AI
Models, agents and practical artificial intelligence.
How to Test an AI Tool Before Giving It Real Work
Build a small set of real tasks with known outcomes, then record errors, cost and the help each run needs.
Open-Weight vs. Open-Source AI: Why the Difference Matters
Downloading model weights does not tell you what you may do with them or how the model was built.
The Hidden Costs of an AI Workflow
Compare the cost of a completed job, including retries, tools and review—not just the price of one prompt.
What Happens to the Files You Upload to an AI Assistant?
Uploading, storing, retrieving and training are separate operations. Check each one before sharing a file.
Running AI Locally: What Your Laptop Can Handle
Memory, context length and model size determine whether local AI feels usable on your machine.
AI Agents vs. Chatbots: What Actually Changes?
An agent can choose and run the next step. That changes permissions, costs and the way you check its work.