--- title: "QA the agent, not the code" newsletter: "MLOps Community" date: 2026-04-09 source: https://aaif.live/newsletters/mlopscommunity/2026-04-09-qa-the-agent-not-the-code --- # QA the agent, not the code *Plus... tool design for messy search queries, hidden infrastructure debt in production agents, and persistent memory that beats RAG.* *MLOps Community — Agentic AI Foundation, 2026-04-09* Before you vibe-code your billion-dollar idea, make sure you’ve got a vibe strategy [https://techcrunch.com/2026/04/06/indian-startup-rocket-wants-its-ai-to-do-mckinsey-style-consulting-at-a-fraction-of-the-cost/]. ## Fluent Nonsense Better models don’t fix bad interfaces. They just fail more convincingly. What do you optimize first: model or interface? [MODEL](https://gatewaze.mlops.community/offer/surveys/?sid=yesno&question=Better+models+don%E2%80%99t+fix+bad+interfaces.+They+just+fail+more+convincingly.+What+do+you+optimize+first%3A+model+or+interface%3F&y=MODEL&n=INTERFACE&oneclick=true&accept=true) [INTERFACE](https://gatewaze.mlops.community/offer/surveys/?sid=yesno&question=Better+models+don%E2%80%99t+fix+bad+interfaces.+They+just+fail+more+convincingly.+What+do+you+optimize+first%3A+model+or+interface%3F&y=MODEL&n=INTERFACE&oneclick=true&accept=true) ## Legacy, Apparently The “single-agent is legacy” call runs slightly ahead of reality - assistants are still holding nearly half the vote. ## When your context window fills up before your agent’s done anything useful You’ve watched an agent chew through its context budget before it’s shipped a single useful output. That’s one of the production constraints covered at the AI Agents Summit on April 14. Rodney Shen from TextQL is arguing for sandboxes instead - skills and credentials co-located with execution, no bloat, no subprocess dependencies you don’t own. Ten talks on what it takes to run agents in real systems - from durable runtimes and orchestration to what breaks after deployment. Speakers include engineers from Google, Meta, Microsoft, Intuit, Orkes, Union.ai [http://Union.ai], Zipline AI, Braintrust, and Databricks. Museum of Flight, Seattle. April 14. REGISTER TODAY [REGISTER TODAY](https://luma.com/ai-agents-summit-seattle) [https://luma.com/ai-agents-summit-seattle](https://luma.com/ai-agents-summit-seattle) ## Curated finds to help you stay ahead ## Getting Humans Out of the Way: How to Work with Teams of Agents The slow part is no longer writing code. It is proving the agent did the right thing before bad work slips through. * Replace manual QA with screenshot-based walkthroughs that show each feature working, then have a second agent verify the evidence before anything gets approved. * Treat validation as the real control layer by using lint rules, unit tests, and file-level documentation to force cleaner code and make repos easier for agents to navigate. * Ask agents what was hard and build tools around the answer, because that is often where the next bottleneck, cost spike, or hidden maintenance problem starts. The result is a shift from writing every line yourself to building the checks, tools, and structure that let agents work without making a mess. [https://podcasts.apple.com/gb/podcast/getting-humans-out-of-the-way-how-to-work-with-teams-of-agents/id1505372978?i=1000760086660](https://podcasts.apple.com/gb/podcast/getting-humans-out-of-the-way-how-to-work-with-teams-of-agents/id1505372978?i=1000760086660) [https://home.mlops.community/home/videos/getting-humans-out-of-the-way-how-to-work-with-teams-of-agents](https://home.mlops.community/home/videos/getting-humans-out-of-the-way-how-to-work-with-teams-of-agents) [https://open.spotify.com/episode/6R0JoLz4CQSe9Wr4dwCnfT?si=5d6ec3a994e74778](https://open.spotify.com/episode/6R0JoLz4CQSe9Wr4dwCnfT?si=5d6ec3a994e74778) ## Engineering An AI Agent To Navigate Large-scale Event Data - Part 2 Search is easy until the question has two parts, three filters, and nowhere obvious to look. This piece shows how an event-search agent stays useful once queries stop being tidy. * It turns a pile of database query patterns into seven tools the agent can reliably choose between, instead of leaving the model to improvise every step. * It treats tool design as the hard part: self-contained workflows, typed parameters, structured outputs, and errors the agent can recover from. * It shows why prompts still matter, with few-shot examples teaching better tool choice, parameter selection, and multi-step chaining. The result is an agent that can break down messy search questions and answer them with less guesswork. [Read the blog](https://home.mlops.community/home/blogs/engineering-an-ai-agent-to-navigate-large-scale-event-data-part-2) ## IN PERSON EVENTS * Seattle [https://luma.com/ai-agents-summit-seattle] - April 14 * Amsterdam [https://luma.com/i7o74wuo] - April 21 * San Francisco [https://luma.com/p8d635rz] - May 15 ## VIRTUAL EVENTS * Coding Agents Lunch and Learn [https://home.mlops.community/home/events/coding-agents-lunch-and-learn-skill-building-workshop-from-idea-to-evaluation-bzlbvjc1ul?agenda_day=69d3e82956263f6f12e2c767&agenda_track=69d3e82956263f6f12e2c77f&agenda_stage=69d3e82956263f6f12e2c76d&agenda_filter_view=stage&agenda_view=list] - Skill Building Workshop (From Idea to Evaluation) - April 10 ## Legacy Feature [https://forms.gle/8EDvXGizxyFVKfwy8](https://forms.gle/8EDvXGizxyFVKfwy8) --- Source: https://aaif.live/newsletters/mlopscommunity/2026-04-09-qa-the-agent-not-the-code