Practical AI training for everyone
LearnModule 1
9 min read
Most people learn prompting by collecting phrases. Act as an expert. Take a deep breath. Think step by step. Some of these help, some did once and no longer do, and none of them explain why a prompt that worked on Tuesday produced something useless on Thursday. The explanation is worth more than the collection.
A language model generates tokens conditioned on its input and learned parameters. Modern assistants are also trained to follow instructions, and may use internal reasoning, tools and product memory. Predicting continuations is a useful starting model, but it is not a complete explanation of every product behaviour or a reason to assume the model cannot interpret a request.
Prompting gives the system a task, relevant evidence, constraints and examples. A role can steer vocabulary and style; it does not grant professional expertise. Check whether each technique improves your actual task instead of inferring reliability from how expert an answer sounds.
Sampling can produce different outputs from identical inputs. Greedy decoding and low-temperature settings can reduce variation where supported, but they do not guarantee factual correctness or perfect reproducibility across serving systems and versions. Record available settings and evaluate repeated runs instead of treating one output as a promise.
Almost every frustration people report with these tools traces back to this. A prompt is judged on one impressive result, deployed, and then behaves differently on the fourth attempt. It was never reliable. It was sampled once, favourably.
The same prompt, three runs
"Summarise this report in three bullets." Run one returns three bullets. Run two returns four, one of which is a heading. Run three returns three bullets, but the third editorialises about what the company should do next. Nothing changed except the sample. Any downstream process expecting exactly three factual bullets is now broken twice out of three times, and the person who wrote the prompt believes it works.
Four things, in order. How to construct a prompt from parts that each do a job. How to diagnose which part is failing when the output is nearly right. How to constrain output so a machine or a person downstream can rely on it. And how to measure all of that with a test set, so that "it works" becomes a number you can defend.
Try it now
Take a prompt you use regularly and run it five times on the same input, without changing a word. Save all five outputs side by side. The differences between them are the real quality of that prompt, and most people have never once looked at this.
A few quick questions. You'll see an explanation after each one.
Question 1 of 5
Why does the same prompt produce different answers on different runs?
Save your progress
Create a free account so your quiz answers and finished lessons are kept, and you can pick up where you stopped on any device.
Sign up free