Paul Ardeleanu
Principal Architect at Vonage, part of Ericsson
London, United Kingdom
Actions
Paul is a Principal Architect at Vonage, working at the intersection of architecture, AI, and developer tooling, helping transform how developers interact with CPaaS and Network APIs. Having transitioned from managing Developer Relations teams to the central Architecture Team, he brings a unique perspective: understanding both the strategic vision required for enterprise architecture and the practical realities developers face daily.
His path in technology began with Fortran and a PhD in Computational Physics from the University of Lancashire, UK. Decades of hands-on programming experience since then have shaped his approach to architecting systems that serve developer needs. Paul remains active in the developer community through speaking engagements and writing, with a particular focus on JavaScript, Ruby, Swift and Rust.
Area of Expertise
Topics
Your Next Developer Might Be a Robot: DevRel in the AI Era
Developer Relations has always been about meeting developers where they are, but what happens when "developers" aren't just humans anymore? AI agents are rapidly becoming first-class consumers of our APIs, documentation, and tooling, and they don't attend meetups or watch conference talks but are rather parsing your public documentation and sample repositories at 3AM, making decisions based on what they discover. It's happening now and it fundamentally changes what Developer Relations needs to be.
This talk explores how DevRel must evolve when the audience has rapidly expanded to include two new categories of users: humans who build with the help of AI-enabled tools, and AI that operates autonomously. We'll dig into the critical questions: is the documentation agent-readable? Are the APIs designed for non-human consumers? What does "developer experience" mean when the developer never sleeps and has no patience for ambiguity?
We'll also address the new challenges head-on: trust gets harder when agents act on behalf of users, support gets messier, and traditional success metrics start to break down. The upside is proportionally substantial: DevRel teams equipped with AI tools can produce more content, reach more developers, and respond faster than ever before, multiplying their impact.
Whether you're in DevRel, building developer tools, or just curious about where this is all heading, this session will give you a practical framework for thriving when your newest power users don't have a physical presence. So far…
Learning outcomes:
- Developer Relations now serve two new audiences, AI-assisted developers and AI agents, each with different expectations and needs.
- Traditional metrics are not suitable for the Agentic age.
- AI tools multiply DevRel impact and teams that embrace them gain a competitive edge.
- When agents act on behalf of developers, trust and guardrails become DevRel problems.
Opening Pandora's Box: A Developer's Guide to AI Agents
We've opened Pandora's box on AI coding agents and the instinct is to react with hype or fear. This talk offers a third option: read the instructions in the box.
Agent harnesses moved from research demos to production tools in twelve months. The system is far less mysterious than the discourse suggests: a single while-loop calls a model and dispatches tools, with deliberate engineering all around it. Roughly 1.6% of the codebase is AI decision logic. 98.4% is operational infrastructure.
But at least six 'ills' did fly out: opacity (your diff captures the *what*, not the *why*), misalignment (OpenAI runs internal monitors at maximum reasoning to flag escalations), displacement (Anthropic reports 27% of agent-assisted tasks wouldn't exist without the tool; both ambition and baseline rise), accountability vacuum (who's accountable when the agent decided?), amplified dysfunction (AI multiplies whatever system it runs on, including its sins), and compliance-as-bolt-on (you'll discover your governance gaps in production, not in design).
Inside the box, safety primitives are already shipping (permissions, hooks, MCP boundaries, subagent isolation, append-only sessions), and the engineers who compound are the ones who learn to read them. The only durable strategy is agency: shape your harness, don't just prompt it. When AI flattens skill differences, the developers who shape get disproportionate leverage.
The audience will leave with five concrete moves to make Monday morning, the literacy to read any production agent harness on its own terms, and a sketch of where the practice scales: the AI-Native Software Factory.
Audience: developers at any level, juniors through staff. Mixed-experience room.
Please note that Sessionize is not responsible for the accuracy or validity of the data provided by speakers. If you suspect this profile to be fake or spam, please let us know.
Jump to top