Viktoria Semaan
Beyond Prompting: Building Scalable AI with Multi-Agent Systems and MCP
#1about 4 minutes
Understanding LLMs, context windows, and RAG
Large language models use tokens to process text, but their limited context window requires retrieval-augmented generation (RAG) to access large or real-time datasets.
#2about 3 minutes
Transitioning from monolithic agents to multi-agent systems
Giving a single LLM agent too many tools leads to confusion and failure, so a multi-agent architecture with specialized agents improves performance and scalability.
#3about 3 minutes
Why AI projects fail and the need for evaluation
Most AI proofs-of-concept fail in production due to a lack of business context, highlighting the need for robust evaluation frameworks like MLflow.
#4about 4 minutes
Demo: Evaluating an agent's RAG tool using MLflow
A practical demonstration shows how to use MLflow with custom metrics like relevance and specificity to identify and fix agent hallucinations in a RAG tool.
#5about 3 minutes
Introducing the Model Context Protocol for tool integration
The Model Context Protocol (MCP) standardizes how agents connect to tools, creating a reusable ecosystem of servers and clients to avoid redundant integration work.
#6about 6 minutes
Demo: Automating workflows with MCP servers and clients
This demo showcases connecting local files, GitHub, and Databricks Genie as MCP servers to a client, enabling complex, automated workflows from a single chat interface.
#7about 2 minutes
Exploring the current limitations and future of MCP
The current challenges for MCP include tool discovery, agent confusion from overlapping server functions, and the lack of a centralized security gateway.
Related jobs
Jobs that call for the skills explored in this talk.
Matching moments
22:52 MIN
The future of AI protocols and agent ecosystems
From A2A to MCP: How AI’s “Brains” are Connecting to “Arms and Legs”
14:42 MIN
Using the Model Context Protocol for AI agent integration
How to scrape modern websites to feed AI agents
02:48 MIN
Tracing the evolution from LLMs to agentic AI
Exploring LLMs across clouds
32:29 MIN
Future outlook on AI agents and open standards
Exploring AI: Opportunities and Risks in Development
00:05 MIN
The core challenge of scaling AI agent communication
Event-Driven Architecture: Breaking Conversational Barriers with Distributed AI Agents
08:28 MIN
A practical demo of an agent using multiple tools
From A2A to MCP: How AI’s “Brains” are Connecting to “Arms and Legs”
04:24 MIN
How Model Context Protocol standardizes tool integration
From A2A to MCP: How AI’s “Brains” are Connecting to “Arms and Legs”
02:57 MIN
Understanding the model context protocol for AI applications
WeAreDevelopers LIVE: What's happening to React?, All-in-one editors, Fireships and Firebases & more
Featured Partners
Related Videos
24:12From A2A to MCP: How AI’s “Brains” are Connecting to “Arms and Legs”
Brad Axen
24:22Beyond Chatbots: How to build Agentic AI systems
Philipp Schmid
26:35Agentic AI - From Theory to Practice: Developing Multi-Agent AI Systems on Azure
Ricardo
29:03On a Secret Mission: Developing AI Agents
Jörg Neumann
23:17MCP Mashups: How AI Agents are Reviving the Programmable Web
Angie Jones
39:11Agents for the Sake of Happiness
Thomas Dohmke
23:33Azure AI Foundry for Developers: Open Tools, Scalable Agents, Real Impact
Oliver Will
23:39Building Blocks for Agentic Solutions in your Enterprise
Dennis Zielke & Rene Pajta
From learning to earning
Jobs that call for the skills explored in this talk.
Artificial Intelligence (AI), Agents & Copilot Architect
Techem Messtechnik GmbH
Remote
€52K
API
Azure
Redis
+5
(Senior) Conversational AI Architect
MUUUH! GmbH
Senior
REST
Data analysis
Microsoft Office
Amazon Web Services (AWS)
Software Developer - KI-Automatisierung, Agenten, MCP, Typescript, JavaScript, Prompt Engineering
Fichtner GmbH & Co. KG
API
REST
Python
GraphQL
JavaScript
+2
AI Engineer / Machine Learning Engineer / KI-Entwickler - Schwerpunkt Cloud & MLOps
Agenda GmbH
Intermediate
API
Azure
Python
Docker
PyTorch
+9