Episode

Orchestrating agents, APIs, and MCP servers

Podcast
Practical AI
Published
Apr 14, 2025
Duration seconds
2572
Processing state
failed
Canonical source
https://share.transistor.fm/s/657d28be
Audio
https://pscrb.fm/rss/p/dts.podtrac.com/redirect.mp3/media.transistor.fm/657d28be/0b5d4eee.mp3
JSON
/v1/public/podcasts/practical-ai/episodes/orchestrating-agents-apis-and-mcp-servers
Markdown
/podcast/practical-ai/orchestrating-agents-apis-and-mcp-servers.md

Actions

  • POST https://stenobird.com/v1/public/podcasts/practical-ai/episodes/orchestrating-agents-apis-and-mcp-servers/transcription-requests
    Idempotently request low-priority transcript generation for this episode.
  • GET https://stenobird.com/podcast/practical-ai/orchestrating-agents-apis-and-mcp-servers.md
    Read the agent-friendly Markdown representation of this episode resource.

Summary

In this episode, Daniel sits down with Pavel Veller, EPAM’s Chief Technologist, to explore the practical challenges of orchestrating many AI agents and managing connections to disparate systems/tools. Pavel shares insights from his hands-on work with agentic architectures and internal tools like "DIAL". Pavel also helps us understand things like MCP servers and why connecting assistants via APIs is easy—but making them useful is hard. Featuring: Pavel Veller – LinkedIn , X Daniel Whitenack – Website , GitHub , X Links: EPAM DIAL SWE-bench results