Find your next step

Start exploring

ComparisonsAI tool comparisons

Compare voice-agent platforms and managed versus custom architectures.

BriefingThis week in AI

Dated AI briefing on models, agents, NVIDIA, and robotics.

ModelsNemotron 3.5 Bolt E4B 4GB

NVIDIA released an open small language model aimed at fast conversational agents with a compact memory footprint.

Developer toolsNVIDIA’s local AI stack

NVIDIA’s GTC Berlin update covers local agents, DGX Spark updates, model support, and robotics workflows.

RoboticsMicroduck

The small duck-like robot is a programmable biped for reinforcement learning and simulation-to-real experiments.

Skip to content

AI Application Developer

Learn to build, evaluate, and explain useful applications powered by language models.

Work on the application layer: connect models to data, design useful workflows, and check their reliability.

Explore the first stage

Your learning roadmap

Connect each skill to something you can demonstrate.

  1. 1

    Programming foundations

    Get comfortable with Python, HTTP, and Git. Build a small script that reads a file and handles missing input.

    PythonHTTPGit
    Start with loading a document
  2. 2

    Models and prompting

    Practice clear instructions, output formats, context, and limitations before adding application complexity.

    PromptingStructured outputsLimitations
    Learn: Prompt Engineering Foundations
  3. 3

    Retrieval and evaluation

    Connect a model to source passages and check whether its answers are supported.

    RetrievalCitationsEvaluation
    Explore: Build a document assistant
  4. 4

    Ship a portfolio project

    Document setup, limitations, evaluation failures, and trade-offs. Make your demo reproducible without sharing credentials.

    DocumentationTestingTrade-offs
    Prepare your portfolio deliverables