--- title: "When voice input breaks your stack" newsletter: "MLOps Community" date: 2026-05-28 source: https://aaif.live/newsletters/mlopscommunity/2026-05-28-when-voice-input-breaks-your-stack --- # When voice input breaks your stack *Plus retrieval as an attack surface, coordinating coding agents, and AAIF ambassador applications* *MLOps Community — Agentic AI Foundation, 2026-05-28* We announce we’re joining AAIF, and then MCP moves to a stateless protocol core. Coincidence? Yes. Yes, it is. Still, good to see first-class extensions, trace propagation, and auth hardening in the release candidate [https://blog.modelcontextprotocol.io/posts/2026-07-28-release-candidate/]. ## Not now, Clippy A proactive agent that gets timing wrong is just a push notification with better grammar. What should teams optimize for first: Relevance or Restraint? [RELEVANCE](https://gatewaze.mlops.community/offer/surveys/?sid=yesno&question=A+proactive+agent+that+gets+timing+wrong+is+just+a+push+notification+with+better+grammar.+What+should+teams+optimize+for+first%3A+Relevance+or+Restraint%3F&y=RELEVANCE&n=RESTRAINT&oneclick=true&accept=true) [RESTRAINT](https://gatewaze.mlops.community/offer/surveys/?sid=yesno&question=A+proactive+agent+that+gets+timing+wrong+is+just+a+push+notification+with+better+grammar.+What+should+teams+optimize+for+first%3A+Relevance+or+Restraint%3F&y=RELEVANCE&n=RESTRAINT&oneclick=true&accept=true) ## Don’t Make Yourself Scarce No need to review the results of last week's hot take, you were clear on what’s scarcer. ## Vector Space Day SF: more speakers confirmed Qdrant is bringing Vector Space Day to San Francisco on June 11 for a full day on vector search in production AI systems. The lineup includes talks on retrieval evals, agent memory, GraphRAG, video intelligence, on-device GenAI, robotics, semantic search at Slack scale, and the infrastructure behind 20B+ vectors. Speakers include HubSpot, Google DeepMind, Mem0, Arize, Qualcomm, Slack, LlamaIndex, Neo4j, TwelveLabs, cognee, AWS, Vultr, Adobe, and Qdrant. Register with code MLOPS for 20% off [Register with code MLOPS for 20% off](https://luma.com/vsd-sf) [https://luma.com/vsd-sf](https://luma.com/vsd-sf) ## AAIF wants ambassadors (and yes, there’s swag) There’s been a lot of interest from people who want to get more involved with AAIF, so the foundation has opened applications for its first Ambassador cohort. There are 10 spots, with one project-based contribution a month - tutorials, talks, videos, blog posts, or livestreams - tied to MCP, Goose, or AGENTS.md [http://AGENTS.md]. Ambassadors get: * Recognition on aaif.io [http://aaif.io] * Regular briefings with project maintainers * Early roadmap visibility * Amplification through AAIF channels * Travel support to speak at events * VIP treatment at AGNTCon in Tokyo, Amsterdam, and San Jose, including an Ambassador Breakfast Salon and acknowledgment during the keynote * Actual swag that isn’t a lanyard If you already produce content for the community, run demos, speak at events, or work with any of those three projects, this is a sensible formal step. Submissions for the first intake are open until June 12. The next intake is January 2027. Apply or read more [https://aaif.io/ambassadors/] ## Inside Just Eat's AI Lab: Voice Agents & Agentic Commerce Voice commerce sounds simple until the user is on a bike, hungry, and stuck behind Face ID. * Voice changes the input layer: people give more context when speaking than typing, which can improve recommendations, basket building, and preference handling. * Context has to stay bounded: order history and dietary preferences are useful, but overloading the agent makes accuracy and latency worse. * Incubation needs fast filters: prototypes are tested against desirability, feasibility, and viability before scaling. Voice agents only work when the system can use context without turning helpful nudges into noise. [https://podcasts.apple.com/gb/podcast/inside-just-eats-ai-lab-voice-agents-agentic-commerce/id1505372978?i=1000769602120](https://podcasts.apple.com/gb/podcast/inside-just-eats-ai-lab-voice-agents-agentic-commerce/id1505372978?i=1000769602120) [https://home.mlops.community/home/videos/inside-just-eats-ai-lab-voice-agents-and-agentic-commerce](https://home.mlops.community/home/videos/inside-just-eats-ai-lab-voice-agents-and-agentic-commerce) [https://open.spotify.com/episode/1bkUYvgpihNv4PpSEk4Oe6?si=630c9631234243a6](https://open.spotify.com/episode/1bkUYvgpihNv4PpSEk4Oe6?si=630c9631234243a6) ## An Agent Shouldn't Trust Everything it Reads A planted instruction in a support ticket or retrieved doc can become the thing your agent obeys next. * Retrieved content becomes a control surface: documents, tickets, webpages, and RAG results can smuggle instructions into systems that were only meant to read them. * Tool access raises the stakes: MCP servers, plugins, skills, and internal wrappers need the same scrutiny as executable dependencies. * Monitoring has to include behavior: traces can reveal strange tool use, suspicious retrieved text, and outputs that look fine but shouldn’t exist. Production agents need a hard boundary between what they read and what they are allowed to do. [Read the blog](https://mlops.community/blog/an-agent-shouldnt-trust-everything-it-reads) ## Running Coding Agents Like a Small Engineering Team Last week's Coding Agents Lunch & Learn with Ben Kearns focused on running coding agents like a small engineering team, using Hermes to coordinate agent work across multiple projects, with Burhan Qaddoumi adding a segment on containerized sandboxing. Read the short PDF write-up here [https://go.mlops.community/L&LSession12]. The next Coding Agents Lunch & Learn is tomorrow, May 29, at 5:00 PM BST / 4:00 PM UTC. The session will cover collaborative workspaces for coordinating coding agents across branches, sessions, environments, reviews, and team workflows, plus discussion on recent coding-agent tools and provider updates. Join the next session here [https://home.mlops.community/home/events/coding-agents-lunch-and-learn-session-13-coding-agents-workflows-and-community-show-and-tell-dqk8ixowoo?agenda_day=6a1492a77bc7789edac39c12&agenda_track=6a1492a87bc7789edac39c29&agenda_stage=6a1492a77bc7789edac39c18&agenda_filter_view=stage&agenda_view=list]. ## IN PERSON EVENTS * NYC [https://luma.com/54zz4k5u] - May 28 * Stockholm [https://luma.com/f7o4krel] - June 3 * London [https://luma.com/9k4ohvyj] - June 4 * NYC [https://luma.com/nyc-i97h] - June 4 * Bengaluru [https://luma.com/8zfqurrw] - June 6 * San Francisco [https://luma.com/sf-ohb3] - June 10 * Amsterdam [https://luma.com/6i8pf89q] - June 24 ## VIRTUAL EVENTS * Coding Agents Lunch & Learn Session [https://home.mlops.community/home/events/coding-agents-lunch-and-learn-session-13-coding-agents-workflows-and-community-show-and-tell-dqk8ixowoo?agenda_day=6a1492a77bc7789edac39c12&agenda_track=6a1492a87bc7789edac39c29&agenda_stage=6a1492a77bc7789edac39c18&agenda_filter_view=stage&agenda_view=list] - May 29 * Building Real-Time ML Systems with Zipline + Chronon [https://home.mlops.community/home/events/building-real-time-ml-systems-with-zipline-chronon-2l3sed0h60?agenda_day=6a0db94f3545e18ad39e9a93&agenda_track=6a0db9503545e18ad39e9ac8&agenda_stage=6a0db94f3545e18ad39e9a97&agenda_filter_view=stage&agenda_view=list] - June 10 * Reading Group: Securing the Agent: Vendor-Neutral, Multitenant Enterprise Retrieval and Tool Use [https://home.mlops.community/home/events/securing-the-agent-vendor-neutral-multitenant-enterprise-retrieval-and-tool-use-97o6pxu17x?agenda_day=6a0ada3a99953505591c10a2&agenda_track=6a0ada3b99953505591c10d7&agenda_stage=6a0ada3a99953505591c10a6&agenda_filter_view=stage&agenda_view=list] - June 11 ## Weather or Not [https://forms.gle/8EDvXGizxyFVKfwy8](https://forms.gle/8EDvXGizxyFVKfwy8) --- Source: https://aaif.live/newsletters/mlopscommunity/2026-05-28-when-voice-input-breaks-your-stack