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

AI Driven Development

David Tielke

David Tielke shipped a 19-year enterprise project in 45 days with zero technical debt. Discover his strict AI constraint harness for idea-driven code generation.

Pause
Mute Enter Fullscreen
#1 about 5 min

Testing AI limits in enterprise software design

An experiment evaluates whether modern AI models can build a fully functional enterprise application without structural or technical debt.

#2 about 3 min

Replacing legacy applications with customized AI agents

The project replaces an older operational and customer management system with an updated architecture led by an AI agent named Hermes.

#3 about 4 min

Selecting an enterprise microservices architecture and stack

The technology stack features a complex microservices architecture utilizing an API gateway, multiple UI frontends, and local LLM integrations.

#4 about 3 min

Configuring the DevOps environment and coding agents

The development workflow employs local nodes running coding agents with direct access to technical harnesses, specifications, and a wiremock testing pipeline.

#5 about 2 min

Implementing automated API and workflow testing pipelines

Testing frameworks convert business acceptance criteria directly into comprehensive API tests and internal workflow validations with NUnit.

#6 about 1 min

Micromanagement phase using direct code generation prompts

The initial development phase relies on direct manual instructions to AI agents and significant review processes to assess code structuring.

#7 about 3 min

Enforcing quality standards via automated system harnesses

Integrating tools like ReSharper and NDepend inside system prompt harness files ensures that generated code meets rigorous architectural constraints.

#8 about 2 min

Automating code creation via spec and test-driven workflows

Supplying context-rich specification artifacts replaces granular prompt engineering and auto-generates test scenarios mapped exactly to acceptance criteria.

#9 about 3 min

Voice-driven ideation using comprehensive system context prompts

Transferring large, comprehensive context documents to a mobile LLM application enables fluid technical and architectural design entirely through spoken interactions.

#10 about 3 min

Analyzing project sizing, token usage, and technical depth

The finalized implementation produces a virtually debt-free codebase while scaling highly cost-efficient localized inference mixed with broader LLM usage.

#11 about 2 min

Comparing AI development speed against traditional engineering teams

Metrics indicate AI-driven coding processes operate exponentially faster than traditional baseline estimates derived from human software delivery times.

#12 about 5 min

How automation shifts software engineering toward high-level abstraction

Rapid AI advancements demand that technology professionals transition from manual coding towards orchestrating architectural guidelines, development operations, and systemic harnesses.

Matching moments

1:55 min

Shifting developer workloads and realistic AI productivity gains

Chris Heilmann Chris Heilmann +2 · LIVE

1:21 min

Using artificial intelligence to reimagine developer experience

Alexander Trusheim Alexander Trusheim +1 · World Congress 2025

5:16 min

Motivations for adopting AI to enhance developer productivity

4:08 min

Transitioning software engineering teams to AI-native development workflows

Florian Deter Florian Deter +4 · World Congress 2026 Europe

4:03 min

Impact of AI on the software development lifecycle

Jemiah Sius Jemiah Sius +1 · World Congress 2026 Europe

2:10 min

Leveraging AI-assisted coding to amplify developer capabilities

Francesco Ciulla Francesco Ciulla · World Congress 2023