Agentic Mesh with Eric Broda

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.