LLMs, Tokens and Context Windows

Learning Outcome

Understand how language models process prompts, context, memory, and long inputs.

Core Ideas

• Token: A unit of text processed by a language model.
• Context window: The amount of prompt and prior conversation the model can consider.
• System instruction: Higher-priority behavior guidance for the model.
• Temperature: A setting that affects variation in generated responses.

Career Use Case

A product manager summarizing long customer feedback can decide what to include in the prompt and what to split into smaller batches.

Practical Workflow

1. Start by naming the outcome: what should improve after using LLMs, Tokens and Context Windows?
2. Add the input material, constraints, and success criteria before asking for output.
3. Ask for assumptions and uncertainty when the answer affects a real decision.
4. Verify important claims, numbers, and policy statements before publishing or acting.

Hands-On Mini Task

• Take a long article title, a meeting note, and a policy excerpt; decide which parts must fit into the model context for a useful summary.
• A good answer explains what context is necessary, what can be omitted, and where memory limits may affect accuracy.
• Before moving on, explain how Token and Context window change the decision.

Common Mistakes

• Using a generic prompt when the task needs clear context.
• Accepting polished wording as proof of accuracy.
• Sharing private data without redaction or approval.
• Skipping a final human review for important decisions.

Quick Revision

Module 1: AI Foundations lesson 2 is about practical judgement: use AI to increase speed, but keep the goal, context, evidence, and accountability clear.

FAQs