← back
Agentic Engineering: Working With AI, Not Just Using It — Brendan O'Leary
Takeaway
Productivity gains from AI coding come from explicit context engineering and treating agents like fast but judgment-poor juniors you must direct.
Summary
- Brendan O'Leary distinguishes 'using AI' (autocomplete) from 'agentic engineering' (delegating tasks, breaking down work, running tests, returning PRs); cites Armin Ronacher's 30%-time-savings claim.
- Recommends the mental model of an 'enthusiastic, well-read, confidently wrong junior developer' that lacks business judgment, so humans must direct and gate the work.
- Stresses context engineering (Karpathy quote): more context isn't better, quality degrades past ~50% context fill, and too many MCP servers loaded simultaneously poison the window.
- Argues teams that articulate exactly what they hand off, what they keep, and how they decide capture far more value than teams that 'just autocomplete through the day'.
agentic-engineeringcontext-engineeringdeveloper-productivity
Original description
Coding agents are quickly moving from novelty to necessity, but most teams are still stuck between demos that feel magical and systems that break down in real-world engineering environments. In this session, Brendan O’Leary explores what it takes to make coding agents reliable collaborators rather than unpredictable copilots. Drawing from hands-on experience building and scaling AI coding agents, Brendan can unpack where agents succeed, where they fail, and how engineers can design workflows that balance speed with control. Attendees will learn how to think about agent autonomy, context management, and human-in-the-loop design so AI can meaningfully accelerate development without sacrificing code quality, security, or trust. This talk is for engineers ready to move past “vibe coding” and into production-grade agent-driven software development. Brendan O'Leary - Developer Relations Engineer, Kilo Code As conversations shift from AI demos to real engineering and coding agents begin moving into production environments, Brendan is passionate about helping teams understand not just what’s possible, but what’s practical. He’s especially energized by audiences who are grappling with the same questions he sees every day: how much autonomy to give agents, how to keep humans meaningfully in the loop, and how to move beyond “vibe coding” into reliable software development. Brendan is a builder and practitioner at Kilo Code, working hands-on with AI coding agents and the realities of deploying them in serious engineering contexts. He’s mastered the role of choreographer, successfully balancing the collaborative dance between human creativity and machine capability. His perspective of coding agents is rooted in lived experience, combining a deep technical understanding with a clear-eyed view of where agents succeed, where they fail, and why trust is the missing layer most tools overlook. Brendan brings a candid, engineer-first approach that resonates with technical audiences and leaves them with concrete ways to rethink how humans and coding agents collaborate in production systems. Socials: https://www.linkedin.com/in/olearycrew/ https://boleary.dev/ https://x.com/olearycrew https://gitlab.com/brendan/boleary-dot-dev https://kilo.ai/