In this lesson
- 01Learning Objectives
- 02The Problem
- 03The Concept
- 04Build it
- 05Use it
- 06Exercises
- 07Key Terms
- 08Further Reading
About 900 words of reading, with code, 7 quiz questions and the tutor.
The full lesson opens with an access code
You can see what this lesson covers and the milestone it sets. The full text, code, quizzes, the tutor and the AI reviews come with the K850 practice, along with weekly build sessions and code review.
Milestone forAn observable back-office agent
Break it on purpose
Build a failure suite from real statement mess: duplicate payments, partial payments, reversed transactions, two customers sharing a phone, and the agent claiming a match it never verified. Record how each is detected.
Done when
- At least 25 failure cases: duplicates, partials, reversals, shared phones, false completion
- Detection of false completion claims by checking tool evidence
- Pass rate per failure type, at least 90% overall
Stretch: Add a chaos mode that injects tool failures at random
Reviews open with an access code.
Interview practice
Questions on this topic that AI engineering interviews ask, with the companies reported to ask them. Answer the way you would out loud; Jev scores it and DeepSeek tells you what to add.
Scoring opens with an access code. You can still read the questions and prepare.
Adapted from open-source work: AI Engineering from Scratch by Rohit Ghumare (MIT, lesson text, code and quizzes); Awesome LLM Apps by Shubham Saboo (Apache-2.0, starter code); AI Engineering Interview Questions by Outcome School (Apache-2.0, interview questions). Capstones, milestones, data packs and Zambian context by Zambrite.