STARWEST 2026 - Consultant
Customize your STARWEST 2026 experience with sessions for consultants.
Monday, September 21
Forming Your Agent Team: From LLM to Agent
NewThe conversation around AI has already moved beyond prompts and chatbots. Today's engineering teams are beginning to build agents that can reason, use tools, and perform meaningful work. While many professionals have experimented with large language models (LLMs), far fewer understand how agents actually work or how to build one themselves. In this hands-on tutorial, you'll move beyond simply using AI and begin building with it. Through practical exercises and real-world examples, you'll learn the foundations of modern agentic systems and follow the evolution from LLM to agent. Along the...
Testing AI Systems That Refuse to Sit Still: Practical Evals, Red Teaming, and Oversight for AI Agents
NewModern AI systems don’t behave like traditional software. The same prompt can produce different outputs, models can drift without code changes, and AI agents may hallucinate, misuse tools, leak context, or confidently invent facts while appearing completely functional. In this hands-on tutorial, Jeremiah Marble will show attendees how to test and harden modern AI systems using practical, lightweight techniques teams can apply immediately. Participants will build tiny AI agents, intentionally break them through prompt injection, unsafe outputs, hallucinations, and memory drift, then create...
Automation Framework Essentials
Automation is critical in today’s software delivery lifecycle, and yet many organizations struggle to keep their automation running. How can we mitigate difficulties and get consistent automation runs and results we can trust? The secret is implementing a solid automation framework, but that isn’t as easy as it seems. Chris Loder has built several automation frameworks over his career and has learned what works—and, more importantly, what doesn’t. This tutorial will cover what an automation framework is, the benefits of having one, and the keys to a successful framework, including...
Leading Your Agent Team: From Agent to Agentic Orchestration
NewBuilding an agent is only the beginning. The next wave of AI innovation is being driven by teams of specialized agents working together to solve increasingly complex problems. As organizations move beyond individual agents and toward coordinated AI systems, a new challenge emerges: how do you lead, coordinate, and govern intelligent teams? In this hands-on tutorial, you'll move beyond creating agents and begin learning how to orchestrate them. Through practical exercises and real-world examples, you'll explore how specialized agents can collaborate, share responsibilities, and work...
Building Apps and Tests Together with AI: Agentic Spec-Driven Development
NewWhat if you could turn ideas into working software with tests to prove it, using AI as your collaborator? This hands-on half-day tutorial introduces agentic spec-driven development, a practical approach for building web apps and test automation together with AI coding agents like Claude, Cursor, Copilot, or Codex. Designed for testers and anyone involved in software development, this session shows how to define a clear project context and rules. You will write feature specs as structured markdown with user stories, design decisions, and acceptance criteria. Then you will use AI to generate...
Tuesday, September 22
Agentic AI: From Rules to Reasoning
NewAI agents have existed for decades, but generative AI has fundamentally changed what agents can do and how they are designed and built. Come and explore the evolution of AI agents across two major waves. First, learn the foundations of Agentic AI through agents built using rules, heuristics, and traditional machine learning, examining where these approaches excel and why they struggle with complexity, ambiguity, and scale. Then dive into the second wave of agents powered by generative AI and multimodal large language models. These modern agents can reason, plan, use tools, and interact...
Quality and Testing Measures and Metrics
To be most effective, leaders—including development and testing managers, ScrumMasters, product owners, and IT managers—need metrics to help direct their efforts and make informed recommendations about the software’s release readiness and associated risks. Because one important evaluation activity is to “measure” the quality of the software, the progress and results of both development and testing must be measured. Collecting, analyzing, and using metrics are complicated because developers and testers often are concerned that the metrics will be used against them. Join Jeff Pierce as he...
Wednesday, September 23
The Future of Test Automation: Trends, Challenges, and Your Burning Questions - Panel
Test automation is evolving at an unprecedented pace, driven by AI, continuous testing, and the ever-increasing complexity of modern software development. Join us for an engaging panel discussion where industry experts will explore the latest trends in test automation, including AI-powered testing, low-code/no-code automation, and the role of testers in a rapidly changing landscape. This session will also serve as an open forum for attendees to ask any lingering questions from the conference. Whether it’s about the future of automation, best practices, or the impact of AI on testing roles...
Thursday, September 24
AI Enablement at Scale: How to Lead an Organization Through a Successful AI Transformation
As AI rapidly moves from experimentation to a core organizational capability, many companies struggle not with models or tools—but with transformation itself. In this talk, Svetlana Stogni shares real-world experiences of leading AI enablement transformations at the organizational level. You will learn how to assess AI readiness, review existing PDLC processes, run rapid assessments, and establish continuous health monitoring to guide sustainable change. The session covers practical approaches to AI tools and platform setup, driving adoption across teams, defining performance and...
Global Teams, Unified Quality—Building a Single Quality Mindset Across Borders
In the world of Quality Engineering, the distance between "Developer" and "Tester" is already a challenge. Add 8,000 miles and a 12-hour time difference, and that gap can become a canyon where bugs hide and requirements die. Poorva Dixit, a Senior Manager with nearly two decades of experience in QA and Test Automation, argues that successful offshore leadership isn't about micromanagement, it's about rigorous process and radical human connection. This session unpacks the "One Team" framework: a methodology for erasing the line between onshore strategy and offshore execution. Attendees will...
Testing in Production: How QA Frameworks Debug Life's Messy Systems
As QA professionals, we're experts at identifying system failures, analyzing root causes, and implementing sustainable fixes—at work. But when Alison McGuigan's personal life became a critical severity issue (layoff, miscarriage, postpartum fog, and a chaotic household), she realized she'd never applied that same rigor to her own circumstances. She treated her messy house like a failed deployment. So she ran an 8-week experiment: What if she debugged her life like a QA project? She conducted root cause analysis to find real problems beyond surface symptoms. She defined "minimum viable...
RAG Testing That Holds Up: Evaluating LLMs for Faithfulness, Boundaries, and Trust
PreviewMany teams are adopting RAG to constrain LLMs to internal documents, policies, and knowledge bases, but “using RAG” does not guarantee trustworthy behavior. In practice, models still hallucinate, blend outside knowledge, ignore source boundaries, and produce confident answers that are not supported by retrieved evidence. Traditional test approaches (happy-path assertions, correctness spot checks, performance metrics) often miss these failures because the output reads plausibly correct. Drawing from real evaluation work on document-constrained enterprise systems, this session...