Learning: LLM Fundamentals for Agents¶
How to Use This Page¶
- Work lesson-by-lesson and keep prompts versioned.
- Measure both quality and token cost.
- Iterate only one variable at a time.
Lesson 1: Fundamentals¶
Learn how prompt structure and instruction clarity shape model behavior.
What You Learn¶
- How to write task, constraints, and output format explicitly
- Why instruction ordering changes model compliance
- How token budgets influence response quality
Walkthrough¶
- Create a baseline prompt for one fixed task.
- Add explicit format constraints.
- Compare output consistency across 5 repeated runs.
Try It Yourself¶
- Move key instructions from bottom to top and compare outcomes.
- Remove one constraint at a time and note failure modes.
- Rewrite the prompt in half the tokens and compare quality.
Lesson 2: Intermediate Patterns¶
Learn template families, routing strategies, and context budgeting.
What You Learn¶
- How to route simple tasks to lower-cost models
- Why prompt templates should be task-specific
- How to track token usage by task class
Walkthrough¶
- Define low, medium, and high-complexity prompt templates.
- Route inputs by complexity.
- Log token input/output and quality score per run.
Try It Yourself¶
- Add a misroute case and analyze quality impact.
- Tune one template for lower cost without quality loss.
- Create a fallback template when the first response fails format checks.
Lesson 3: Production Patterns¶
Learn context trimming, relevance control, and prompt release management.
What You Learn¶
- How to keep only relevant context chunks
- Why noisy context causes lost-in-the-middle errors
- How to version prompts and roll back safely
Walkthrough¶
- Add a context filtering step before model invocation.
- Evaluate output quality with full vs filtered context.
- Store prompt versions with simple change notes.
Try It Yourself¶
- Build a tiny eval set with 10 representative queries.
- Compare two prompt versions on cost and accuracy.
- Pick a release candidate and document rollback criteria.
Code Examples¶
- Starter script:
docs/starter/stage02_llm_fundamentals.py - Stage architecture notes:
docs/roadmap/stage-02-prompt-design-context-control/architecture.md