Skip to main content

The Agentic AI Hub

A software engineer's complete reference to AI, from foundations to agents.

Find your path Start reading

New to AI?

Four questions to start with, foundation first. Already past the basics? Skip ahead.

I'm new to all this. Where do I start? Which model should I actually use? How do I build my own agent? How do I keep up without drowning?

Find your level.

Every developer is somewhere on this ladder, from AI as fancy autocomplete (L0) to software that builds itself (L5). Each level up changes what your job is day to day. Find the one that sounds like your workweek, then climb one rung. Every rung links the chapters that unlock it. The framework comes from Dan Shapiro. The full version, along with a per-task autonomy dial, is in Levels of AI Adoption.

  1. L0: Manual

    The ground floor: AI as a search engine and occasional tab-complete. No real productivity change.

    Everyone starts here. There's nothing to unlock yet.

  2. L1: Discrete task offloading

    You hand the AI small, self-contained jobs: write the unit tests, draft the docstring, generate one well-scoped function. The real work is still yours.

    Chat assistants · Prompting 101 · IDE assistants

    Explore path

  3. L2: Active pairing

    The AI writes alongside you all day, handling the boring parts while you steer and review everything as it lands. Shapiro estimates about 90% of AI-native developers live here.

    CLI agents · AGENTS.md & CLAUDE.md · What an agent actually is

    Explore path

  4. L3: Human-in-the-loop management

    You mostly stop typing code. Agents run several tasks at once and your day becomes reviewing their work. Most people never go past this level.

    Own the outer loop · Agentic code review · Role separation · MCP & tools

    Explore path

  5. L4: Specification-driven

    You define what to build instead of building it: write the spec, set the tests, judge the results. Leave for twelve hours and come back to a green suite.

    The harness as an artifact · Evals-as-tests · LLMOps & guardrails

    Explore path

  6. L5: The dark factory

    Agents building the software with humans out of the loop. Shapiro reports it working only for teams under five people, and calls it likely our future.

    Swarms & fleets · The factory model · Human factors

    Explore path

Build with AI.

You have something to build. Each path puts the chapters in the order that takes you from first idea to shipped.

How do I build my own agent? Can I trust what agents produce? How do I ground AI in my company's data? How do I ship an AI feature to production? Can I run models myself? What's out there beyond text?

Keep up.

Part of this handbook will be stale by the time you finish it. These paths set up a small routine that keeps you current anyway.

How do I keep up without drowning? Where do I go deeper? What does this do to my career?

All 45 chapters.

Everything in the handbook, in book order. The paths above are the shortcuts; this is the whole territory.

Foundations Models, Labs & Benchmarks Tools, Products & Agents Building with AI: The Engineering Stack Working with AI: Techniques, Workflows & Adoption Ecosystem & Staying Current Appendices

"The Agentic AI Hub" is published by daily.dev under the CC BY 4.0 license.