Back to Academy

AI Cost Academy

Build production LLM applications

Choose the right LLM pattern for structured data, retrieval, agents, chat, multimodal workflows, and ML-adjacent systems.

Course goal

Choose and implement the right LLM pattern for one production workflow.

Built for application engineers, ml engineers, product builders. Work through the modules in order if you want the full picture, or jump directly to the lesson that matches the job in front of you right now.

Module 1

Structured outputs for extraction, classification, and scoring

Use schema-constrained outputs for reliable extraction, classification, and decision support instead of brittle free-form prompting.

10 min
Open lesson
Module 2

Hybrid search and reranking patterns for RAG

Combine lexical retrieval, dense retrieval, and reranking so the best evidence reaches the model more consistently.

11 min
Open lesson
Module 3

Query rewriting, decomposition, and retrieval routing

Improve retrieval quality by deciding when to rewrite, split, or reroute queries before they ever hit the retriever.

9 min
Open lesson
Module 4

QA over structured data and grounding patterns

Choose SQL, tool-based grounding, or retrieval when answers need to come from systems of record instead of model memory.

10 min
Open lesson
Module 5

Agentic tool-use patterns: planner, executor, and recovery

Design tool-using systems that can plan, act, retry, and escalate without turning every workflow into an unstable agent.

12 min
Open lesson
Module 6

Binary decisions and constrained choice with LLMs

Use bounded output spaces for routing and approvals without pretending the model should be the final authority.

9 min
Open lesson
Module 7

Summarization patterns for LLM applications

Choose operational, executive, or structured summaries based on the decision the summary needs to support.

10 min
Open lesson
Module 8

Production chat systems: memory, handoffs, and escalation

Structure chat assistants around session memory, retrieval, containment, and human handoff instead of a single giant prompt.

11 min
Open lesson
Module 9

Multimodal LLM workflows: vision, voice, and cost patterns

Understand where voice and vision help, where they create extra latency and cost, and how to design around those constraints.

10 min
Open lesson
Module 10

LLM-generated features for traditional ML

Use LLMs to generate labels, summaries, and semantic features that feed cheaper, faster downstream models.

9 min
Open lesson