Prompting & Context Engineering.

How to make a probabilistic model behave like a reliable business tool. Last week you drove a coding agent and saw its harness. This week we zoom into one layer — the instruction layer — because it is the highest-leverage, lowest-cost skill in the entire stack.

This week: 📝 Quiz 1 (Weeks 1–3 foundations, 5 multiple choice, closed-book) at the end of class — readings and sample questions are on the Week 2 Summary page. 👥 GA1 is due Tue 9/15 (Wed section) / Wed 9/16 (Thu section), 11:59 pm — join a group if you haven’t. 📡 Agent Radar opens class.

The hook

One prompt change flips reliability

Same model. Same 20 messy vendor emails. The only thing that changes is the prompt. (Illustrative teaching example — you’ll reproduce this effect yourself in the hands-on.)

Before

What’s the total?

Usable outputs: sometimes a number, sometimes a sentence, sometimes the wrong currency…

~60% usable · format varies every run

After

SYSTEM: You are an invoice-processing assistant. Return ONLY JSON: {"total_usd": number|null} If no total is present, use null. EXAMPLE input: "…amount due USD 1,284.50…" output: {"total_usd": 1284.50}

Same model — now every answer is a clean, parseable record.

~100% usable · identical shape every run

The gap between ~70% and ~98% reliability is the gap between a tool people trust and a tool people turn off. Prompting is free and instant — it’s where an MIS professional adds value without an ML PhD.

The cost lever

Cheapest fix first

When an LLM feature underperforms, there is an ordered menu of fixes — and the price rises steeply as you go down it.

Fix	Cost	Speed	When
1 · Edit the prompt	Free	Seconds	Always start here
2 · Add few-shot examples	Free (a few tokens)	Minutes	Format or edge-case misses
3 · Better context / retrieval	Engineering time	Days	Model lacks the facts (Week 7: RAG)
4 · Fine-tune	Data + compute + upkeep	Weeks	Consistent style at scale, hundreds+ examples
5 · Wait for a new model	—	Quarters	Not a strategy

This week

Work through the four parts

01 FoundationsAnatomy of a promptThe five parts every prompt has — click through an annotated real example — plus system vs user prompts and why the system prompt is your policy guardrail. → 02 ReliabilityTechniques that raise reliabilityFew-shot, chain-of-thought, structured JSON output, and a temperature dial you can drag — with a which-technique picker to test yourself. → 03 The 2026 core skillContext engineeringThe window is a budget. Play the packing game: fit a support agent into 4,000 tokens — and meet context rot, plus the week’s news hook. → 04 PracticeExercises, case studies, interview checkPrompt Autopsy, the hands-on with a reliability check, the $1 Chevy Tahoe and friends, your capstone system prompt, and five interview questions. →

Objectives

By the end of Week 3 you can…

Name the five parts of a prompt and use each as a knob Apply system prompts, few-shot examples, chain-of-thought, and JSON output Set temperature to match the task — low to automate, high to ideate

Explain context engineering: the budget, curation, and context rot Decide when to prompt vs when to fine-tune (and why fine-tuning comes last) Prove a prompt change actually improved results — with a reliability check