← All drillsBuild LLM Applications with LangChain
What you'll be able to do- ✓Build a chain of a prompt template, a chat model and an output parser, and measure how reliably it returns a clean answer
- ✓Get typed, validated data out of a model with a schema, and know what a schema checks that a prompt cannot
- ✓Teach a model a company's rules with few-shot examples (as chat messages) and with written rules, and compare them on a test set
- ✓Give a chat model a memory you control: keep the history, measure its cost per turn, and trim it knowing what you lose
- ✓Compose runnables with batch, retry, fallback, parallel chains and routing, and stream a reply
- ✓Serve a tutor as a FastAPI service and test it with real requests, including rejected ones
- ✓Solve a business problem end to end: extract terms from supplier contracts, test four versions, and let plain-code rules decide what needs a person
Ship LLM applications you have measured, not just demonstrated: chains, structured output, memory, an API, and a document-review pipeline for a real business problem.
⌁ In production at Klarna, Rakuten, Replit, and Morningstar for chatbots, RAG apps, and internal assistants.
Start this internshipCreate an account to unlock the 9 sections, the workbench, and askThili.
BeginSections
1. Build LLM Applications with LangChain
🔒 locked2. Your first chain: prompt, model, parser
🔒 locked3. Structured output: from text to typed data
🔒 locked4. Teach with examples: few-shot prompts
🔒 locked5. Chat models, messages and memory
🔒 locked6. Runnables and LCEL: composing, batching, retrying, branching
🔒 locked7. An AI tutor as an API
🔒 locked8. A business problem: reviewing supplier contracts
🔒 locked9. Optional: run a model on your own computer with Ollama
🔒 lockedDig deeper
📄Language Models are Few-Shot Learners (Brown et al., 2020)
paper🔗LangChain overview — official docs
article🔗Groq documentation (the API used in lessons 1 to 7)
docs🔗Ollama — run open LLMs locally (lesson 8)
docsPart of these learning paths
I'm a student and I want to get my first AI/ML job
View path →I want to build my first AI agent
View path →I want to build an app that answers from my own documents
View path →