Episode

The Hidden Problem with AI Agents: Too Much LLM, Not Enough Engineering with Karthikeyan VK (MVP)

Podcast
M365.FM - Modern work, security, and productivity with Microsoft 365
Published
May 21, 2026
Duration seconds
2984
Processing state
not_requested
Canonical source
https://www.spreaker.com/episode/the-hidden-problem-with-ai-agents-too-much-llm-not-enough-engineering-with-karthikeyan-vk-mvp--72081356
Audio
https://dts.podtrac.com/redirect.mp3/api.spreaker.com/download/episode/72081356/the_hidden_problem_with_ai_agents_too_much_llm_not_enough_engineering_with_karthikeyan_vk_mvp.mp3
JSON
/v1/public/podcasts/m365-fm-modern-work-security-and-productivity-with-microsoft-365-7311214/episodes/the-hidden-problem-with-ai-agents-too-much-llm-not-enough-engineering-with-karthikeyan-vk-mvp
Markdown
/podcast/m365-fm-modern-work-security-and-productivity-with-microsoft-365-7311214/the-hidden-problem-with-ai-agents-too-much-llm-not-enough-engineering-with-karthikeyan-vk-mvp.md

Actions

  • POST https://stenobird.com/v1/public/podcasts/m365-fm-modern-work-security-and-productivity-with-microsoft-365-7311214/episodes/the-hidden-problem-with-ai-agents-too-much-llm-not-enough-engineering-with-karthikeyan-vk-mvp/transcription-requests
    Idempotently request low-priority transcript generation for this episode.
  • GET https://stenobird.com/podcast/m365-fm-modern-work-security-and-productivity-with-microsoft-365-7311214/the-hidden-problem-with-ai-agents-too-much-llm-not-enough-engineering-with-karthikeyan-vk-mvp.md
    Read the agent-friendly Markdown representation of this episode resource.

Summary

Artificial Intelligence is moving faster than almost any technology wave we have seen before. Every week brings new models, new copilots, new frameworks, new AI agents, and endless promises about autonomous systems replacing repetitive work across the enterprise. But beneath all the hype lies a deeper engineering problem. Too many organizations are building AI systems with Large Language Models at the center of everything — while completely ignoring architecture, orchestration, state management, observability, governance, and deterministic engineering principles. In this episode of the m365.fm podcast, Mirko Peters sits down with Microsoft AI MVP, CTO, international speaker, and author Karthikeyan VK to discuss one of the most important realities of enterprise AI today: why most AI agent architectures are fundamentally flawed from an engineering perspective. This conversation goes far beyond AI hype and dives deep into what actually matters when building scalable, reliable, enterprise-grade AI systems with Microsoft Azure AI Foundry, orchestration patterns, memory management, evaluation pipelines, multi-agent architectures, and domain-specific AI solutions. WHY MOST AI AGENTS ARE BUILT WRONG According to Karthikeyan, one of the biggest mistakes organizations make today is trying to use Large Language Models for everything. Instead of treating the LLM as a reasoning engine or orchestration layer, many teams try to make the model itself perform every business operation directly. The result is often a probabilistic system attempting to replace deterministic engineering. And that creates serious reliability problems. Karthikeyan explains that enterprise systems cannot behave unpredictably. If an AI system returns different results for the same financial transaction, custom…