Pick the right AI tool
Start with the job, not the tool
Tool choice begins with the job’s input, output, evidence, consequence, and frequency.
1Learn the idea
Read
The working principle
Tool choice begins with the job’s input, output, evidence, consequence, and frequency. This principle matters because an AI system produces likely output from the context and instructions it receives; it does not automatically know the organization’s current facts, private policy, unstated intent, or acceptable risk.
Use the following sequence for this page: describe the desired outcome without naming a product; identify inputs, freshness, and source authority; estimate error cost and reversibility; decide whether the task is one-off or repeatable. The sequence is a guide, not a ritual. Skip a step only when its question truly has no effect on the outcome, and strengthen it when mistakes would be costly.
Read
A practical method
Read
1. Describe the desired outcome without naming a product
Read
2. Identify inputs, freshness, and source authority
Read
3. Estimate error cost and reversibility
Read
4. Decide whether the task is one-off or repeatable
Read
Work through the scenario
Return to the opening case: A colleague buys an AI subscription to “help with reports” before deciding whether the bottleneck is finding facts, calculating metrics, drafting prose, or obtaining approval. Begin by rewriting the request as a small contract. Name the intended reader or user, the authoritative material, the operation to perform, the required output, and the review owner. If current information is required, identify where it will come from. If exact calculation or action is required, assign that step to a deterministic tool or an approved system rather than relying on prose generation.
A useful instruction could follow this shape:
Goal: help [reader] accomplish [outcome]. Use only [named sources or supplied material] for factual claims. Perform [specific operation] and return [format]. Mark missing information as TBD or ask a focused question; do not guess. Before the result is used, [named person or role] will check [criteria].
Read
Failure modes to catch
- Choosing from a demo instead of a requirement. This hides an important assumption or removes a review point. Replace it with an explicit rule, a source check, or a human decision.
- Equating a fluent interface with broad capability. This hides an important assumption or removes a review point. Replace it with an explicit rule, a source check, or a human decision.
- Ignoring the non-AI option. This hides an important assumption or removes a review point. Replace it with an explicit rule, a source check, or a human decision.
Read
Make it reusable
Turn Start with the job, not the tool into a template you can reuse this week: job statement, required evidence, failure mode to catch, and reviewer. Store it next to your other pick the right ai tool notes. When the job changes, rewrite only the job statement and re-run the same failure-mode list — do not invent a new workflow from scratch. Role of this page: Hook and intuition.
Go deeper
Before you start
Why this matters
A colleague buys an AI subscription to “help with reports” before deciding whether the bottleneck is finding facts, calculating metrics, drafting prose, or obtaining approval. The temptation is to begin by typing a broad request and judging whatever appears. That approach makes a good result hard to repeat and a bad result hard to diagnose.
Related lessons
Check your understanding
Page assessment
Answer from memory. Completion is saved from this evidence, not from opening the next page.
All responses are required.