World Congress 2026 Europe • Jul 10, 2026 • Session details

Pair Programming with Generative Agents: Refactoring Legacy Android at Speed

Ahmed Tikiwa

Shift from writing code to architectural director. Discover how pair programming with autonomous generative AI systematically overhauled a tangled legacy Android architecture at speed.

Pause
Mute Enter Fullscreen
#1 about 3 min

Exploring the Jetpack Compose architecture of Upnext

The Upnext TV tracking app utilizes a multimodule architecture built entirely in Jetpack Compose.

#2 about 3 min

Identifying accumulated architectural debt in a modern codebase

Manual deployments, tight navigation coupling, and locked dependencies created a fragile development environment.

#3 about 3 min

Adopting the Antigravity AI agent for complex refactoring

Using an autonomous AI collaborator instead of simple autocomplete requires defining target architectures and reviewing implementation plans.

#4 about 2 min

Shifting developer roles in autonomous pair programming loops

Developers focus on directing, reviewing, and approving implementations while the agent compiles, debugs, and tests in branch isolation.

#5 about 3 min

Enforcing architectural consistency using markdown agent skills

Portable skill files guide the AI framework effectively by applying progressive disclosure and custom modular constraints.

#6 about 2 min

Resolving a three-way dependency lock in legacy code

Tracing the conceptual dependency graph resolved compatibility issues between the Kotlin language level, KSP, and Hilt versions.

#7 about 4 min

Executing a structural migration to Jetpack Navigation 3

The transition required explicitly passing route objects with assisted injection and scoping view model lifecycles accurately.

#8 about 3 min

Implementing adaptive app layouts across diverse screen sizes

Independent scaffold navigation systems are bridged with reactive state tracking to automatically reveal split views on tablets.

#9 about 3 min

Constructing comprehensive continuous integration and deployment pipelines

Replacing manual uploads with GitHub Actions, Fastlane scripts, and smart staleness gates ensures reliable automated releases.

#10 about 2 min

Validating autonomous code generation with robust automated testing

The AI agent proved its reliability by autonomously writing comprehensive unit and instrumented tests for emulators.

#11 about 3 min

Directing the AI symphony and avoiding unmonitored deployments

Successful AI collaboration requires setting explicit rules, demanding strict test verifications, and monitoring output rigorously.

#12 about 2 min

Comparing Antigravity and Claude Code for complex tasks

Practical experiences show tailored AI agents effectively navigating full workflows without running into restrictive token constraints.

Matching moments

1:55 min

Shifting developer workloads and realistic AI productivity gains

Chris Heilmann Chris Heilmann +2 · LIVE

2:06 min

Rethinking team structures around AI agent capabilities

Mike Mike · World Congress 2025

2:36 min

Learning software engineering through pair programming with AI assistants

Logan Kilpatrick · Coffee With Developers

46 sec

Shifting from chat interfaces to autonomous agentic co-piloting

Sergej Reznik Sergej Reznik · Europe 2026 Virtual

4:08 min

Transitioning software engineering teams to AI-native development workflows

Florian Deter Florian Deter +4 · World Congress 2026 Europe

3:56 min

The evolution of AI programming and agentic workflows

Fabian Hedin Fabian Hedin · World Congress 2026 Europe