scalable/ai/agentic patterns/lesson 01 cph / /
lesson 01 / 07 · 10 min · updated ·

what are agentic patterns

the shape of the problem. why patterns, not frameworks. the four primitives you'll see in every later lesson.

the problem

most tutorials show you a single agent loop: llm → tool → llm → tool → answer. production systems rarely look like that. they look like teams — small units with narrow jobs, handing off to each other, calling into shared skill libraries, driven by a router or a plan. the pattern is the glue; the llm is just the engine.

this course is about that glue.

what a pattern is, and isn't

a pattern is a recurring shape you reach for to solve a recurring problem. for agents, patterns aren't a framework — they're closer to what "patterns" meant in the gang-of-four book: if you see this situation, reach for this shape first. no ceremony, no inheritance hierarchy — just a named shape other engineers already recognise.

three things a pattern isn't:

the four primitives

the rest of this course is built around four building blocks. treat these as the vocabulary. every pattern in later lessons is a combination of these, stacked or nested.

  1. skills a small, named capability an agent can invoke — not just a tool call, but a tool call plus the prompting, validation, and return-shape glue around it. think "book this calendar slot" or "parse this invoice". a skill is reusable across agents.
  2. extensions anything that wraps or augments the base loop: memory injection, retrieval, safety filters, telemetry, caching, retries. the pattern equivalent of middleware.
  3. personas the identity an agent takes on. a bundle of prompt, voice, allowed skills, and guardrails. swap the persona and the same underlying loop behaves completely differently.
  4. handoffs how one agent passes control to another, with just enough context to be useful without over-sharing. the most undervalued primitive — most "the agent got confused" bugs are bad handoffs in disguise.
why these four. you can reduce most agent architectures to some combination of: what can this agent do (skills), what shapes its behaviour (extensions, personas), and who takes the next turn (handoffs). that's the whole surface.

a minimal pattern, end to end

the smallest complete example: a triage agent hands off to one of two specialists. the whole thing is two personas, four skills, and a handoff.

a minimal triage → specialist handoff — click run
ready

four things to notice:

this is the shape you'll see repeated — with more personas, more skills, and smarter routers — in every real agent system worth studying.

what this course is and isn't

seven lessons. each one is a pattern, with a minimal implementation and notes on when the pattern breaks. examples are framework-agnostic typescript pseudocode — when we need something concrete (a queue, a memory store, a router) we'll name a specific tool, but the pattern itself is portable.

lesson seven is evals: how you know a pattern is actually working, not just demoing well. it's the lesson most "build an agent" courses skip, and the one you'll reach for most often once something is in production.

scalable labs·cvr 30091604·github·linkedin·hello@scalable.dk