--- title: "Don’t Press That Button" newsletter: "MLOps Community" date: 2026-03-26 source: https://aaif.live/newsletters/mlopscommunity/2026-03-26-don-t-press-that-button --- # Don’t Press That Button *Plus... why your eval harness lied, five hidden gems, and the free CV guide* *MLOps Community — Agentic AI Foundation, 2026-03-26* We’ve released a free practical Computer Vision guide on what breaks once models leave the notebook - shifting data, real-world constraints, and why accuracy isn’t the whole story. This week’s ML Confession shows what happens when you skip that step. Download it here. [LINK TO BE ADDED] ## Unsafety harness Most teams optimising model choice are solving the wrong problem. The harness is doing more work than the model ever will. Are you tuning the engine or fixing the car? [HARNESS](https://gatewaze.mlops.community/offer/surveys/?sid=yesno&question=Most+teams+optimising+model+choice+are+solving+the+wrong+problem.+The+harness+is+doing+more+work+than+the+model+ever+will.+Are+you+tuning+the+engine+or+fixing+the+car%3F&y=HARNESS&n=MODEL&oneclick=true&accept=true) [MODEL](https://gatewaze.mlops.community/offer/surveys/?sid=yesno&question=Most+teams+optimising+model+choice+are+solving+the+wrong+problem.+The+harness+is+doing+more+work+than+the+model+ever+will.+Are+you+tuning+the+engine+or+fixing+the+car%3F&y=HARNESS&n=MODEL&oneclick=true&accept=true) ## Open for business Surprisingly close about what's keeping you awake at night between model errors or system failures. ## Have You Secured Your Spot at the DevConnect Global Roadshow? 🌍 Get ready to go way beyond the documentation. Databricks DevConnect [https://www.databricks.com/events?event_type=devconnect®ion=all] is a global, high-energy roadshow bringing hands-on sessions to the world’s leading tech hubs. This is the ultimate destination for data engineering and AI innovation. No high-level fluff, no sales pitches, just raw technical deep dives, architectural breakdowns, and real-world tactical advice from the people actually building the future. Why DevConnect? * Dive Deep: Tear down complex architectures and master the latest Lakehouse features, from Lakeflow to Agent Bricks. * Expand Your Circle: Connect and collaborate with a global community of developers who face the same challenges you do. * Level Up Your Career: Learn the workflows and hacks that make you a faster, sharper, and more effective developer. Global Tour Dates The roadshow is moving fast. Secure a spot in your city: March 31📍 Bellevue, WA April 1📍 Vancouver, CA April 14📍 Austin, TX April 16📍 Denver, CO April 28📍 Munich, Germany April 29📍 London, UK REGISTER TODAY [REGISTER TODAY](https://www.databricks.com/events?event_type=devconnect®ion=all) [https://www.databricks.com/events?event_type=devconnect®ion=all](https://www.databricks.com/events?event_type=devconnect®ion=all) ## Curated finds to help you stay ahead ## A New Kind of Marketplace When a filter button got mistaken for a bulk action, dealers refused to press it. That's where real agentic deployments break. * Open-ended chat causes paralysis or overreach; preset prompts that feed into chat gave users a clearer mental model and led to natural follow-up questions. * Agentic trust has to be earned in stages - show data first, confirm before acting, automate last. * The deeper infrastructure gap isn't the agent itself but the discovery and escrow layer that lets buyer and seller agents transact autonomously and at scale. The agents that reach production will be the ones people were willing to let act. [https://podcasts.apple.com/us/podcast/agentic-marketplace/id1505372978?i=1000756364469](https://podcasts.apple.com/us/podcast/agentic-marketplace/id1505372978?i=1000756364469) [https://home.mlops.community/home/videos/a-new-kind-of-marketplace](https://home.mlops.community/home/videos/a-new-kind-of-marketplace) [https://open.spotify.com/episode/6Ku6yZuWvcKS0J9sXEJNUT?si=5f11f83e978144d2](https://open.spotify.com/episode/6Ku6yZuWvcKS0J9sXEJNUT?si=5f11f83e978144d2) ## The Illustrated Guide on How to Use AI Coding Platforms A model was scoring 45% on internal benchmarks. The team assumed the model was the bottleneck. They were wrong - a bug in the harness was. Fix the harness, the score jumps to 65%. * Keep context windows under 50-80% capacity; beyond that, accuracy drops and hallucinations rise, regardless of advertised window size. * Brownfield and greenfield are opposite problems: existing code constrains arbitrary decisions, but greenfield needs explicit harness definitions before the AI touches anything. * Start a fresh chat to debug. The window that built the bug has already convinced itself the approach was correct. The model is rarely what's failing you. [Read the blog](https://home.mlops.community/home/blogs/the-illustrated-guide-on-how-to-use-ai-coding-platforms) ## CALL FOR SPEAKERS PyConAU [https://www.linkedin.com/posts/nletcher_python-cfp-pyconau-activity-7440124889316954112-CNIL/]'s call for speakers closes March 29, so you'll have to be quick if you want to be part of the MLOz Community. ## IN PERSON EVENTS * London [https://luma.com/h57hqyvq] - March 26 * Lagos [https://luma.com/gcgmri06] - March 28 * New York [https://luma.com/uk9vvgal] - April 8 * Seattle [https://luma.com/ai-agents-summit-seattle] - April 14 ## VIRTUAL EVENTS * Ship Agents: A Virtual Conference [https://home.mlops.community/home/events/ship-agents-a-virtual-conference-zzr92e4gsi?agenda_day=69b2b893d6b7fbe3b94ffdbf&agenda_track=69b2b893d6b7fbe3b94ffdd6&agenda_stage=69b2b893d6b7fbe3b94ffdc5&agenda_filter_view=stage&agenda_view=list] - March 26 ## Shelf Awareness [https://forms.gle/8EDvXGizxyFVKfwy8](https://forms.gle/8EDvXGizxyFVKfwy8) --- Source: https://aaif.live/newsletters/mlopscommunity/2026-03-26-don-t-press-that-button