Вход на сайт

Просмотр новости

Найдите то, что Вас интересует

Building an agentic SDLC with a QA engineering mindset

Дата публикации: 18-08-2026 07:40:00

Ryan welcomes Suneet Malhotra, Senior Manager of Test Engineering at Motorola Solutions, to chat about building end-to-end agentic SDLC pipelines using MCPs, using Cohen’s kappa to evaluate multiple LLMs-as-judges, and how you can improve requirements by shifting QA left through a specification enrichment stage immediately after the design phase.

Основное содержимое страницы с новостью.

Blog

Loading…

August 18, 2026

Ryan welcomes Suneet Malhotra, Senior Manager of Test Engineering at Motorola Solutions, to chat about building end-to-end agentic SDLC pipelines using MCPs, using Cohen’s kappa to evaluate multiple LLMs-as-judges, and how you can improve requirements by shifting QA left through a specification enrichment stage immediately after the design phase.

The Stack Overflow Podcast cover art

You can learn more about Suneet’s five-agent SDLC (and see the companion code) on his GitHub.

Read the papers discussed: Cross-Layer Observability for LLM-Assisted Test Automation: A Reference Architecture and Web Feasibility Study and Cross-Layer Observability for LLM-Assisted Test Automation — Reference Implementation and Evaluation Data (v1.5.2, JSS In-Practice).

Connect with Suneet on LinkedIn and see more of his work on his website.

Congrats to user Sanjay for winning a Great Question badge for asking What does it mean to fork on GitHub?.

Add to the discussion

Login with your stackoverflow.com account to take part in the discussion.

Схожие новости

#Наименование новостиТональностьИнформативностьДата публикации
1Constructing and Judging Modern Agentic Workflows07.6210-07-2026
2How to be fearlessly AI native06.5207-08-2026
3Your tokenmaxxing is not valuemaxxing09.5811-08-2026
4Cisco's SVP of Security: re-engineering the stack for AI with secure-by-design013.3802-03-2026
5Мультиагентная система без LangChain: почему абстракции ломаются и как строить production на чистом Python04.9711-04-2026
6Coding agents can be evaluated. We just have to evaluate the work.014.3109-08-2026
7Building The Future Of Software In The AI-Native Era017.7819-11-2025
8MCP vs Thin MCP: где AI агенты теряют скорость09.9103-04-2026
9 How to Use Prompt Engineering and Context Engineering for AI Agents 05.6324-07-2026

Классификация: . Схожих патентов: 0. Схожих новостей: 9. Тональность: 0. Информативность: 10.4. Источник: stackoverflow.blog.