Evaluation

Free Canadian small business workbook

AI Evaluation Rubric Builder

A worksheet for evaluating AI outputs, retrieval, tool use, escalation, tone, and reviewer confidence.

7 pages · PDF workbook · No email required

Actual working-record worksheet from the AI Evaluation Rubric Builder, page 3 of 7.
Preview all 7 pages Read the complete workbook before downloading.
Preview the complete PDF All 7 pages · Free to explore

Scroll through the full workbook below. Download the PDF for selectable text, printing and your own working copy.

Workbook page 1 of 7. For selectable text, use the free PDF download.
Page 1 of 7
Workbook page 2 of 7. For selectable text, use the free PDF download.
Page 2 of 7
Workbook page 3 of 7. For selectable text, use the free PDF download.
Page 3 of 7
Workbook page 4 of 7. For selectable text, use the free PDF download.
Page 4 of 7
Workbook page 5 of 7. For selectable text, use the free PDF download.
Page 5 of 7
Workbook page 6 of 7. For selectable text, use the free PDF download.
Page 6 of 7
Workbook page 7 of 7. For selectable text, use the free PDF download.
Page 7 of 7

What’s inside

A working guide
for a real decision.

Define pass/fail criteria, reviewer instructions, sample cases, escalation thresholds, and improvement loops before AI-supported work reaches production. Use this guide to make the operating choice explicit, test it with evidence, and record who owns the next decision.

Who this is for

Agentic workflows, advisory tools, document assistants, and sales or service copilots.

Bring the people who own the work

Include the workflow owner, a person who performs the work, a reviewer with authority to approve or stop it, and the relevant data or tool owner.

Includes an explainer, working worksheet, three illustrative examples and practical considerations. This is a planning PDF, not prebuilt automation software.

Use it with your own work

Five questions
to work through.

Choose one workflow. Record enough context to support a decision, then use the worksheet to name the owner, evidence and next review.

  1. Accuracy

    What must be correct, sourced, complete, and current?

  2. Grounding

    What evidence should the system cite or expose to the reviewer?

  3. Tool behavior

    Did the system call the correct deterministic tool with valid inputs?

  4. Escalation

    When should the system stop and route to a person?

  5. Tone and fit

    Does the output match the workflow, audience, and risk level?

Illustrative examples from the workbook

Where this becomes practical.

Consulting Practice

Evaluate intake briefs

A fluent brief may omit a client constraint that changes the proposed work.

Independent Retailer

Evaluate customer answers

A reply can sound helpful while inventing a price, policy, or availability claim.

Accounting Practice

Evaluate financial summaries

The firm needs a rubric for factual grounding, materiality, clarity, and abstention.

AI-supported role
Score representative outputs against explicit criteria and attach source and tool evidence.
Human authority
Reviewers define pass thresholds, adjudicate disagreements, and approve remediation.
What to measure
Track rubric pass rate, severity of defects, reviewer agreement, and escalation accuracy.

Illustrative scenarios, not client results or a promise of performance. The workbook includes additional case-specific prompts.

A useful first step

Use the workbook.
Bring us the next question.

Download and use it without booking a call. If you want help applying it, email Chris with the workflow you’re considering and what you want to improve.

Discuss your workflow

Further reading in the library

General operational guidance only. These resources are not legal, privacy, cybersecurity or regulatory advice.