Framework
AI Model Selection Cheatsheet
Match cognitive load to model capability. A decision framework to select the right model for your task — whether you're using Claude, OpenAI, or Google.
The Decision Framework
Three questions to select the right model:
| Question | If Yes | Model Tier |
|---|---|---|
| Is this execution? | Well-defined task, clear success criteria, checklist exists | Small Model (no thinking) |
| Does this need judgment? | Guidelines exist but interpretation needed, some ambiguity | Mid Model + Thinking |
| Is this complex? | Define the problem then solve it, strategic reasoning required | Top Model + Thinking |
Context Modifier: Skills, Projects, or Instructions with domain knowledge reduce complexity by one tier.
Cross-Platform Model Reference
Note: Model names and versions change frequently. What matters is the tier — not the specific model. Choose your provider's fastest/cheapest option for Small tier, their balanced/mid-range for Mid tier, and their most capable for Top tier.
| Task Type | Claude Tier | OpenAI Tier | Google Tier | Thinking? |
|---|---|---|---|---|
| Structured / Execution | Fastest & Economical | Fast & Cost-Effective | Speed-Optimized | No |
| Unstructured / Judgment | Balanced Capability | Balanced Reasoning | Advanced Reasoning | Yes |
| Complex / Strategic | Most Capable | Most Advanced | Most Powerful | Yes |
The Employee Analogy
| Employee Level | Task Type | What They Do |
|---|---|---|
| Junior | Execution | Executes instructions from a checklist |
| Mid-Level | Judgment | Interprets intent within guidelines |
| Senior | Complex | Frames the problem, then solves it |
Don't pay senior rates for junior work. Don't expect junior output on senior problems.
Practical Examples
Format a document, run a template
Site audit, data extraction
Evaluate my LinkedIn headline
Debug code, implement feature
Blindspot analysis, strategy development
System architecture, novel frameworks
Key Rules
Always enable thinking mode for Mid and Top tier models
Context (Skills/Projects/Instructions) drops complexity by one tier
Pay compute upfront to avoid correction tax downstream
The less structured the request, the more advanced the model
Ready to apply this framework?
Use this decision framework to build Digital Employees that match your task complexity. The right model at the right tier saves both compute and iteration.