Roadmaps
Community-curated paths to learn to code. Pick one and a squad forms around you — you finish it together, not alone.
Community-curated paths to learn to code. Pick one and a squad forms around you — you finish it together, not alone.
Design and ship AI agents: the agent loop, tool use, MCP, evaluation, and guardrails that keep autonomous systems safe. Best if you're comfortable with Python or JavaScript and have called an LLM API before.
The model-tools-loop anatomy, and when an agent beats a simple workflow.
Define tool schemas, execute calls, and return results the model can act on.
Prompt chaining, routing, parallelization, and orchestrator-worker designs.
Connect agents to data and tools through the open MCP standard.
Trace, test, and score multi-step behavior — not just single responses.
Sandboxing, permissioning, human-in-the-loop, and defending against prompt injection.
Put it together: build a working agent with an SDK and real tools.