AI artefact templates and rubrics

How to use this

Practical, not perfection

Pick the tier you are studying and copy the template into your notes.
Complete it for one real example (work, a side project, or a safe fictional scenario).
Use the rubric to tighten it until it is defensible.
Paste a short reflection into your CPD record: what you assumed, what evidence you would keep, and what you would do next.

Foundations. Use case boundaries memo

Template + rubric + example

Template

Title: Use case boundaries memo

1) What this system is for (one sentence)
- 

2) What it must NOT be used for (three bullets)
- 
- 
- 

3) Inputs and outputs
- Inputs: 
- Outputs: 

4) Who is affected if it is wrong
- 

5) Bad day plan (fallback)
- How do we notice it is wrong?
- What do we do when we notice?

6) Evidence to keep
-

Rubric (what “good enough” looks like)

Scope and boundaries are clear (what is in/out).
High-impact use is identified (or explicitly excluded).
Evidence is identified (what you would log/measure/keep).
Next actions are concrete and realistic.

Worked example (short)

Example (short):
This system drafts customer support replies for low-risk queries.
It must not make account changes, provide legal advice, or handle medical/safety emergencies.
Bad day plan: route to human if confidence is low or retrieved policy is stale; log tool use and citations.

Applied. Evaluation and red flag checklist

Template + rubric + example

Template

Title: Evaluation plan (lightweight)

1) Goal and decision
- What decision will this support?

2) Success metrics
- Primary metric:
- Secondary metrics:

3) Slice tests
- Slice 1:
- Slice 2:
- Slice 3:

4) Failure we most want to catch
- 

5) Red flags (stop or rollback triggers)
- 
- 
- 

6) Evidence to keep
-

Rubric (what “good enough” looks like)

Assumptions are explicit and testable.
Metrics match the real cost of errors (not vanity scores).
Slices cover a vulnerable group or a high-impact scenario.
Evidence is identified (what you would log/measure/keep).

Worked example (short)

Example (short):
Primary metric: resolution time saved without increasing complaint rate.
Red flags: citations missing; tool calls spike; user reports unsafe advice.

Modern systems. Monitoring and governance pack

Template + rubric + example

Template

Title: Monitoring and governance pack

1) Risks we accept (residual risk)
- 

2) Monitoring signals
- Data drift signal:
- Quality signal:
- Safety signal:

3) Guardrails
- Tool permissions:
- Stop conditions:

4) Incident trigger
- When do we escalate to a human?

5) Evidence and retention
- What logs do we keep?
- For how long?

Rubric (what “good enough” looks like)

Trade-offs are stated, not implied.
Monitoring is actionable (alert → owner → runbook).
Guardrails include permission scoping and rollback.
Evidence is identified (what you would log/measure/keep).

Worked example (short)

Example (short):
Signals: stale retrieval rate, refusal rate, tool-call anomalies.
Guardrails: approved tools only, per-action limits, fast revoke.