Skip to main content
Software Engineering Daily

Agentic Mesh with Eric Broda

47 min episode · 2 min read
·
Eric Broda

Episode

47 min

Read time

2 min

Topics

Productivity, Health & Wellness, Remote Work

AI-Generated Summary

Key Takeaways

  • Enterprise Readiness Gap: Agents fail to reach production because they lack security, observability, traceability, and explainability — capabilities every enterprise application already requires. Data scientists building proofs-of-concept often lack enterprise architecture knowledge. Treat agent deployment like any production system: it must pass security, operations, and architecture review gates before going live.
  • Event-Driven Architecture for Agent Communication: Use Kafka or event streaming backbones instead of HTTP or gRPC for agent-to-agent communication. Publish-subscribe models provide consistent naming spaces, eliminate complex network configuration, enable state replay for error recovery, and support long-running distributed conversations — capabilities request-response HTTP cannot deliver at enterprise scale.
  • Agent Explainability Logging: Log each agent's task plan — how it decomposes a request, which sub-agents it selects, and which parameters it passes — before execution. Comparing this explainability log against the observability log reveals whether agents did what they planned, enabling richer testing and auditability beyond traditional structured logging alone.
  • Know Your Agent (KYA) Trust Framework: Assign every agent a persistent identity, then layer on permissions, roles, and task-plan logging. Model governance after Underwriters Laboratory certification: federated, third-party-accredited verification that an agent behaves as specified. This mirrors HR onboarding practices and becomes mandatory when enterprises run hundreds of thousands of agents simultaneously.
  • Agentic Process Automation over Cost-Cutting: Deploy agents to make existing employees ten times more efficient rather than replacing headcount. Compliance document processing — normalizing PDFs, emails, and spreadsheets from hundreds of counterparties — is the current highest-ROI use case. Organizations that use agents to enter new markets and retain institutional knowledge outperform those focused purely on labor cost reduction.

What It Covers

Eric Broda, coauthor of the O'Reilly book *Agentic Mesh*, explains why enterprises fail to move AI agents from lab to production, covering distributed computing principles, agent trust frameworks, explainability logging, event-driven communication via Kafka, and the emerging concept of agentic process automation replacing traditional RPA systems.

Key Questions Answered

  • Enterprise Readiness Gap: Agents fail to reach production because they lack security, observability, traceability, and explainability — capabilities every enterprise application already requires. Data scientists building proofs-of-concept often lack enterprise architecture knowledge. Treat agent deployment like any production system: it must pass security, operations, and architecture review gates before going live.
  • Event-Driven Architecture for Agent Communication: Use Kafka or event streaming backbones instead of HTTP or gRPC for agent-to-agent communication. Publish-subscribe models provide consistent naming spaces, eliminate complex network configuration, enable state replay for error recovery, and support long-running distributed conversations — capabilities request-response HTTP cannot deliver at enterprise scale.
  • Agent Explainability Logging: Log each agent's task plan — how it decomposes a request, which sub-agents it selects, and which parameters it passes — before execution. Comparing this explainability log against the observability log reveals whether agents did what they planned, enabling richer testing and auditability beyond traditional structured logging alone.
  • Know Your Agent (KYA) Trust Framework: Assign every agent a persistent identity, then layer on permissions, roles, and task-plan logging. Model governance after Underwriters Laboratory certification: federated, third-party-accredited verification that an agent behaves as specified. This mirrors HR onboarding practices and becomes mandatory when enterprises run hundreds of thousands of agents simultaneously.
  • Agentic Process Automation over Cost-Cutting: Deploy agents to make existing employees ten times more efficient rather than replacing headcount. Compliance document processing — normalizing PDFs, emails, and spreadsheets from hundreds of counterparties — is the current highest-ROI use case. Organizations that use agents to enter new markets and retain institutional knowledge outperform those focused purely on labor cost reduction.

Notable Moment

Broda argues that enterprises treating agent adoption as a cost-reduction play will become laggards. The organizations that win will use agents to augment existing staff, turning average employees into ten-times-more-productive contributors while retaining institutional knowledge that departing human workers would otherwise take with them.

Know someone who'd find this useful?

Episode Transcript

AI agents are evolving from individual productivity tools into distributed systems components inside enterprises. The next frontier is coming into focus, and it involves large scale ecosystems of collaborating agents embedded directly into business processes. However, multi agent architectures introduce serious challenges around orchestration, state management, trust, governance, and observability. Eric Broda is a veteran of the software industry, and he's the coauthor of the new O'Reilly book, Agentic Mesh, the Gen AI Powered Autonomous Agent Ecosystem. In this episode, Eric joined Sean Falconer to discuss the architectural challenges of deploying agents as core infrastructure, how distributed computing principles apply to multi agent systems, why trust and explainability are foundational, and what enterprises may look like as agents become full participants in business processes. This episode is hosted by Sean Falconer. Check the show notes for more information on Sean's work and where to find him. Eric, welcome to the show. Well, Sean, it's great to be here. Thanks for having me. Yeah. Thanks so much for being here. So I want to start off. You you wrote a great book, The Gen AI Powered Autonomous Agent Ecosystem. Now you mentioned me as the author. I'm just gonna point out a very quick thing here. I had the pleasure of actually writing this book with my son. So this is a father son team. Davis Broda and Eric Broda were the authors. And we're absolutely pleased that it's coming out in the March. Oh, that's amazing. Yeah. Sorry for for, missing that. I I knew that you coauthored it with another Broda, but I wasn't sure. I realized I didn't realize it was your son. That's great. I've actually been lately, one of my fun things I've been doing with my son, who's only five, so it'd be incredible if we wrote a book together, but has been I've been taking his ideas and using quad code to implement games based on his ideas that that he then gets to play. So lots of things coming. Father, sons working together, you know, agents at all. It's all coming together now. Well, it's kind of funny you mentioned that because I think the times, as they say, as Bob Dylan said, times they are a change and the speed of change is incredible. Whether it's codex, Claude Code with your son, we're using them obviously on a daily basis. The things are changing so rapidly that this is truly exciting times. And I think the book is perhaps at the right place at the right time right now. Yeah. Well, I'm kinda curious about why why a book, you know, given that things are changing so fast. Like, literally, the entire, like, developer experience has shifted in the last, like, two to four months alone. So is it old news by the time something like a book comes out? Yeah. Well, that's a great question. It's kind of funny because, I was talking I was on a podcast with Joe Rice. …

Get the full transcript (8,890 words) + summary by email — free

One-time email with the complete transcript and AI summary of this episode. No account needed.

One email, no spam. We’ll also show you what SignalCast does.

Browse all Software Engineering Daily transcripts →

You just read a 3-minute summary of a 44-minute episode.

Get Software Engineering Daily summarized like this every Monday — plus up to 2 more podcasts, free.

Pick Your Podcasts — Free

Keep Reading

Books, tools, and gear mentioned in this episode

SignalCast may earn commission on purchases via these links. As an Amazon Associate, SignalCast earns from qualifying purchases.

Books

Tools

  • KafkaRecommended
    Use Kafka or event streaming backbones instead of HTTP or gRPC for agent-to-agent communication. Publish-subscribe models provide consistent naming spaces, eliminate complex network configuration, enable state replay for error recovery

More from Software Engineering Daily

We summarize every new episode. Want them in your inbox?

Similar Episodes

Related episodes from other podcasts

Explore Related Topics

This podcast is featured in Best Cybersecurity Podcasts (2026) — ranked and reviewed with AI summaries.

Read this week's Health & Longevity Podcast Insights — cross-podcast analysis updated weekly.

You're clearly into Software Engineering Daily.

Every Monday, we deliver AI summaries of the latest episodes from Software Engineering Daily and 192+ other podcasts. Free for one show.

Start My Monday Digest

No credit card · Unsubscribe anytime