Multi-agent orchestration template
An orchestrator agent splits a goal across specialist agents with their own tools, then a reviewer agent checks the result.
Use this templateFree, opens in your browser. No sign-up.
What's on the board
- Specialist agents (run in parallel)
- Research agent · Data agent · Coding agent · Writer agent · Tools: search_docs, read_url · Tools: run_sql (read-only), chart · Tools: python sandbox, unit tests · Tools: style guide, templates
- Guardrails
- Budget per agent: 20 steps or $0.30 · Shared state is append-only + traced · Agents never call each other directly · Human approves any external action
Table columns: Pattern, Use when.
Also on the board
- User goal: 'Compare our churn to Q2 and draft a summary'
- Orchestrator agent: plan tasks, assign, merge results
- Reviewer agent: check facts, numbers and the plan
- Final answer + full trace
- Approved?
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
- multi-agent
- agents
- orchestration
- 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
LLM agent loop
How a tool-using agent plans, calls tools, observes results and updates memory until the goal is met, with guardrails.
RAG pipeline
Retrieval-augmented generation end to end: ingest and embed documents offline, then retrieve, rerank and answer with citations.
Prompt design canvas
Design a production prompt piece by piece — role, context, task, constraints, examples, output format — plus test cases.
Model evaluation plan
Metrics, datasets, targets and owners for evaluating an LLM or ML model, plus the gate a release must pass.
AI guardrails & risk register
Input and output guardrails around an LLM call, with a risk register for hallucination, injection, leakage and bias.
Prompting vs RAG vs fine-tuning
A decision tree for choosing prompt engineering, RAG, fine-tuning or an agent, with a cost and speed comparison.
All ai and machine learning diagram templates · All templates