Data Engineering Podcast

Enabling Agents In The Enterprise With A Platform Approach

44 snips
Jun 29, 2025
Arun Joseph, an AI engineering leader and entrepreneur, discusses his journey in developing multi-agent systems. He emphasizes the transformative potential of agentic capabilities in businesses and shares insights on building robust data models and orchestration loops. Arun tackles the challenges of managing large-scale data contexts, the importance of unified context management to avoid silos, and the shift toward open-source platforms like LMOS. He also explores how these innovations can enhance decision-making and streamline enterprise data management.
Ask episode
AI Snips
Chapters
Transcript
Episode notes
ANECDOTE

Arun Joseph's Background

  • Arun Joseph has extensive experience building large-scale distributed and AI systems in enterprises like Deutsche Telekom.
  • He recently transitioned to entrepreneurship focusing on multi-agent systems for agentic capabilities.
INSIGHT

Agentic Orchestration Feedback Loop

  • Agentic orchestration works as a feedback loop enabling systems to iteratively refine actions toward a goal.
  • This paradigm allows business users to specify objectives which the system autonomously executes and improves.
ADVICE

Start Simple with Existing APIs

  • Start integrating language models with existing APIs simply before adopting new protocols like MCP or A2A.
  • Build incrementally and add complex layers as scalability demands increase, following the KISS principle.
Get the Snipd Podcast app to discover more snips from this episode
Get the app