Jörg Neumann

On a Secret Mission: Developing AI Agents

Building powerful AI agent teams is simpler than you think. It's about knowing the right architectural patterns, not just mastering complex APIs.

On a Secret Mission: Developing AI Agents
#1about 5 minutes

The evolution from chatbots to autonomous AI agents

AI agents represent a shift from simple chatbots by operating independently based on triggers and using data, tools, and memory.

#2about 5 minutes

Exploring OpenAI's built-in tools and APIs

OpenAI provides powerful built-in tools like Code Interpreter and Web Search, supported by an evolving set of APIs for agent development.

#3about 4 minutes

Getting started with the OpenAI Agents SDK

The Agents SDK simplifies development by providing a clear structure for defining an agent, its instructions, and running it synchronously or asynchronously.

#4about 2 minutes

Integrating custom Python functions as agent tools

The Agents SDK allows you to easily extend an agent's capabilities by decorating a standard Python function and assigning it as a tool.

#5about 2 minutes

Using built-in tools like web search

Agents can be equipped with pre-built functionalities like the web search tool to access and process up-to-date information from the internet.

#6about 1 minute

Managing conversational history in agent interactions

Maintain context across multiple turns in a conversation by collecting the message history and passing it as a chained list to the agent.

#7about 3 minutes

Routing tasks with the handoff workflow pattern

The handoff pattern uses a central triage agent to analyze a request and delegate it to the most appropriate specialized agent in a team.

#8about 3 minutes

Building cross-functional collaborative agent teams

Create a collaborative team where a primary agent orchestrates complex tasks by using other specialized agents as callable tools.

#9about 3 minutes

Implementing guardrails to control agent behavior

Guardrails act as programmable input or output filters that check agent messages against predefined rules to ensure safe and appropriate responses.

#10about 1 minute

The conceptual shift in modern AI development

Building effective AI agents is less about mastering complex APIs and more about applying the right architectural concepts and patterns.

Related jobs
Jobs that call for the skills explored in this talk.

Featured Partners

Related Videos

Beyond Chatbots: How to build Agentic AI systems24:22

Beyond Chatbots: How to build Agentic AI systems

Philipp Schmid

Agents for the Sake of Happiness39:11

Agents for the Sake of Happiness

Thomas Dohmke

From A2A to MCP: How AI’s “Brains” are Connecting to “Arms and Legs”24:12

From A2A to MCP: How AI’s “Brains” are Connecting to “Arms and Legs”

Brad Axen

Azure AI Foundry for Developers: Open Tools, Scalable Agents, Real Impact23:33

Azure AI Foundry for Developers: Open Tools, Scalable Agents, Real Impact

Oliver Will

Agentic AI - From Theory to Practice: Developing Multi-Agent AI Systems on Azure26:35

Agentic AI - From Theory to Practice: Developing Multi-Agent AI Systems on Azure

Ricardo

Agentic AI Systems for Critical Workloads30:01

Agentic AI Systems for Critical Workloads

Mario Fusco

Building Blocks for Agentic Solutions in your Enterprise23:39

Building Blocks for Agentic Solutions in your Enterprise

Dennis Zielke, Rene Pajta

Rethinking Workflows in the Agentic Era27:07

Rethinking Workflows in the Agentic Era

Eric Jadi, Rene Pajta

From learning to earning

Jobs that call for the skills explored in this talk.