MLOps news and analysis on Web Pulse: 3331 curated articles tracking the latest MLOps developments, tools, and research, updated continuously from vetted sources.
Kong announced at API & AI Summit the evolution of Kong Konnect into an AI Connectivity Platform, with six launches mapped to what it calls the agent connectivity journey. Generally available now are Konnect Catalog, a p…
Kong expanded its AI Gateway with new cost management capabilities that price AI interactions at the individual request level and attribute spend across models, providers, applications, teams, users, and agents, the comp…
Kong previewed advanced AI observability capabilities in Kong Konnect that make the session, rather than the individual request, the unit of AI observability, according to Alex Drag, Kong's Head of Product Marketing. The…
NVIDIA published a tutorial showing developers how to trace Hermes Agent behavior with NVIDIA NeMo Relay, running two Hermes Agent examples and inspecting the resulting traces for model and tool calls, errors, retries, d…
VDURA released v12.0 of its VDURA Data Platform, a generally available multi-tenant, API-driven storage service aimed at GPU clouds and AI factories, CEO Ken Claffey said. The HYDRA-based release adds per-tenant QoS, nam…
Cloudflare expanded its AI Gateway User Insights platform with a model overkill view, task analysis, turns analysis, and a Potential Savings dashboard, all free to AI Gateway users, and put a companion Auto Router tool i…
A developer released modelshift, an open-source CLI tool that scans a repository for retiring model IDs, reports their file and line locations with recommended replacements, and can apply fixes or open pull requests. Run…
Cloudflare launched the public beta of Auto Router, a feature in AI Gateway that automatically routes each AI request to the most cost-effective capable model, with internal tests showing up to 30% cost savings versus us…
A security practitioner outlines a pipeline-first approach to adding AI to security operations, replacing individual steps in existing analyst workflows rather than learning machine learning in the abstract. The approach…
Arize AI is a launch partner for MongoDB's Atlas Agent Engine, a new platform for building, deploying, and governing AI agents in production, with Arize AX adding trace-level observability and evaluation. The integration…
A developer outlines a five-stage AIoT reference architecture — Identify, Sense, Decide, Act, Verify — for building AI applications on industrial sensor data rather than clean databases. The writeup stresses contextualiz…
A developer argues that AI coding agents' terminal execution states like COMPLETED or SUCCESS describe only the runtime's own lifecycle, not the eventual real-world outcome, since evidence such as a pull request being me…
A first-person account from Mudassir Khan reports that a risk scoring pipeline ran for three weeks returning every assessment marked low because the team measured success only by whether the LLM output parsed as JSON, no…
LLMxRay 0.6.0 launched as a free, local observability tool for Ollama models, adding a Cache Lab feature that the project reports delivered 3.5x faster prefill in its test. The tool runs via `npx llmxray` or a Docker ima…
Cloudflare added a model overkill view to its User Insights dashboard, flagging conversations where the selected AI model appears more capable than the task requires and showing which users, agents, and applications driv…
A Vienna-based founder running Postservice.at through Claude Code built a "How I fool myself" section in the project's CLAUDE.md that logs every agent error with its date and root cause, and each new session reads it bef…
A developer built six retrieval pipelines over 2,951 Wikipedia articles in TigerGraph Savanna and benchmarked them on 100 questions using gemini-3.1-flash-lite, finding that an agentic architecture alone added only 3 poi…
A developer built an open-source tool called receipts that reverts each fix in a change and re-runs its tests to determine whether the tests actually fail on the old code, then applied it to 81 maintainer fix commits and…
A developer known as @danisherror has published a self-directed M.Tech program in Networked Systems & Security for AI Infrastructure, a two-year, four-semester self-study curriculum of roughly 15 hours per week (~1,500 h…
Google published two reference architectures for networking AI inference model serving, one built on Google Kubernetes Engine (GKE) and one for all other backend types, both anchored by a Private Service Connect inferenc…