Prompt chaining workflow template
Break one big LLM task into small chained prompts with checks between them: classify, extract, draft, critique, send.
Use this templateFree, opens in your browser. No sign-up.
What's on the board
- Why chain instead of one prompt
- Each step is easy to test on its own · Cheap model for simple steps · Checks catch errors before the user sees them · Logs show exactly which step failed
Table columns: Step, Input, Output, Model.
Also on the board
- Incoming customer email
- Prompt 1: classify intent + urgency → JSON
- Valid JSON?
- Retry once with the parse error
- Prompt 2: extract order ID, product, issue
- Prompt 3: draft a reply from policy snippets
- Prompt 4: critique the draft for tone + policy
- Passes checks?
- Send reply, log the chain
- Queue for human review
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 chaining
- prompt engineering
- workflow
- 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 design canvas
Design a production prompt piece by piece — role, context, task, constraints, examples, output format — plus test cases.
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.
Model evaluation plan
Metrics, datasets, targets and owners for evaluating an LLM or ML model, plus the gate a release must pass.
Approval workflow
A request moves through manager and finance approval, with rejection and rework loops.
Content publishing workflow
Idea to published post: draft, edit, review, schedule, promote, with a revision loop.
All ai and machine learning diagram templates · All templates