Prompt design canvas template
Design a production prompt piece by piece — role, context, task, constraints, examples, output format — plus test cases.
Use this templateFree, opens in your browser. No sign-up.
What's on the board
- Role
- Who is the model? e.g. senior support agent at Acme · Tone: friendly, plain, concise
- Context
- Retrieved docs or data the answer must use · Who the user is and what they tried
- Task
- One clear instruction · Number the steps for multi-step work
- Constraints
- Max 150 words · Use only the context; say 'I don't know' otherwise · No legal or medical advice
- Examples (few-shot)
- Input → ideal output #1 · A tricky edge case · A bad answer to avoid
- Output format
- JSON schema or markdown headings · Cite sources as [1], [2]
Table columns: Input, Expected behaviour, Pass?.
Also on the board
- Test cases
How to use this template
- Click Use this template. It opens in the Kelvo app as a new board, saved in your browser.
- Double-click any box to change its text. Replace the examples with your own content.
- Sketch, then convert. Draw boxes and arrows with the pen, select the strokes and click Convert sketch: they become real boxes and links.
- Ask Kelvo right on the board (Pro). With Pro, type @kelvo and what you want in any box or text, for example “@kelvo add error handling”, and press Enter. The change is made there and the request disappears; ⌘Z undoes it.
- Keep the prompt next to the diagram. Add a code block from the Insert (+) menu for prompts, schemas or config, right beside the boxes they belong to.
Good for
- ai
- llm
- prompt engineering
- canvas
- Explaining an LLM feature's architecture to engineers and stakeholders
- Deciding between prompting, retrieval and fine-tuning
- Planning evaluations and risks before launch
Related templates
Prompt chaining workflow
Break one big LLM task into small chained prompts with checks between them: classify, extract, draft, critique, send.
RAG pipeline
Retrieval-augmented generation end to end: ingest and embed documents offline, then retrieve, rerank and answer with citations.
LLM agent loop
How a tool-using agent plans, calls tools, observes results and updates memory until the goal is met, with guardrails.
AI use-case canvas
Assess an AI opportunity on one page: problem, users, data, approach, value, risks and the smallest pilot.
Solution architecture canvas
Frame a solution on one page: goals, stakeholders, scope, qualities, constraints, integrations, decisions, risks and roadmap.
Business Model Canvas
Describe how your business creates, delivers and captures value on one page, in the nine classic blocks.
All ai and machine learning diagram templates · All templates