AI guardrails & risk register template

Input and output guardrails around an LLM call, with a risk register for hallucination, injection, leakage and bias.

Use this templateFree, opens in your browser. No sign-up.

AI guardrails & risk register template
User input
Input guardrails: PII redaction, injection + topic checks
Safe?
Refuse politely + log
LLM call with system prompt + grounded context
Output guardrails: toxicity, grounding, PII
Pass?
Fallback answer or human review
Response to user
Risk
Example
Likelihood
Impact
Mitigation
Owner
Hallucination
Invents a refund policy
High
High
RAG + citations, faithfulness evals
ML eng
Prompt injection
A document says 'ignore your rules'
Medium
High
Input filters, least-privilege tools
Security
Data leakage
Shows another customer's data
Low
Critical
Access-filtered retrieval, PII redaction
Security
Bias
Tone differs by user name
Medium
Medium
Red-team set, regular audits
Trust & safety
Over-reliance
Staff accept wrong answers
Medium
Medium
Show sources + confidence, training
PM
AI guardrails & risks
no
yes
yes
no
The AI guardrails & risk register template as it opens in Kelvo: 9 boxes, 2 decisions among them, 1 table and 8 links.

What's on the board

Table columns: Risk, Example, Likelihood, Impact, Mitigation, Owner.

  • Refuse politely + log
  • Fallback answer or human review
  • Input guardrails: PII redaction, injection + topic checks
  • Output guardrails: toxicity, grounding, PII
  • Safe?
  • Pass?
  • User input
  • LLM call with system prompt + grounded context
  • Response to user

How to use this template

  1. Click Use this template. It opens in the Kelvo app as a new board, saved in your browser.
  2. Double-click any box to change its text. Replace the examples with your own content.
  3. Sketch, then convert. Draw boxes and arrows with the pen, select the strokes and click Convert sketch: they become real boxes and links.
  4. 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.
  5. 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
  • safety
  • risk
  • governance
  • 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

  • RAG pipeline template previewRAG pipeline

    Retrieval-augmented generation end to end: ingest and embed documents offline, then retrieve, rerank and answer with citations.

  • LLM agent loop template previewLLM agent loop

    How a tool-using agent plans, calls tools, observes results and updates memory until the goal is met, with guardrails.

  • Prompt design canvas template previewPrompt design canvas

    Design a production prompt piece by piece — role, context, task, constraints, examples, output format — plus test cases.

  • Model evaluation plan template previewModel evaluation plan

    Metrics, datasets, targets and owners for evaluating an LLM or ML model, plus the gate a release must pass.

  • Decision log template previewDecision log

    Record what was decided, why, who owns it and its status, so decisions don't get re-litigated.

  • Board meeting agenda template previewBoard meeting agenda

    A timed board of directors agenda with presenters, purpose and pre-reads, plus resolutions and attendance.

All ai and machine learning diagram templates · All templates

Use the AI guardrails & risk register template