Agentic Workflows and Performance Testing in the Age of AI | 5th NA Huddle

5th North America Huddle - Agentic Workflows and Performance Testing in the Age of AI

Building with AI is moving beyond using copilots to generate code. Teams are beginning to use agentic workflows across requirements, architecture, implementation, testing, and delivery.

At the same time, AI-powered applications introduce performance challenges that are harder to predict with conventional test scripts alone. Variable latency, changing execution paths, and more dynamic system behaviour can make it difficult to understand where performance problems are coming from.

The Test Tribe’s North America Virtual Huddle brings together QA professionals, software engineers, architects, DevOps engineers, performance engineers, and AI practitioners for two sessions looking at these challenges from different parts of the software delivery lifecycle.

Event Details

• Date: September 3, 2026
• Time: 12:00 PM – 2:00 PM ET
• Platform: Zoom. Joining details will be shared closer to the event.

Agenda

All timings are in ET

• 12:00 PM – 12:15 PM: Welcome and introductions
• 12:15 PM – 1:00 PM: Session 1 – Building with Agentic Workflows: From Idea to Launch by James Koch
• 1:00 PM – 1:10 PM: Solution Spotlight / Community Break
• 1:10 PM – 1:55 PM: Session 2 – The Day the Bot Broke the Backend: Performance Testing in the Age of AI by Gargi Majumder
• 1:55 PM – 2:00 PM: Closing

Session 1: Building with Agentic Workflows: From Idea to Launch

Speaker: James Koch
Quality Engineering Solutions Architect

AI agents can support much more than code generation. The harder question is how to use them within a structured engineering workflow without losing the planning, review, and quality controls that teams still need.

In this session, James Koch will break down the workflow he used to build and launch a blog application end-to-end.
He will show how GitHub Copilot agents can support different stages of the process, including drafting requirements, generating implementation plans, validating architecture decisions, and accelerating delivery while retaining engineering quality gates.
The session will also cover the practical side of introducing AI into engineering workflows, including where human review remains important and how structured prompts, planning templates, and documentation workflows can help teams work more consistently.

Session 2: The Day the Bot Broke the Backend: Performance Testing in the Age of AI

Speaker: Gargi Majumder
Performance Engineering & NFR Specialist

Performance testing becomes more difficult when application behaviour is less predictable.
AI-driven systems may introduce variable latency, dynamic workflows, changing code paths, and additional dependencies that make it harder for traditional performance tests to explain what is happening inside the system.
Through the story of “Alex,” a performance engineer responding to an AI-driven production incident, Gargi Majumder will explore the Black Box Performance Gap and what it means for performance engineering teams.

The session will examine how AI can also be used as a white-box collaborator, helping teams analyse code changes, generate test data, and surface system telemetry that may otherwise be difficult to investigate.
Rather than treating AI as a replacement for performance engineering, the session looks at how it can support deeper analysis and help teams design performance strategies for AI-powered applications.

How This Huddle Solves Your Problem

The two sessions focus on different stages of the engineering lifecycle, but both address the same broader challenge: introducing AI without losing engineering discipline.

You will explore:

• How agentic workflows can support requirements, architecture, development, and testing
• Where human review and quality gates still matter when AI agents are involved
• How structured prompts and documentation can make AI-assisted workflows more repeatable
• Why AI-powered applications can create new performance-testing challenges
• How AI can support performance analysis through code inspection, test-data generation, and telemetry

Why Show Up on September 3?

This Huddle is an opportunity to hear two practitioners explain how they are approaching AI from different engineering perspectives.
You will be able to compare agentic development workflows with the challenges of testing and analysing AI-powered systems, ask questions during the sessions, and discuss where these approaches may or may not fit within your own team.
You will also connect with QA professionals, engineers, architects, DevOps practitioners, performance engineers, and AI practitioners from across North America who are working through similar questions.

Become a Speaker at The Test Tribe Events

Wish to share your insights with the community at a future event?
Submit your talk idea here, and if it resonates with the perspective we are trying to build at our events, our team will connect with you.

About The Test Tribe

The Test Tribe is the world's largest software testing community, empowering testers globally since 2018. With 925+ events and 170K+ members across 130+ countries, we bring software professionals together to learn, grow, and connect through meetups, conferences, cohorts, masterclasses, and more.

By RSVPing, you agree to our Terms & Conditions and Privacy Policy and consent to be contacted by The Test Tribe and our event partners.