2657 - 学生开发日：智能体应用：用例、经验教训和最佳实践.pdf

1、Orlando,FLOctober 69IBM TechXchange 2025Session 2657Andre TostIBM Distinguished EngineerIBM watsonx Client EngineeringAgentic ApplicationsUse cases,lessons learned and best practicesAgenda010203040506Level setUse casesFunctional requirementsApplication typesGovernanceBest practicesIBM TechXchange|20

2、25 IBM CorporationIBMs definitionWhat is an agent?IBM TechXchange|2025 IBM Corporation3Evolution of LLMsIBM TechXchange|2025 IBM Corporation4LLM with tools Web search Calculator Code interpreter Image generator Function callingLLM Trained knowledge base Logical thinking Problem solving Reasoning Evo

3、lution from LLMs to AgentsIBM TechXchange|2025 IBM Corporation5Agent Planning Multi-step reasoning Action taking Self-correctingAssistants Customized LLM with tools Prescriptive chains LLM with tools Web search Calculator Code interpreter Image generator Function callingLLM Trained knowledge base Lo

4、gical thinking Problem solving Reasoning Basics of an Agentic System6IBM TechXchange|2025 IBM Corporation2025 IBM Corporation7An AI agent is an autonomous system that can use tools and collaborate with other agents to plan and act on tasks.After it acts,the agent reflects on the results of its actio

5、ns,learning iteratively and refining its approach to better align with its defined objectives.AI AgentsInput(Conversational UI or APP/Business Process)Output of executionThe Orchestrator Agent is a multi-agent,multi-tool supervisor,router,and planner,facilitating complex task executionIBM TechXchang

6、e|2025 IBM CorporationAgenda010203040506Level setUse casesFunctional requirementsApplication typesGovernanceBest practicesIBM TechXchange|2025 IBM CorporationUse CasesIBM TechXchange|2025 IBM Corporation9Mainframe&Data Platform ModernizationDigital LaborCustomer CareAI GovernanceEmbedded AIZ Lakehou