LLM App Developer
Ship a product on top of the LLM API — prompting, evaluation, cost, and reliability.
This track assumes you already know
- 1
Just enough theory
- What Is a Token in AI? A token is the unit an AI model actually reads — not a word, not a letter. It explains your bill, your context limit, and why models miscount letters. Foundations
- What Is an LLM? A large language model is a machine trained to predict the next token. Here is why that simple objective produces something that looks like thinking. Foundations
- How Does an LLM Actually Write? One token at a time, each conditioned on everything before it. The generation loop explains streaming, cost, and why models cannot revise. Foundations
- What Is an Embedding? Embeddings turn meaning into coordinates, which is what lets a machine compute with language. The foundation under search, RAG, and attention. Foundations
- Temperature and Top-p, Explained Why the same prompt gives different answers, and how the two main sampling knobs actually reshape the model's choices. Foundations
- 2
Prompting that works
- Prompt Basics Not magic words. Prompting is task specification, and four reusable structures cover most of what works. Prompting
- Show, Don't Tell: Few-Shot Prompting Two examples communicate more than three paragraphs of instruction. Why in-context learning works and how to build examples that carry their weight. Prompting
- Prompt Patterns and Anti-Patterns A small set of prompt structures solves most tasks, and a smaller set of mistakes causes most failures. The reusable shapes, and the ones to avoid. Prompting
- Getting JSON Out of an LLM Asking politely for JSON gets you JSON most of the time. Most of the time is not good enough for code, and there are ways to make it guaranteed. Prompting
- What Is a System Prompt? Instructions set once at the top of a conversation, in a structurally distinct slot the model was trained to weight differently. Prompting
- Making a Model Think Step by Step Written-out reasoning is not a psychological trick. Each token gets one forward pass, so intermediate steps are genuine additional computation. Prompting
- What Is a Context Window? One token budget covering your prompt, the conversation history, retrieved documents, and the answer being generated. Everything competes for the same space. Prompting
- Why Do AI Models Hallucinate? Fluent, confident, wrong. Hallucination is not a bug in the system — it follows directly from what the system was built to do. Prompting
- Your Prompt Isn't Working. Now What? Four distinct failure types wear the same costume. Diagnosing which one you have saves the hours usually spent rewording a prompt that was never the problem. Prompting
- 3
Build and ship
- Your First LLM API Call From zero to a working request, plus the four errors that catch everyone on the way. Application
- Which Model Should You Use? Match the model tier to the task rather than defaulting to the largest. A framework that survives the next model release. Application
- Cutting Your API Bill Four places cost hides, ordered by how much they usually save. Most bills are dominated by one fixable thing. Application
- Why Responses Stream Token-by-token delivery is not a UI trick. It is the raw shape of generation, and it changes perceived latency more than any optimization. Application
- How Do You Know It Works? Without evals you are tuning prompts by vibes. A dozen saved examples is enough to start, and it changes how you work. Application
- From Demo to Production A working demo is maybe a fifth of the way there. Five gaps separate something that works when you try it from something that works when everyone does. Application
- 4
Keep it running
- Reliability Patterns Providers rate-limit, time out, and return malformed output. The patterns that keep a system up when its dependency is unreliable. Production
- Observability for LLM Systems When a user reports a bad answer next week, you need to reconstruct what happened. What to log, and the one field everyone omits. Production
- Cost Monitoring and Attribution Token spend is easy to measure and easy to ignore until the bill arrives. What to track, and which dimension actually explains your costs. Production
- Latency Optimization Perceived speed is dominated by time to first token, and most of that is prefill. Where the milliseconds actually go. Production