A hands-on school for Agentic AI

Don't just read about agents. Build them.

AgentSwarms is an interactive playground for Agentic AI enthusiasts. Learn RAG, tool use, guardrails, and multi-agent swarms by running real demos — with guided lessons baked into every click.

6
core lessons
5+
live demo agents
0
setup required
Curriculum

Six lessons. From "what's an agent?" to "I shipped a swarm."

Every lesson is interactive. You read a concept, then run a live agent that demonstrates it — prompts and all.

Lesson 01

Prompts & System Messages

Learn how an agent's personality, role, and constraints are shaped by the system prompt. See the same model behave like a teacher, a lawyer, or a sarcastic pirate — just by changing words.

  • Anatomy of a great system prompt
  • Few-shot vs zero-shot patterns
  • How temperature changes creativity vs accuracy
Read the full lesson
Lesson 02

RAG & Knowledge Bases

Watch a generic chatbot transform into a domain expert by grounding its answers in your documents. Real citations, real docs, no hallucinations.

  • Why retrieval beats fine-tuning for facts
  • Chunking, embeddings, and citations
  • When RAG fails — and how to detect it
Read the full lesson
Lesson 03

Tools & Function Calling

Give your agent superpowers. Connect it to APIs, MCP servers, and webhooks so it can actually do things — fetch data, send emails, run SQL.

  • OpenAI tool-call schema, plain English
  • MCP servers in 5 minutes
  • Designing safe, idempotent tools
Read the full lesson
Lesson 04

Guardrails & HITL

Production agents need brakes. Add input/output filters, PII detection, content safety, and human-in-the-loop approvals for risky actions.

  • PII redaction and prompt-injection defense
  • Approval inboxes for high-risk actions
  • Cost & rate-limit guardrails
Read the full lesson
Lesson 05

Multi-Agent Swarms

One agent is a worker. A swarm is a team. Build researcher → writer → reviewer pipelines with explicit handoffs and shared memory.

  • Orchestrator vs peer-to-peer patterns
  • Routing and handoff messages
  • When to split an agent into a swarm
Read the full lesson
Lesson 06

Observability & Evals

If you can't trace it, you can't trust it. Inspect every token, tool call, and dollar spent — and learn how to evaluate agent quality systematically.

  • Reading execution traces like a pro
  • Token, latency & cost dashboards
  • Building your first eval suite
Read the full lesson
How it works

Learn by doing, in four steps

No installs. No API keys to start. Open a demo, follow the guided prompts, then make it your own.

01

Try a Live Demo

Start with the Templates gallery. Click any template — Product Support, Research Assistant, Code Reviewer — and a fully working agent is provisioned for you in seconds.

02

Follow the Guided Tour

Each demo opens in the Playground with a side-panel lesson. Suggested prompts walk you through RAG, guardrails, and approvals one checkpoint at a time.

03

Fork & Experiment

Tweak the system prompt, swap models (Lovable AI, OpenAI, Gemini, Grok, Claude…), wire up your own knowledge base. Break things — that's how you learn.

04

Build Your Own

Apply what you learned. Compose your own agents, chain them into a swarm, and watch your traces light up in the observability dashboard.

Cheat sheet

The Agentic AI vocabulary, demystified

Every term you'll hear in agent papers, blog posts, and Twitter threads — explained in one line.

Agent
An LLM with a system prompt, optional tools, and memory — capable of multi-step reasoning toward a goal.
RAG
Retrieval-Augmented Generation. Inject relevant chunks from your docs into the prompt so the model can cite real sources.
Tool / Function call
A typed action the model can invoke (search_web, send_email, query_db). The agent decides when to call it.
Guardrail
Rules that filter input or output — PII redaction, profanity blocks, schema validation, cost caps.
HITL
Human-in-the-Loop. The agent pauses for human approval before doing something risky (refunds, deletes, sends).
MCP
Model Context Protocol. A standard way to expose tools and data sources to any compatible agent.
Swarm
Multiple specialized agents that hand off work to each other — researcher → writer → reviewer.
Eval
A test suite for agents. Score outputs on accuracy, format, safety, cost — not just vibes.

Your first agent is 60 seconds away

Sign up free, pick a template, and start the guided tour. By the end of the day you'll understand what makes agents tick — and you'll have built one yourself.