Accéder au contenu principal

Cours

Google: Optimize Agent Behavior

Intermédiaire2 h

Turn a basic AI agent into a sophisticated assistant using advanced instructions, model selection, planning capabilities, and structured output.

R2 h19 exercices950 XP151Attestation de réussite

Créez votre compte gratuit

Continuer avec Google
ou
En continuant, vous acceptez notre conditions d'utilisation, nos politique de confidentialité et que vos données soient stockées aux États-Unis.

Plébiscité par les apprenants de milliers d'entreprises

Vous formez une équipe ?

Essayer pour les entreprises

Description du cours

You’ve built your first agent—now it’s time to take it further. In this course, you’ll advance your skills by learning how to turn a basic AI agent into a sophisticated, precise assistant—applying advanced instructions, model selection, planning capabilities, and structured output patterns. Join the community forum for questions and discussions

Prérequis

Ce cours ne requiert aucun prérequis.

Programme de formation

Plan du cours

1

Advanced instruction writing

This module transforms basic instructions into professional agent guidance systems. You’ll learn structured patterns for defining agent persona, role, boundaries, and communication style—turning simple prompts into sophisticated behavioral frameworks grounded in ADK best practices.
Commencer le chapitre
2

Structured output

This module transforms unpredictable text responses into reliable, structured JSON output that systems can parse and use. You’ll learn how to use Pydantic schemas to enforce output format, making your agents production-ready for integration with applications, databases, and workflows.
Commencer le chapitre
3

Choosing and configuring models

This module empowers you to strategically select models and configure generation parameters for optimal performance. You’ll learn when to use Flash versus Pro models, how to set safety thresholds, and how to fine-tune temperature and token limits—transforming basic agents into production-optimized systems.
Commencer le chapitre
4

Planning for complex tasks

This module adds multi-step reasoning to your agents, transforming them from reactive responders into thoughtful problem-solvers. You’ll learn how to enable Gemini’s built-in thinking capabilities using BuiltInPlanner, allowing agents to plan their approach before executing—essential for complex, multi-step tasks.
Commencer le chapitre
5

Reading List

Reading List
Commencer le chapitre
R

Google: Optimize Agent Behavior

Cours
terminé

Obtenez un certificat de réussite

S'inscrire maintenant

Développez vos compétences en données avec DataCamp for Mobile

Progressez où que vous soyez grâce à nos cours mobiles et à nos défis de code quotidiens de 5 minutes.