Kimi Novice tutorial

Novice · step 1 of 7

The 5-part prompt formula

Role, context, task, format, constraints.

Role: you're helping a small-business owner.
Context: [paste facts].
Task: [one clear job].
Format: [table / 5 bullets / 120 words].
Constraints: say "unknown" instead of guessing; cite sources.

A good result follows the format and length you set. Missing parts in the prompt show up as generic parts in the answer.

Why this step matters: The same model gives much better answers to a specific prompt. This is the cheapest improvement you can make.

Novice · step 2 of 7

Organize your work

Keep one chat per document or project, and put a short brief at the top so a fresh chat can pick up the thread.

Why this step matters: Grouping chats and files keeps context together, so you stop re-explaining and re-uploading.

Novice · step 3 of 7

Files and research

Upload the document and ask for page references for every claim; then spot-check two of them.

Why this step matters: Grounding answers in your own files or live sources cuts made-up details and makes them checkable.

Novice · step 4 of 7

Limits you'll hit

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

• Start a new session when a thread gets long; paste a short summary.
• Don't re-run big jobs you could have checked on a small sample first.

Why this step matters: Knowing when limits reset and what drains them stops you getting cut off mid-task.

Novice · step 5 of 7

Two-source rule

For anything you'll act on, confirm with two independent sources, one of them official.

1. Ask for the source of any fact you'll reuse.
2. Open the link and find the exact sentence (Ctrl+F).
3. If you can't find it, treat the claim as unverified.
4. For files, check two page or row references yourself.

Before you answer: separate what you checked from what you're assuming. Write "unknown" instead of guessing. Give a link for every number.

Why this step matters: Chatbots state wrong facts in the same confident tone as right ones. Checking is the only way to tell them apart.

Novice · step 6 of 7

Bad vs good prompts

Bad: help me

Good: Here is a 30-page report. Give me a one-paragraph summary, then the 5 numbers that matter most with the page each comes from. Finish with 3 questions I should ask the author.

Why: a clear situation, task, format and limits.

Bad: is this right?

Good: Check this against the official page. Quote the sentence that supports it, or say it isn't there.

Why: asks for evidence instead of agreement.

Why this step matters: The same model gives much better answers to a specific prompt. This is the cheapest improvement you can make.

Novice · step 7 of 7

Three starter workflows

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