Tell lrnit what you want
to master.

01 · how lrnit works

One sentence in.
A whole course out.

02 · the mechanism

It builds
while you
watch.

6/ 6 modules ready
01

Retrieval, end to end

4 lessons · 38 min

02

Chunking and recall

3 lessons · 26 min

03

Tool-calling loops

5 lessons · 51 min

04

Evals before you ship

4 lessons · 33 min

05

Context budgets and latency

3 lessons · 29 min

06

One feature behind a guardrail

6 lessons · 1 h 04

28 sources citedordered for what you shiprewritten as the field moves

03 · inside a lesson

One lesson,
four ways in.

Watch6:12

Read1,240 words

Listen8:40

Build40 lines

For the part you need to see happen.

For the part you need to check a source on.

For the commute, offline.

For the part you only believe once you have made it.

Your place is kept across all four.

MODULE 02 · LESSON 3Why your retriever misses the right chunk

Drawn explanation · chapters follow the syllabus

Embeddings put the answer near the question, not inside it.

A chunk that splits a definition from its example scores below a paragraph that mentions neither. That one fact explains most of what makes a good corpus retrieve badly[3] and why the boundaries, not the model, are usually what you are debugging[7].

SOURCE 3

Lewis et al., Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks (2020) · §2.1

“So the fix isn’t a bigger context window. It’s where you cut…”

audio brief · 8:40 · plays offline

retriever.py · yours, forty lines in

chunks = split(doc, on=headings)index  = embed(chunks)hits   = index.search(q, k=4)answer = llm(prompt(q, hits))

The last lesson of chapter one, and the only one with no quiz after it. You either have a retriever that answers, or you don’t.

62% · picks up where you left off

04 · built this week

Nobody asked for the same thing twice.

1,414

courses built since launch, updated daily

CRASH COURSE

Ship a RAG endpoint before Friday

3 modules · 44 min

FULL COURSE

Agents that call tools without looping forever

9 modules · 6 h 20

SEARCH

Why my reranker made recall worse

answer · 7 sources

FULL COURSE

Evals for a chatbot nobody trusts yet

11 modules · 7 h 05

CRASH COURSE

Cut token spend without losing answers

5 modules · 1 h 12

FULL COURSE

Take a prototype notebook to production

12 modules · 8 h 40

SEARCH

Is a vector DB worth it under a million chunks

answer · 9 sources

CRASH COURSE

Prompt injection, and what stops it

4 modules · 52 min

FULL COURSE

Earn the fine-tune before you pay for one

8 modules · 4 h 30

SEARCH

Why my agent costs four dollars a conversation

answer · 11 sources

So what do you actually want to know?

For teams