LLM Application Engineering
AIE-1013 credits · 48h required · 2h optional
You have already shipped four of these. This course is not here to teach you to call an API — it is here to convert what you did by instinct into something you can specify, defend, and repeat. Two of three credits are already awarded, so most of what follows is exemptable; what is not exemptable is the part that closes your actual gap.
By the end you can
- Specify and enforce structured output such that malformed responses are impossible rather than unlikely
- Design tool interfaces a model can actually use, and explain why a given interface fails
- Name and detect the specific failure modes of a deployed LLM feature
- Manage context deliberately — what goes in, what gets dropped, and what that costs
What this builds
- LLM application engineering0/20 demonstrated
Next assessment. Anatomy of a feature you already shipped — 60 min, tier 2
0/20 assessed items demonstrated · 5/20 read or watched. The second number is how you close a gap; only the first is evidence that it closed.
0 of 20 demonstrated · 5/20 read
4h 45m of 48h
M1 · What you are actually programming
3/5 · 6hlecture · 1h · tier 0 self-marked
Intro to Large Language Models — Andrej Karpathy
reading · 1h · tier 0 self-marked
reading · 1h · tier 0 self-marked
reading · 1h · tier 0 self-marked
assignment · 1h · tier 2 panel-assessed
M2 · Prompting as engineering
1/9 · 11h 15m- optional
lecture · 1h · tier 0 self-marked
Learn to Spell: Prompt Engineering (LLM Bootcamp) — The Full Stack
lecture · 1h · tier 0 self-marked
Prompting 101 | Code w/ Claude — Anthropic
lecture · 1h 15m · tier 0 self-marked
AI prompt engineering: A deep dive — Anthropic
reading · 45m · tier 0 self-marked
Chain-of-Thought Prompting Elicits Reasoning in Large Language Models
reading · 30m · tier 0 self-marked
Self-Consistency Improves Chain of Thought Reasoning in Language Models
assignment · 1h 30m · tier 1 machine-verified
assignment · 1h · tier 2 panel-assessed
reading · 1h · tier 0 self-marked
reading · 1h 15m · tier 0 self-marked
DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning
assignment · 2h · tier 2 panel-assessed
M3 · Structured output and schema enforcement
0/5 · 5h 30mreading · 1h · tier 0 self-marked
reading · 1h · tier 0 self-marked
- exemptable
assignment · 2h 30m · tier 1 machine-verified
assignment · 45m · tier 1 machine-verified
retention · 15m · tier 1 machine-verified
M4 · Tool use and function calling
0/7 · 7h 30mlecture · 1h · tier 0 self-marked
Augmented Language Models (LLM Bootcamp) — The Full Stack
reading · 45m · tier 0 self-marked
Toolformer: Language Models Can Teach Themselves to Use Tools
reading · 45m · tier 0 self-marked
reading · 1h · tier 0 self-marked
assignment · 3h · tier 1 machine-verified
assignment · 45m · tier 2 panel-assessed
retention · 15m · tier 1 machine-verified
M5 · Context management
1/6 · 6h 15mreading · 1h · tier 0 self-marked
reading · 45m · tier 0 self-marked
reading · 45m · tier 0 self-marked
assignment · 3h · tier 1 machine-verified
assignment · 30m · tier 2 panel-assessed
retention · 15m · tier 1 machine-verified
M6 · Failure modes
0/4 · 4h 45mlecture · 1h · tier 0 self-marked
UX for Language User Interfaces (LLM Bootcamp) — The Full Stack
assignment · 2h · tier 2 panel-assessed
- exemptable
assignment · 1h 30m · tier 1 machine-verified
retention · 15m · tier 1 machine-verified
M7 · Course project
0/4 · 8h 45mproject · 3h · tier 3 artifact
project · 2h 45m · tier 2 panel-assessed
project · 2h · tier 3 artifact
defense · 1h · tier 4 defended