World Congress 2025 • Aug 20, 2025 • Session details

AX is the only Experience that Matters

Ivan Burazin

Is your SaaS ready for autonomous AI? Agents are replacing human developers as the primary users of software tools, making Agent Experience (AX) the only metric that matters.

Pause
Mute Enter Fullscreen
#1 about 3 min

The exponential rise of autonomous software agents

The growing number of software agents outnumbering humans requires a fundamental shift beyond traditional deterministic web applications.

#2 about 2 min

Defining the core components of an ai agent

Autonomous software functions strictly at the intersection of intelligence models, user prompts, and accessible digital tooling.

#3 about 2 min

Understanding the core principles of agent experience

Simplifying digital environments enables machines to easily access, comprehend, and operate within systems to achieve user-defined goals.

#4 about 3 min

Exploring real-world examples of seamless agent tooling

Implementing authentication layers and machine-readable text files improves the ability of agents to navigate complex api documentation securely.

#5 about 3 min

Designing software systems for complete agent autonomy

Removing fallback requirements ensures tools remain functional even when no human is available to troubleshoot errors or click buttons.

#6 about 4 min

Building fast and stateful agent native runtimes

Creating custom bare-metal sandboxes solves the unique requirement for agent environments that spin up instantly but run stateful tasks indefinitely.

#7 about 2 min

Implementing machine native interfaces for autonomous tasks

Replacing human user interface components with headless terminals and language servers allows optimal machine-to-machine communication.

#8 about 3 min

Developing new infrastructure primitives for automated workflows

Equipping agents with declarative image builders and shared network volumes removes human bottlenecks in container orchestration and dependency management.

#9 about 2 min

Leveraging parallel execution for automated problem solving

Forking system runtimes drastically multiplies computational capabilities by enabling an agent to test varying programmatic solutions simultaneously.

#10 about 5 min

Meeting the market demand for agent computing infrastructure

Iterating with developers reveals significant gaps in current serverless offerings and highlights an explosive market demand for machine-first hosting platforms.

Matching moments

1:48 min

Defining true agent behavior versus traditional enterprise chatbots

Dennis Zielke Dennis Zielke +1 · World Congress 2025

1:14 min

Adapting to the changing landscape of autonomous software development

World Congress 2026 North America

6:55 min

Comparing agent experience with traditional developer experience

Han Wang Han Wang +3 · World Congress 2026 North America

4:08 min

Transitioning software engineering teams to AI-native development workflows

Florian Deter Florian Deter +4 · World Congress 2026 Europe

2:32 min

Preparing for the future of agent-driven software development

Matan Grinberg Matan Grinberg +2 · World Congress 2026 North America

4:37 min

Transitioning to a hybrid human and agent workforce

Thomas Dohmke Thomas Dohmke · World Congress 2025