Platforms for Humans and Machines: Engineering for the Age of Agents

As AI coding agents become first-class users of internal developer platforms, the practices that make platforms accessible to humans turn out to be the same ones that enable AI to thrive.

Self-service interfaces, well-defined APIs with schemas and documentation, local-first workflows, and rich observability have always been important elements of a good platform. Now they are prerequisites for agents that can autonomously build, debug, and ship software.

This talk explores what it means to design platforms where both humans and AI can collaborate effectively. We'll cover:

- How to expose your platform as a product with structured APIs (and perhaps MCPs)
- Why prioritizing local tooling pays dividends when agents need to iterate on errors
- How observability becomes the bridge between runtime behavior and AI understanding

We'll also discuss the flip side: AI is making it easier than ever to *contribute* to platform code, but that comes with new responsibilities around quality gates, context files like CLAUDE.md, and maintainability.

Walk away with concrete practices to ensure your platform is ready for a future where agents are not just tools, but users of it.

Transcript

1. NEXT GEN BANKING. POWERED BY THE LATEST TECHNOLOGY. Platforms for Humans and Machines AI Engineer Europe 2026
2. Next Gen Banking. Powered by the Latest Technology. Banking Circle • Global cross-border payments, accounts and liquidity management • Providing banking services to over 700 regulated financial institutions • €1 Trillion processed annually • 40% of our organisation workforce are engineers
3. Platform Engineering @ Banking Circle Atlas > 250 people are building: • Client-facing APIs • Core Banking Systems • Internal tools • Data • Integrations with other companies and clearing schemes
4. Platform Engineering @ Banking Circle Atlas • Compute • Infrastructure • Messaging • Observability
7. Agents just make the cost of ignoring them immediately visible Best practices are still best practices
8. Self-service • Automatic • No human involved • Intuitive
9. API-based • Discoverable • Schema validation • Auth
10. Local-first • Shift left • Let the agent work until it gets there • Tell it how to do and how to verify (o11y)
11. Documentation • Context • Docs next to code or via API • Agents.md, skills
12. Contributions • Encourage contributions • Guardrails for security, compliance, standards • Context for ease of use, DevEx
13. Did it work?
14. Measure • Delivery (DORA) • Reliability (SLOs, golden signals) • Support requests • Developer Experience (SPACE)
15. Summary 1.Self-service 2.API-based 3.Local-first 4.Documentation 5.Enable contributions 6.Measure
16. Best practices AI
17. NEXT GEN BANKING. POWERED BY THE LATEST TECHNOLOGY. Thank you! Juan Herreros Elorza LinkedIn JuanHerreros.com GitHub