Patrick Liekhus
Principal AI Enablement Engineer @ Provation
Overland Park, Kansas, United States
Actions
Patrick Liekhus is Principal AI Enablement Engineer at Provation, a company revolutionizing how clinicians and care teams around the world work together to deliver quality healthcare, trusted globally in hospitals, ambulatory surgery centers, and medical offices. He believes the biggest risk in the AI coding era isn't moving too slow - it's moving fast in the wrong direction.
Patrick champions spec-driven development as the discipline that keeps AI-assisted teams honest: clear specs before code, steering files that encode architectural intent, and multi-agent workflows that scale engineering output without sacrificing quality. His work sits at the intersection of scalable architecture and practical AI enablement - helping teams in engineering and the business build systems that are fast to ship and built to last.
A frequent voice on engineering discipline in the age of AI, Patrick brings hard-won experience from regulated, compliance-heavy healthcare environments where getting it right isn't optional — and where AI must be steered, not just unleashed.
Area of Expertise
Topics
Steering the Ship: Production-Ready AI Workflows with Context, Rules, and Guardrails
Your AI copilot is brilliant in the moment but has the memory of a goldfish. Ask it to "add a new API endpoint" and it might choose REST when you're building GraphQL, scaffold Entity Framework when you're using Dapper, or forget your team's naming conventions entirely. Every. Single. Time. The problem isn't the AI—it's that you're starting from scratch with every prompt.
This session reveals the architecture behind production-grade AI workflows that maintain consistency across your entire codebase. You'll learn how to build "steering files"—external context documents that shape AI behavior without touching source code—and discover practical patterns for Product_Overview.md files, behavioral rule sets, and context management strategies. We'll explore real examples from healthcare software development: Cursor rules that enforce EARS requirements syntax, behavioral files that generate C4 architecture diagrams on demand, and guardrails that prevent AI drift during complex refactoring. You'll see how to structure context hierarchies so your AI knows when to write BDD tests, when to follow your team's coding standards, and when to generate comprehensive technical documentation.
Walk away with ready-to-use templates for steering files, a decision framework for what belongs in context vs. prompts, and battle-tested patterns for maintaining AI consistency across sprints, developers, and codebases. Whether you're using Cursor, GitHub Copilot, or Claude Code, you'll learn how to transform unpredictable AI assistants into reliable team members who remember your team's standards, architectural decisions, and quality expectations.
Red-Green-AI: How BDD and Test Automation Became 10x Faster with AI Copilots
Writing Gherkin scenarios is tedious. Writing step definitions is boilerplate hell. Maintaining Playwright selectors when the UI changes makes you want to quit testing altogether. But what if your AI copilot could generate comprehensive BDD scenarios from requirements, scaffold step definitions that follow your team's patterns, and even suggest test cases you forgot? Not "magic AI testing"—real behavior-driven development that's faster, more consistent, and actually maintainable.
This session reveals how to supercharge your BDD workflow using AI assistance at every stage while maintaining test quality. You'll learn how to transform EARS-formatted requirements into Gherkin scenarios automatically, generate Reqnroll step definitions that follow your conventions, and leverage AI to identify edge cases and negative test paths you might have missed. We'll explore the complete pipeline from user story through executable tests: using steering files to enforce your BDD style guide, prompting patterns that generate maintainable Playwright locators, and techniques for keeping tests synchronized as requirements evolve. You'll see real examples from healthcare software where comprehensive test coverage isn't optional—it's a compliance requirement.
But it's not all roses. We'll tackle the hard problems: when AI-generated tests give false confidence, how to review AI test code effectively, and maintaining the "test-first" discipline when AI makes it tempting to test-last. Walk away with prompt templates for scenario generation, patterns for AI-assisted test maintenance, and a decision framework for when AI helps versus when it hurts your testing culture. Whether you're using Reqnroll, Cucumber, or SpecFlow with Playwright or Selenium, you'll learn how to leverage AI to write better tests faster—without sacrificing the thoughtfulness that makes BDD valuable.
KCDC 2026 Sessionize Event Upcoming
CommunityDays KC 2026 Sessionize Event
Patrick Liekhus
Principal AI Enablement Engineer @ Provation
Overland Park, Kansas, United States
Actions
Please note that Sessionize is not responsible for the accuracy or validity of the data provided by speakers. If you suspect this profile to be fake or spam, please let us know.
Jump to top