The engineer who understands systems is the one who can direct AI

AI code generation and autonomous agents are changing how software is built. What they cannot change is the judgment required to determine whether the result is architecturally sound. That judgment belongs to the engineer who understands the system as a whole – its boundaries, its responsibilities, its failure modes. In this track you will learn, how experienced engineers direct AI development tools and agentic systems.

AI in Development & Agentic Systems

Learn from Industry Leaders about:

  • AI-Driven Development & Vibe Coding: Guiding AI systems instead of writing every line of code
  • Agentic Engineering & Coding Agents: Using autonomous agents to implement and evolve systems
  • Agentic Systems Architecture: Designing systems where agents plan and execute tasks within defined boundaries
  • Model Context Protocol (MCP) & Tool Integration: Connecting agents to enterprise systems, APIs, and data sources through auditable interfaces
  • Context Engineering for Developers: Structuring prompts and specifications for reliable, architecturally coherent results
  • Guardrails for AI-Generated Code & Agent Behavior: Ensuring quality, consistency, and alignment across the generative layer

Track Speakers 2025

Track Program 2025

Track Sessions on Jax London

Track Sessions on Jax London

View all sessions

What is the focus of the track?

The focus is on how experienced engineers can effectively direct AI development tools and agentic systems. It emphasizes that architectural judgment remains a human responsibility and teaches the technical skills needed to oversee AI-driven development, from context engineering to building autonomous agent architectures.

What is "Vibe Coding" and how does it apply to a professional environment?

"Vibe Coding" is the practice of guiding AI systems through high-level intent and architectural direction rather than writing every line of code manually. In a professional context, this means the engineer acts as a director, using their understanding of system boundaries and responsibilities to ensure the AI's "creative" output aligns with technical reality.

How do we securely connect AI agents to our existing enterprise data?

The track highlights the Model Context Protocol (MCP) and tool integration. You will learn how to build auditable interfaces that allow agents to interact with APIs and data sources, ensuring that autonomous actions are transparent and compliant with enterprise security standards.

What is "Context Engineering" for developers?

Unlike standard prompting, Context Engineering is the disciplined practice of structuring technical specifications and system metadata. This ensures the AI has a clear "mental model" of your architecture, leading to code that isn't just functional, but also architecturally sound and consistent with your codebase.

How do we maintain code quality when agents are evolving the system?

A major focus is on Guardrails for AI-Generated Code. You will learn how to implement automated checks and design patterns that govern agent behavior, ensuring that the generative layer doesn't introduce technical debt, security flaws, or architectural drift.

STAY TUNED!

JOIN OUR NEWSLETTER

[mc4wp-simple-turnstile]

Explore other Tracks

Engineering Teams in the Age of AI

The team structures that worked yesterday need rethinking for AI adoption
DevOps, CI/CD & Platform Engineering

The platform is what makes AI systems trustworthy in production
Software Architecture for Intelligent Systems
Designing systems that stay coherent as intelligent capabilities enter the architecture.
Software Engineering Practices
Engineering judgment is what gives AI-generated code its quality.
AI in Development & Agentic Systems
The engineer who understands systems is the one who can direct AI
Enterprise AI: Security, Scale & Performance
Keeping AI systems secure, cost-efficient, and stable under real-world conditions.