Paths

Four paths, taken in order.

Each path strings courses together. Path 1 is the base every later path assumes.

  1. Path 1 of 4Start here

    LLM and Agent Foundations

    Start here: how language models work inside, what an agent really is, and how to build one on Claude and eve.

    3 courses21 lessons~56h

    Open the path
    1. 1LLMs for EngineersHow large language models are built, trained and run, so you can reason about their behaviour, cost and failure modes in production.
    2. 2Agent FoundationsWhat an AI agent really is, how it uses tools and context, and how to make one dependable enough for high-stakes work.
    3. 3Building Agents with Claude and eveBuild real agents on production harnesses: Claude Code, the Claude Agent SDK and Vercel's eve, with skills, subagents and human approval built in.
  2. Path 2 of 4

    Evaluation and Optimisation

    Measure agents with numbers you can defend, then use those numbers to improve prompts, tools and models.

    2 courses13 lessons~33h

    Open the path
    1. 1Evaluating and Scoring AgentsTurn "it seems better" into numbers you can defend: error analysis, code graders, calibrated LLM judges and honest statistics.
    2. 2Prompt and Context OptimisationTreat prompts, examples, tool descriptions and skills as versioned, measured artefacts, and improve them by hand, by optimiser and in production without breaking what already works.
  3. Path 3 of 4

    Documents, Retrieval and Memory

    Turn your documents into knowledge agents can find, cite and remember: ingestion, retrieval and memory.

    3 courses24 lessons~60h

    Open the path
    1. 1Document Ingestion PipelinesTurn a case's PDFs, scans, forms and emails into verified, structured, privacy-safe data your agents and search can trust.
    2. 2Retrieval and Knowledge SystemsBuild retrieval your agents can trust over a case's documents and a company's reference library, and measure that it finds what it should.
    3. 3Agent MemoryMake agents remember the right facts about a customer and a case for weeks, keep each case's memory sealed, and prove that memory helps rather than harms.
  4. Path 4 of 4

    Production AI at Scale

    Deploy, secure, scale and pay for a fleet of agents running real work for many customers.

    4 courses29 lessons~72h

    Open the path
    1. 1Infrastructure for AgentsRun a fleet of agents in production: compute, sandboxes, durable workflows, queues, state, tenant isolation, gateways and safe delivery.
    2. 2Production Agent SystemsTake an agent from working demo to a system you can run for months: architecture, security, compliance, observability and safe change.
    3. 3Scaling AI SystemsKeep a fleet of agents fast and available under real load: rate limits, flow control, retries, backpressure, caching, failover, latency budgets, load tests and capacity plans.
    4. 4LLM Cost EngineeringKnow what each case costs in tokens, then cut that cost with caching, trimming, batching, routing, distillation and self-hosting, without losing quality.

Plus an elective outside the paths: System One Models with Jev.

Catalogue

Every course.

95 lessons ~237h

Setup guides

All guides

Set up once, use in every course.

For teams

Want this for your team?

We started by teaching people to code. Today we coach engineers and leaders, and help companies build the teams and processes that ship.

Coaching & team setup

Coders In Hoods Academy

Sign in to start learning

Free, no card. We use your account to save progress, quiz scores, bookmarks and occasionally send updates from our team.