Se rendre au contenu

Generative AI & LLMs for Builders

Our flagship, hands-on bootcamp for building with Generative AI. Understand how LLMs work, master prompt engineering, build chatbots and copilots on the Claude & GPT APIs, ship RAG pipelines and AI agents, and deploy a production GenAI app as your capstone. Certification on completion.

IA générative Intelligence artificielle Avancé Ingénierie des Prompts
  • 8 leçons
  • Mis Ă  jour 05/09/2026
1 déjà inscrit
DĂ©tails du cours
Cours privé
Veuillez se connecter pour demander l'accès
Terminé
0 %

avatar
Par Administrator

Contenu du cours

AI agents & tool use

Préc Suivant
Plein Ă©cran Partager

From answering to acting

An agent is an LLM given tools (functions/APIs) and a goal. It decides which tool to call, reads the result, and loops until the task is done.

The agent loop

  1. Model receives a goal + the tools available.
  2. It chooses a tool and arguments.
  3. Your code runs the tool and returns the result.
  4. The model incorporates it and continues — or finishes.

Examples of tools

  • Web search, database queries, sending email.
  • Running code, calling internal APIs, updating records.

Building them well

Clear tool descriptions, guardrails on destructive actions, timeouts/retries, and observability. Start with one or two tools before going autonomous.

Takeaway: tools turn a chatbot into a system that gets real work done.

Évaluation
0 0

Il n'y a aucune réaction pour le moment.