A candid look at turning AI hype into production results, told through the lens of Prakhar Srivastava, our newest recruit on the Enterprise Architecture team at SnapLogic. Over the years, Prakhar has been a practitioner, a consultant, and a vendor, and shares perspectives from each of those roles. We map lessons from SOA and APIs to agentic AI, and show how governance, data fabric, and empathy drive real outcomes in complex, regulated environments, using Prakhar's experience in the airline industry as a guide.

• three lenses on enterprise architecture and value
• composable enterprise as an AI readiness strategy
• agents as APIs with memory and similar pitfalls
• need for gateways, meshes, and security guardrails
• four risks to manage: governance, interoperability, trust, security
• data as water and the role of a fabric
• crawl‑walk‑run roadmap from use case to production
• outsourcing lessons and knowledge repatriation
• retraining, drift, and resilient deployments
• empathy and partnering over hard selling

We explore how embedded AI in SaaS tools amplifies sprawl and risk, and outline a practical path to governed, composable, cross‑platform agents. Chris Ward shares real use cases for Customer 360 and finance reconciliation, plus metrics, onboarding and versioning that keep AI accountable.

The LinkedIn post that kicked everything off

More details on the finance use case Chris discussed

SnapLogic's own support for MCP

Composable architecture isn’t a buzzword; it’s the overdue upgrade to lessons we learned the hard way in the SOA era. We share a pragmatic path from heavyweight standards and ESB monocultures to API-first, domain-driven systems that actually deliver reuse, speed, and resilience across cloud and on-prem. With guest Brad Drysdale, we map the shift from monoliths to distributed services, the rise of REST and gateways, and why a discovery-led mindset matters more than any protocol.

We dig into the techniques that make composability real: treat API contracts as products in their own right, with owners, roadmaps, and strong versioning; build a living catalogue that developers can trust; and use domain-driven design to create bounded contexts that align services to business language. We talk openly about governance debt, API sprawl, and the trap of point-to-point integrations disguised as microservices. Then we connect the dots to modern DevOps — Kubernetes, Terraform, and infrastructure as code — showing how to run heterogeneous, multi-cloud estates without drowning in complexity.

Now AI raises the stakes. Agents need secure, reliable access to knowledge and tools; contracts machines can interpret; and guardrails that earn trust. We compare REST and OpenAPI to emerging agent-to-agent standards like MCP, and explain why the future likely builds on today’s contracts rather than replacing them. Finally, we explore vibe coding’s next act: vibe orchestration, mapping intent to capabilities letting AI assemble outcomes from a curated service catalogue. The takeaway is simple: composability scales when you fund shared capabilities, measure adoption, and make reuse the default.

If this sparked ideas for your stack or strategy, follow the show, share it with a colleague, and get in touch with your questions and suggestions. Your stories and challenges shape what we explore next.