Getting Real Work Out of a Model

A practical course for people who use AI chat tools every week and quietly suspect they are getting less than the tools can give. Eight short lessons on what actually changes an answer: context, tasks, examples, format, reasoning, and honest iteration. Every lesson carries real before-and-after prompts you can copy tonight. No secret words, no incantations, no promises the tools cannot keep. By the end you will be able to brief a model the way you would brief a capable colleague, and to tell when it is guessing.

1. 1Why the same question gets a better answer6 minA vague question has a vague best answer; detail is what makes a good answer possible at all.
2. 2Context is most of the job7 minThe model only knows what is in front of it, so paste the thing itself and paste the part that matters.
3. 3A role is not a task6 minNaming a persona sets tone; only naming the verb, the object, the constraints and the finished state sets the work.
4. 4Show it two examples8 minExamples transmit their entire shape, including the parts you did not notice you were demonstrating.
5. 5Ask for the shape you can actually use7 minState the shape, the omissions, and what to do about gaps — but leave room for reasoning before the tidy part.
6. 6Make it show its work8 minShown reasoning is not a log of how the answer was made, but it puts claims where you can check them.
7. 7Edit the prompt, do not spin the wheel6 minRegenerating resamples the same prompt; naming what is wrong is the only thing that changes the pile.
8. 8How to tell when it is guessing9 minFabrication can be more specific than truth, so verify by cost of being wrong, never by how confident it sounds.