Mission 2030

Get 10,000 software developers into better jobs with AI by 2030.

We train the developers companies need to build with AI.

Explore the open ecosystemsSee the bootcamps
nieva ~ chat

Building an agent with LangGraph and running it: python -m extractor --batch reports/2026-Q3. 38 PDFs · 1,240 pages · ~4 h of manual work. pull revenue, margin and debt from every report. Before writing anything, I'll define the graph and. dry-run it over three documents.. from langgraph.graph import StateGraph, START, END. from langgraph.checkpoint.memory import InMemorySaver. from langgraph.types import interrupt, Command. class State(TypedDict):. document: str. figures: dict. review: bool. builder = StateGraph(State). builder.add_node("read", read_pdf). builder.add_node("extract", extract_figures). builder.add_node("review", ask_confirmation). builder.add_node("save", save_row). builder.add_edge(START, "read"). builder.add_conditional_edges("extract", route). builder.add_edge("save", END). agent = builder.compile(checkpointer=InMemorySaver()). graph compiled · 4 nodes · 1 branch · 1 interrupt. run the three test files. read → pdf.text("acme-q3.pdf"). extract → model(schema=Figures). acme-q3 · revenue 4.2M · margin 31% · debt 0.9M. read → pdf.text("borealis-q3.pdf"). borealis-q3 · no text layer · it's a scan. This one has no text. The branch sends it to OCR. instead of inventing the numbers.. route → ocr. ocr.read(dpi=300). borealis-q3 · revenue 1.8M · margin 12% · debt 2.4M. what if the model gets a figure wrong?. That's why nothing writes itself. The review node. halts the run and hands it back to you.. def ask_confirmation(state):. return interrupt({"figures": state["figures"]}). ⏸ interrupt · waiting for human confirmation. helios-q3 · margin 91% · confidence 0.41. That 91% doesn't match the sector. Flagged, not saved.. fix it to 19 and carry on. agent.invoke(Command(resume={"margin": 19})). resumed from checkpoint · step 3 of 4. good, run it over all 38. agent.stream(batch, config). 38/38 · 35 automatic · 3 flagged for review. 6 min 12 s · 0.42 USD in tokens. Four hours of work in six minutes, and the three. doubtful cases are flagged, not buried.

The tools you will build with:

  • Python
  • FastAPI
  • PostgreSQL
  • LangChain
  • LangGraph
  • n8n
  • Docker
  • Apache Airflow

Beyond the tutorial

Start where you are

A path for every moment: organize what you know, get to production, or prepare for the interview.

  1. Courses and ecosystems

    You already code. You need an order to get to AI.

    The open ecosystems: guides from beginner to production, also from your AI assistant.

    At your own pace, come and go as you like.

    Explore the catalog
  2. Bootcamps

    From using AI to building products with AI.

    The same syllabus in two formats: a dated cohort, or individual with a 1:1 hour every week.

    In a group we meet live every week; individually the hour is yours alone.

    See individual bootcampsSee group bootcamps
  3. Technical interviews

    Practice your technical interview with AI, in English or Spanish.

    Technical interviews with an AI interviewer, on what you already study, with a report scored by criterion.

    By packs, no subscription: you use them when it's time to prepare.

    Start practicing

Bootcamps

Learn to take what you build with AI all the way to production.

In a group or 1:1, with real projects from start to finish.

In a group

Live classes every week, with a cohort that starts the same day you do.

See group bootcamps

1:1

The same syllabus, with one individual session every week at a time we agree on.

See 1:1 bootcamps

Open catalog

Complete ecosystems, open end to end

Each ecosystem orders the guides from beginner to production, built from what real job postings actually ask for.

These are the ecosystems available today:

By the numbers

6,917 developers have signed up for NIEVA.

14 open ecosystems, live workshops every week, and AI technical interviews in English and Spanish.

5 verified reviews