasks with known good answers.
2. Run them now and score each pass/fail.
3. Re-run them when the model, plan or your prompt changes.
4. Keep the prompt that wins, not the one that feels better.

Why this step matters: Without a fixed test set, 'better' just means 'felt better'. Scores let you compare prompts and models fairly.