Agentic systems: ReAct, planning and multi-agent patterns

Function calling gives a model one tool call per turn. An agentic system goes further: the model runs in a loop, choosing what to do next after seeing the result of its last action, until it decides the goal is complete. This turns a language model from a responder into a problem-solver. But loops without guardrails spin forever, and agents that can call real APIs can cause real damage. This lesson covers the architecture, the main reasoning pattern (ReAct), and how to build multi-agent systems that stay under control.

Full content is available with a subscription.
Get full access to all courses on the platform for one year with a single payment.
Unlike other platforms that charge per course, here you get everything for one price, and after one year of use there will be no automatic charge for the following year.