Consulting Practice
Budget proposal support
Long source packets make a pilot look cheap per call but expensive per approved proposal.
Economics
Free Canadian small business workbook
AI Cost and Token Budget Planner
A worksheet for estimating the operating cost of model routing, retrieval, tools, evaluation, and cached context.
7 pages · PDF workbook · No email required
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.
What’s inside
A working guide
for a real decision.
Build a practical cost model across usage scenarios, model tiers, token volume, tool calls, evaluation passes, caching, and monthly operating budget. Use this guide to make the operating choice explicit, test it with evidence, and record who owns the next decision.
Who this is for
SMBs deciding whether AI is affordable at production scale.
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.
Volume
How many requests, sessions, or documents will this workflow process?
Context
How much retrieved or uploaded context is needed per run?
Routing
Which requests need stronger models and which can use smaller models?
Tools
Which deterministic calls add cost, latency, or operational value?
Evaluation
How many review, scoring, or regression passes are required?
Illustrative examples from the workbook
Where this becomes practical.
Independent Retailer
Budget customer-service responses
High-frequency routine questions should not route to the most expensive model every time.
Accounting Practice
Budget review summaries
Low-volume but complex cases may justify escalation only when confidence or materiality requires it.
- AI-supported role
- Estimate request routes, context size, cache use, tool calls, evaluation passes, and usage-derived cost.
- Human authority
- The owner sets a budget, quality floor, escalation criteria, and spend review cadence.
- What to measure
- Track actual cost per completed outcome, token use, latency, retries, and quality.
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 workflowFurther reading in the library
General operational guidance only. These resources are not legal, privacy, cybersecurity or regulatory advice.