Skip to main content
🚀 Taking AI from prototype to production?Find the architecture, GPU, security and governance gaps before they become incidents.Get an AI Readiness Assessment
Main stage session at PlatformCon London 2026 on the IDP reference architecture for agentic AI
Platform Engineering

Your IDP Is the Foundation for Agentic AI

A PlatformCon London 2026 session mapped how internal developer platforms evolve for the agentic era: agent paths, a governance plane, and agentic PR review.

Luca Berton

· The Production AI Expert

Published ·Updated ·5 min read

The most reassuring line from the earliest session I caught at PlatformCon Live Day London 2026 was also the least dramatic: “Not that much changes.” In a day full of talks insisting AI rewrites the rules of platform engineering, one early-morning session made the opposite case — the internal developer platform you have already built is the foundation the agentic era gets built on top of, not something it replaces.

Three Kinds of Paths

The clearest framework of the session split platform workflows into three categories, and it is worth adopting as shared vocabulary:

  • Agent paths — work executed primarily by AI agents: PR reviews, spec drafting, triage. More standardized agent paths are reportedly on the way as the tooling matures.
  • Deterministic paths — the CI pipelines you already run, and they are not going anywhere. Even in an agentic platform, the assumption that an agent could just spin up a production database on its own remains firmly off the table, especially in regulated industries.
  • Hybrid paths — the combination: feed the error output from a deterministic step into the model, loop until resolution. This is what people actually mean when they talk about “loop engineering,” and it is a more precise term than the hand-wavy way “agentic workflow” usually gets used.

The core insight holds up under scrutiny: agents do not replace pipelines, they work alongside them in feedback loops. That is a grounding correction to a lot of AI hype that implies deterministic infrastructure is obsolete.

The Reference Architecture, Updated

The session’s IDP reference architecture kept the shape platform teams already recognize, with two additions:

  • Developer control plane — portals, knowledge surfaces, skill management, and now agent observation as a first-class capability
  • Integration and delivery pipelines — the same deterministic actions as always, now additionally augmented by agent-executed steps
  • Resource plane — where your software actually runs, unchanged and still vital
  • Tool security and tool observability — two genuinely new dedicated layers, built specifically for agentic workloads

A slide at PlatformCon Live Day London 2026 titled “Agent Infrastructure will be the AI substrate of the agentic enterprise”, showing agentic marketing, sales, finance, development and legal platforms above agent-driven, pipeline-driven and agent-plus-gate paths

A slide from the morning’s agentic-platform talks: separate agentic platforms (marketing, sales, finance, development, legal) sit on top of shared “paths” and one agent infrastructure layer.

The slide is a useful companion to the architecture above. It shows the same idea from the enterprise side: each business function can have its own agentic platform, but they all rest on one set of paths (agent-driven, pipeline-driven, and agent plus gate) and shared agent infrastructure. That supports the point that the platform team’s shared layer matters more, not less.

Infrastructure as code stays exactly where it is. Some tools need to become agent-consumable — exposing capabilities in a way an agent can discover and call — but a platform team that has already built a solid IaC foundation is most of the way there already.

The Governance Plane

A companion session from the same morning sharpened the operational reality of running agents at scale. The “operating system” of a single agent breaks down into execution, context, capability, and evaluation — and hot-loading the right context while exposing the right capabilities is, in the speaker’s words, “going to be our bread and butter for years to come.”

The scaling problem is the one platform teams will recognize immediately: running one agent is a demo, running dozens or hundreds or thousands simultaneously demands a governance plane covering identity, security, and observability — the same shared infrastructure platform engineers already build for human-driven workloads, extended to cover agents before the sprawl gets ahead of you. This is the same argument I make about production guardrails for AI agents: the governance layer has to exist before scale forces it into existence reactively.

Platform Engineering University slide listing two courses: Agentic Development Platforms (transition IDP to ADP, four levels of agentic autonomy, hands-on building of 8 core paths) and Agent Infrastructure for Platform Engineers (design the agent infrastructure, 3-tier agent permission model, hands-on seven pillars in practice)

A Platform Engineering University slide from the same morning at PlatformCon London: “Transition IDP to ADP”, four levels of agentic autonomy and a 3-tier agent permission model.

The slide shows how the training side is framing the same shift: moving from an IDP to an agentic development platform (ADP) is a defined path, and agent permissions are treated as a tiered model rather than an afterthought.

A Concrete Walkthrough: Agentic PR Review

The most useful part of the morning was a practitioner stepping through exactly how an agentic PR-review workflow runs inside a real platform, end to end:

  1. A human triggers the PR review, firing a webhook that starts an orchestration function.
  2. Identity is resolved, and the correct execution path is selected.
  3. Policies are pulled and available capabilities are identified.
  4. Context is gathered and handed off to the model for execution.
  5. Guardrails are applied and an evaluation runs.
  6. The platform decides: loop again, or report back to the human.

The standout observation — echoing Anthropic’s own writing on agentic systems — is that model execution is only a small slice of what the platform actually does. The real engineering work lives in orchestration, identity resolution, policy enforcement, and context assembly. That is precisely the layer building AI agents as Kubernetes operators is designed to formalize: treat the orchestration logic as infrastructure, not as glue code bolted onto a chat completion call.

Why This Framing Matters

Every vendor pitch at PlatformCon London wanted to convince you that agentic AI demands a wholesale platform rebuild. This session’s quieter, more useful claim is the opposite: the discipline of platform engineering — deterministic pipelines, policy enforcement, identity, observability — is exactly what makes agentic adoption safe. The work is extension, not replacement.

About the Author

I am Luca Berton, AI and Cloud Advisor. I work at the intersection of platform engineering, cloud security, and enterprise AI deployments. Book a consultation.

Free 30-min Production AI consultation

Book Now