--- title: "Context Is the Real Stack" newsletter: "MLOps Community" date: 2025-12-18 source: https://aaif.live/newsletters/mlopscommunity/2025-12-18-context-is-the-real-stack --- # Context Is the Real Stack *Plus free GPU guide, awards, why Agentic RAG reduces hallucinations, how Da2a rethinks data platforms, and what Uber learned about real-time search* *MLOps Community — Agentic AI Foundation, 2025-12-18* In the holiday spirit, I’m sharing our free 2026 GPU Buyer’s Guide. After six months researching the neo-cloud landscape, I put together a guide to demystify hardware, pricing, and cold starts. It’s a practitioner-focused resource, built with Community input, answering the questions your AI tools can't. Enjoy your holidays, and your free GPU guide [https://go.mlops.community/NL_Intro_Dec18_GPUGuide]. ## The RAG Hallucination RAG didn’t fix hallucinations. It made them harder to notice. When something breaks, do you inspect retrieval or ship another prompt? ## You've Got Standards The majority of you see standards as the way to fix fragmentation. ## COMMUNITY AWARDS 2025 ## The OpsCARS 2025 https://go.mlops.community/NL_OpsCARS_Dec18 We’re wrapping up 2025 with The OpsCARS - our end-of-year awards, picked by you. Some categories are serious (Best Original Research, Most Interesting OSS Project). Some are less so (Most Overhyped Term, Most Unhinged Model Response). All of them reflect what shaped the year, for better or worse. Voting is open now. Cast yours and help recognize the people, projects, and moments that defined the year. Vote now [https://go.mlops.community/NL_OpsCARS_Dec18] ## Hidden Gems ## Job of the Week [https://go.mlops.community/NL_Jobs_Board](https://go.mlops.community/NL_Jobs_Board) ## Context Engineering 2.0 Production agents don’t usually fail because the model is dumb - they fail because the system can’t feed them the right context fast, safely, and cheaply. This conversation argues the next bottleneck is “context engineering,” not prompts. * Where MLOps still pays for itself: high-scale, direct-to-money systems like recommenders and fraud, where feature stores keep getting rebuilt because in-house maintenance hurts. * Context as a unified layer: treat unstructured docs, memory, and structured data as one “context surface,” with relationships between them - instead of three separate pipelines that never agree. * MCP as org scaling, not hype: moving tools into servers lets teams evolve context endpoints independently from agent workflows, like microservices for data access. Tie it together and you get the punchline: the winners won’t be the teams with the fanciest agent - they’ll be the ones who control context end-to-end. Video [https://go.mlops.community/NL_Pod1_G_Dec18] || Spotify [https://go.mlops.community/NL_Pod1_S_Dec18] || Apple [https://go.mlops.community/NL_Pod1_A_Dec18] DOES AGENTICRAG REALLY WORK? Agents don’t hallucinate because the model is careless - they hallucinate because the prompt is wrong. This discussion breaks down why the real leverage sits in how prompts are built dynamically, not statically. * RAG’s ceiling: grounding helps, but generic RAG collapses under ambiguity, stale data, and risky actions like SQL generation against production systems. * Agentic RAG as separation of concerns: split work into narrowly scoped agents with their own context, data access, and guardrails, closer to microservices than monoliths. * Dynamic prompts as the control plane: dense embeddings over schemas and docs drive context-aware prompts that guide the LLM, rather than letting it guess joins, metrics, or intent. The payoff is simple: fewer hallucinations, safer systems, and agents that answer the question you meant to ask. Video [https://go.mlops.community/NL_Pod2_G_Dec18] || Spotify [https://go.mlops.community/NL_Pod2_S_Dec18] || Apple [https://go.mlops.community/NL_Pod2_A_Dec18] DA2A: THE FUTURE OF DATA PLATFORMS IS AGENTIC, DISTRIBUTED, AND COLLABORATIVE Waiting days for a simple metric is a clear sign of a broken data platform. This post argues for flipping the stack: instead of one monolithic “source of truth,” run multiple domain agents (sales, marketing, ecommerce) and let an orchestrator stitch answers together. * Shift the bottleneck: move from centralized pipelines and dashboards to domain-owned agents that answer questions directly against their own data. * How Da2a works: a root orchestrator calls remote specialist agents via “agent cards” over an A2A protocol, treating agents as tools. * What breaks next: payload size (A2A is for small JSON/text), agent discovery (hardcoded today), and memory (stateless agents need learning). If this model holds, the next data platform upgrade is organizational - not another warehouse migration. Read the blog [https://go.mlops.community/NL_Blog_Dec18] [Video](https://go.mlops.community/NL_Pod1_G_Dec18) ## A Very Silent Night [https://go.mlops.community/NL_Confess](https://go.mlops.community/NL_Confess) ## Making the hard stuff simpler Working on something tricky or planning ahead? Here’s how we can help - just hit reply: * Custom workshops tailored to your company’s needs * Hiring? I know some quality folks looking for a new adventure * Want to connect with someone tackling similar problems? I can introduce you Thanks for reading, catch you next time! --- Source: https://aaif.live/newsletters/mlopscommunity/2025-12-18-context-is-the-real-stack