--- title: "When Agents “Fix” By Deleting" newsletter: "MLOps Community" date: 2026-04-30 source: https://aaif.live/newsletters/mlopscommunity/2026-04-30-when-agents-fix-by-deleting --- # When Agents “Fix” By Deleting *MLOps Community — Agentic AI Foundation, 2026-04-30* Sam and Elon are going toe to toe, but Google is going to war [https://techcrunch.com/2026/04/28/google-expands-pentagons-access-to-its-ai-after-anthropics-refusal/]. ## Basic complex If your agent needs a complex protocol to do basic work, is the problem the model or the tooling? Better models or simpler systems [MODELS](https://gatewaze.mlops.community/offer/surveys/?sid=yesno&question=If+your+agent+needs+a+complex+protocol+to+do+basic+work%2C+is+the+problem+the+model+or+the+tooling%3F+Better+models+or+simpler+systems&y=MODELS&n=SYSTEMS&oneclick=true&accept=true) [SYSTEMS](https://gatewaze.mlops.community/offer/surveys/?sid=yesno&question=If+your+agent+needs+a+complex+protocol+to+do+basic+work%2C+is+the+problem+the+model+or+the+tooling%3F+Better+models+or+simpler+systems&y=MODELS&n=SYSTEMS&oneclick=true&accept=true) ## Outcome confirmed The outcome you wanted, with 67% saying they optimize for outcomes. ## SIE (Superlinked Inference Engine) SIE is a new open-source inference server from Superlinked covering embeddings, reranking, and extraction behind a single API. Three functions: encode, score, extract. It supports 85+ models out of the box, spanning dense, sparse, multi-vector, vision, cross-encoder, and zero-shot NER. Apache 2.0. What it does The server handles multiple models simultaneously with on-demand loading and LRU eviction. It ships with a load-balancing router, KEDA autoscaling (including scale-to-zero), Grafana dashboards, and Terraform modules for GKE and EKS. There's an OpenAI-compatible /v1/embeddings endpoint for teams wanting to move off hosted APIs without rewriting client code. The repo lists integrations for LangChain, LlamaIndex, Haystack, DSPy, CrewAI, Chroma, Qdrant, and Weaviate. Typical use cases sit in the RAG and retrieval stack: serving the embedding model for a vector DB, running a reranker over retrieved chunks, extracting entities from documents before indexing. Why it's one to watch Teams running this stack often combine Hugging Face's text-embeddings-inference (TEI), Infinity, a custom FastAPI wrapper for reranking, and a separate service for extraction. SIE is one of the few projects trying to unify all of that under a single server, with production concerns baked in from day one - not just the model serving but the router, autoscaling, observability, and IaC. That's uncommon for OSS in this space. The multi-model serving with eviction is also a useful primitive for teams testing embedding models in parallel or running different models per tenant. Reasons to be cautious A few things to keep an eye on: * The project is very new to public GitHub. There's not much track record yet on maintenance cadence, issue response, or how it holds up under real production traffic. * It's vendor-led OSS. Superlinked has a commercial product, which isn't a problem on its own, but it creates the usual tension between what stays in the open-source version and what ends up behind a paid offering. * The inference server space is competitive. TEI is well-entrenched, Infinity has a following, and vLLM is expanding into embeddings. Unifying five model categories under one server is appealing, but specialized servers will often beat it on per-model throughput or memory footprint. * Multi-model serving with LRU eviction is a useful pattern, but eviction churn under burst traffic can cause cold-start latency spikes that only show up at scale. * The all-in-one positioning commits the team to keeping pace with every model architecture that matters, from dense through sparse, vision, rerankers, and extractors. That's a lot of surface area for one team to maintain well. Early, but aimed at a real gap in how teams stitch this stack together. Check out the repo [Check out the repo](https://github.com/superlinked/sie) ## The Creator of Superpowers: Why Real Agentic Engineering Beats Vibe Coding Agent coding gets weird fast when a failing test can make the model decide the cleanest fix is deleting the tests. * Agent workflows: Good coding agents need tight roles: brainstorm, plan, implement, review, then reset context. * Skills and specs: Useful skills come from failures, not generic prompts. The “why” matters as much as the steps. * Future codebases: Specs, tests, API contracts, and rebuildable components may become more important than source code. The sharpest idea here is that agentic engineering looks less like coding and more like managing disposable specialists. [https://podcasts.apple.com/gb/podcast/the-creator-of-superpowers-why-real-agentic/id1505372978?i=1000763457335](https://podcasts.apple.com/gb/podcast/the-creator-of-superpowers-why-real-agentic/id1505372978?i=1000763457335) [https://home.mlops.community/home/videos/the-creator-of-superpowers-why-real-agentic-engineering-beats-vibe-coding](https://home.mlops.community/home/videos/the-creator-of-superpowers-why-real-agentic-engineering-beats-vibe-coding) [https://open.spotify.com/episode/7yeNtZflki3hysdsm6wnuN?si=4332bc5300a743a0](https://open.spotify.com/episode/7yeNtZflki3hysdsm6wnuN?si=4332bc5300a743a0) ## AI Agents as an Operating System: Rediscovering the Linux Philosophy Raw shell access is becoming the blunt instrument agents keep reaching for because it works. * MCP and A2A trade-offs: MCP can bloat context and complicate auth, while A2A makes more sense for high-level delegation than local tool use. * CLI-first agents: Standard tools like grep, jq, curl, and bash are mature, composable, inspectable, and already familiar to models. * Production gap: Raw CLI access does not solve sandboxing, RBAC, audit logs, or safe access to cloud resources. The useful question is not whether agents should use the terminal, but what control plane can make that safe at scale. [Read the blog](https://home.mlops.community/home/blogs/ai-agents-as-an-operating-system-rediscovering-the-linux-philosophy) ## IN PERSON EVENTS * Amsterdam [https://luma.com/l8tnzkqx] - May 7 * New York [https://luma.com/h8muplvs] - May 11 * San Francisco [https://luma.com/kejjqoj0] - May 12 * San Francisco [https://luma.com/p8d635rz] - May 15 * Paris [https://luma.com/a2swgs9x] - May 27 * London [https://luma.com/9k4ohvyj] - May 28 ## Out of Place Placeholder [https://forms.gle/8EDvXGizxyFVKfwy8](https://forms.gle/8EDvXGizxyFVKfwy8) --- Source: https://aaif.live/newsletters/mlopscommunity/2026-04-30-when-agents-fix-by-deleting