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.
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.

You can learn more about Suneet’s five-agent SDLC (and see the companion code) on his GitHub.
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?.
| # | Наименование новости | Тональность | Информативность | Дата публикации |
|---|---|---|---|---|
| 1 | Constructing and Judging Modern Agentic Workflows | 0 | 7.62 | 10-07-2026 |
| 2 | How to be fearlessly AI native | 0 | 6.52 | 07-08-2026 |
| 3 | Your tokenmaxxing is not valuemaxxing | 0 | 9.58 | 11-08-2026 |
| 4 | [Free Tutorial] Master Building AI Agents | 0 | 6.66 | 13-07-2026 |
| 5 | Coding agents can be evaluated. We just have to evaluate the work. | 0 | 14.31 | 09-08-2026 |
| 6 | Мультиагентная система без LangChain: почему абстракции ломаются и как строить production на чистом Python | 0 | 4.97 | 11-04-2026 |
| 7 | ACP vs MCP: What's the difference for agentic coding? | 0 | 5 | 02-07-2026 |
| 8 | Beyond the Pilot: Building the Clinical Data Fabric for the Agentic Era | 0 | 7.02 | 07-05-2026 |
| 9 | MCP vs Thin MCP: где AI агенты теряют скорость | 0 | 9.91 | 03-04-2026 |