AI Agents · Course resources
Notes: Get Better Agent Results With Prompt Engineering
Review the key ideas from Get Better Agent Results With Prompt Engineering.
Section 6 takes one bounded decision through a complete practical run in an existing AI application. The learner chooses a suitable use case, writes one combined request, runs it, examines the result and visible activity, checks the deciding evidence, and keeps the job, prompt and judgment together.
| Lecture | Practical development |
|---|---|
| How Can You Get Useful Work From AI? (Your Agent Practice Run) | A supplier-quote decision establishes the complete route from material and criteria to a checkable recommendation. |
| Which Job Should You Give an AI Agent First? (Use Cases) | Daniel's project-management comparison shows why an investigation is a useful first use case. |
| Which Tasks Make a Poor First Agent Exercise? (Task Selection) | The learner removes 4 first-run difficulties, then records one bounded task in “Choose your practice task” on Your Page. |
| What Does an AI Agent Guess When Your Prompt Is Vague? | Daniel's vague request reveals facts the application must ask about, assume or omit. The Claude Code result remains a proposed capture. |
| How Do You Write a Prompt for an AI Agent? (Requirements) | Purpose, scope, criteria, tradeoff, output format, sources and a stopping boundary become one runnable message. |
| Which Changes Improve an AI Prompt? (Few-Shot and Chain-of-Thought) | Examples teach a missing response pattern before zero-shot, one-shot and few-shot are named. Checkable evidence replaces a demand for private reasoning. |
| How Can You Tell a Good AI Answer From a Bad One? (Checking Results) | Fictional Tools A, B and C let the learner rehearse eliminating an unsuitable option, comparing total costs and preserving the export tradeoff before applying the order to a later result. |
| Can an AI Agent Help With a Business Decision? (Claude Code Case Study) | The exact RegulatorySense customer-group request demonstrates how Claude Code can support a human business decision. The run and answer remain proposed captures. |
| What Is an AI Agent Doing While You Wait? (Latency and Activity) | Latency and visible activity help the learner decide whether to wait, answer a permission request, redirect drift or preserve an error. |
| When Should You Interrupt an Agent? | Judge an unexpected action by the requirement it helps answer. Redirect a misunderstanding, interrupt repeated failure, and preserve useful work before restarting. |
| How Does an Agent Plan Its Work? (ReAct and ReWOO) | ReAct uses returned information to help choose the next action. ReWOO separates planning requests from collecting results. These names do not identify Claude Code’s private method. |
| Why Did Your AI Agent Stop? (Errors and Usage Limits) | The exact error distinguishes an unclear request, unavailable source, failed approach or stated usage limit and guides one relevant correction. |
| Can You Explain an AI Agent Run? (Prompt, Evidence and Judgment) | The learner keeps the request and result together in “Your request, result and review,” then records checked facts and sources, unresolved points and the correction they would make. |
Keep your request, result and review together on Your Page. The record should show which evidence supports your judgment and what remains unresolved.