Dennis Zielke, Manuel Schettler

Composable Intelligence: How Henkel and Microsoft Are Shaping the Agent Ecosystem

Standard chatbots can't tell the difference between gluing an airplane and paper. See how Henkel built a composable agent ecosystem that can.

Composable Intelligence: How Henkel and Microsoft Are Shaping the Agent Ecosystem
#1about 5 minutes

Understanding Henkel's need for AI agent behavior

The vast scale of Henkel's product catalog across global markets creates complex knowledge management challenges that AI agents can help solve.

#2about 2 minutes

Differentiating AI agents from traditional chatbots

AI agents are defined by their ability to make semi-autonomous decisions, decompose problems, and proactively use memory and tools, unlike reactive chatbots.

#3about 2 minutes

How Henkel and Microsoft collaborate on AI innovation

The partnership combines Microsoft's technology push with Henkel's market pull to identify valuable business problems and co-develop innovative AI solutions.

#4about 3 minutes

Core principles for building a composable agent platform

The platform is built on principles of governed autonomy, composability, distributed architecture, and open standards to ensure flexibility and scalability.

#5about 4 minutes

Exploring the layered architecture of the RAQN platform

The RAQN platform architecture consists of a cloud foundation, core building blocks like workflow and memory, and an enablement layer focused on developer experience.

#6about 2 minutes

Overcoming challenges with context and complex data

Building effective agents requires moving beyond simple prompt engineering to systems that can integrate structured and unstructured data using knowledge graphs and memory.

#7about 2 minutes

Using open standards for agent interoperability

Open protocols like MCP for data, A2A for communication, and OIDC for identity are crucial for creating a discoverable and interoperable ecosystem of agents.

#8about 5 minutes

Applying distributed systems principles to AI agents

Proven software engineering practices like the 12-factor app methodology and resiliency patterns are adapted to build robust and scalable agent-based systems.

#9about 1 minute

Key learnings on data, frameworks, and user adoption

The primary challenges in deploying agent solutions are overcoming poor data quality, navigating immature frameworks, and aligning advanced capabilities with user expectations.

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

Featured Partners

Related Videos

Building Blocks for Agentic Solutions in your Enterprise23:39

Building Blocks for Agentic Solutions in your Enterprise

Dennis Zielke, Rene Pajta

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

On a Secret Mission: Developing AI Agents29:03

On a Secret Mission: Developing AI Agents

Jörg Neumann

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

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

AI in Action: Real Use Cases with Real Impact - Hanna Hennig, Michael Ameling, Tobias Regenfuss29:00

AI in Action: Real Use Cases with Real Impact - Hanna Hennig, Michael Ameling, Tobias Regenfuss

Hanna Hennig, Michael Ameling, Tobias Regenfuss and Mike Butcher

Beyond Prompting: Building Scalable AI with Multi-Agent Systems and MCP25:32

Beyond Prompting: Building Scalable AI with Multi-Agent Systems and MCP

Viktoria Semaan

From learning to earning

Jobs that call for the skills explored in this talk.