Practical AI
Plain-English guides to using AI at work, grounded in my experiments.
These guides translate my original research into practical trial ideas. The results come from controlled experiments, not measured savings in customer businesses.
What Can AI Running on Your Own Computer Do for a Small Business?
7 min read
Local AI is worth testing on narrow jobs such as sorting enquiries, preparing document fields, and processing a reviewable backlog. The evidence here comes from controlled tasks on one computer, not measured savings in customer businesses.
Read full articleCan AI Work Through Your Paperwork Overnight?
8 min read
An overnight local-AI queue can prepare work for review, but the right model depends on the document mix. My synthetic batch test measured correct items per hour; it did not measure a complete paperwork workflow or staff time saved.
Read full articleCan You Trust AI to Pull Details From Documents?
8 min read
AI-extracted document fields need source checking. In my missing-field contract test, the small model supplied a value in 6.3% of cases where the answer was absent from the excerpt; this is not an error rate for all document answers.
Read full articleCan an AI Assistant Use Your Company's Procedures?
8 min read
A company assistant needs direct instructions, enough relevant source material, and reliable records of important details. Separate experiments on one small model show why supplying documents alone does not establish reliability.
Read full articleIs Running Your Own AI Really Cheaper?
7 min read
Local AI can have a very small processing electricity cost, but the business comparison must include hardware, setup, maintenance, and review. The prices quoted below describe an October 2026 experiment, not current provider quotes.
Read full articleHow to Test AI Before Spending Money on a Bigger System
8 min read
Test one business job on representative examples, decide what success means in advance, and measure the time to an accepted result. Suggested trial sizes and acceptance rules below are examples, not thresholds established by the research.
Read full article