MLOps news and analysis on Web Pulse: 3370 curated articles tracking the latest MLOps developments, tools, and research, updated continuously from vetted sources.
Gartner formalized AI SRE as an analyst category in January 2026 and projects that 85% of enterprises will use AI SRE tooling by 2029, up from less than 5% today, according to its Market Guide for AI SRE Tooling, 2026. I…
Developer 0xSero released model-toolkit, a GitHub repository of standalone Python tools for evaluating, observing, pruning, and quantizing language models, drawn from the REAP and EXL3 experiments including the GLM-5.3 f…
A developer ran four text-analysis trials on the AIDBDeveloper platform to measure how small workflow design choices affect token usage, caching, and cost across several thousand API requests and millions of tokens. The …
A developer argues that frozen golden-file tests for AI agents break down when serving models change, producing false failures on cosmetic wording while missing real behavioral drift. The proposed workflow replaces stati…
AWS released AgentCore Runtime V2 on September 18, 2026, a microVM-based agent runtime that achieves a P75 cold start latency of 1.9 to 2.0 seconds for images from 200MB to 2GB, down from the 5.4 to 30-second cold starts…
Honeycomb contributed its adaptive_tail_sampling processor to the OpenTelemetry Collector, re-expressing the adaptive sampling algorithms behind Refinery and dynsampler-go in OpenTelemetry-native terms. The processor, bu…
A developer argues that LLM completions should be handled as asynchronous jobs rather than held HTTP connections, proposing a 202 Accepted pattern with a persisted job row, idempotency key, and token budget. The proposed…
A developer has revised their codex-workflows and claude-code-workflows agent review processes to add an outcome-based check that forces coding agents to justify proposed work against the user's actual requirements befor…
Warp, the AI-powered terminal and software factory platform led by co-founder and CEO Zach Lloyd, ships 2,000 pull requests a month through its cloud-based software factory, which runs a Slack → Linear → GitHub → QA work…
Monday.com detailed how it runs evaluations for AI agents against real dependencies in a webinar recap. The engineering-focused session covered the company's approach to testing LLM-based agents in production-like condit…
Monday.com AI Engineering Director Dor Cohen detailed how his team runs agent evaluations against a live staging Kubernetes cluster instead of mocks, using the mirrord tool to connect local or CI eval processes to real d…
A developer argues that finance agents need a repeatable evaluation harness rather than just better system prompts to ensure reliable accounting automation. The proposed harness scores agent outputs across schema validit…
A governance-first personalization architecture that places consent, fatigue, channel sensitivity, cost, and explainability inside the decision path rather than in a downstream analytics sidecar is detailed in an open-so…
A blog post argues that traditional prose runbooks are an architectural dead end in the AI era because AI agents cannot read Grafana screenshots, SSH into bastion hosts, or run scripts from personal home directories, and…
A developer has built the Neuron AI Classifier, a new PHP framework component that routes agent decisions to TypeSafe AI's Jev, a non-generative "System One" model released September 15 that returns probabilities for pre…
A developer at Tiger Tribe Heineken detailed a method for instrumenting .NET AI applications with OpenTelemetry and exporting traces to Langfuse, which currently lacks an official SDK for ingesting OpenTelemetry data. Th…
A developer built a production-style multi-agent orchestration system using Python/FastAPI, LangGraph, PostgreSQL, Redis, ChromaDB, Celery, OpenTelemetry, and React, then documented three bugs encountered after the initi…
A developer published a technical breakdown of AX, Google's open-source agentic orchestrator, which models AI agents as stateful graphs with explicit transitions, retries, and checkpoints rather than prompt-chaining sequ…
A developer built an omnichannel shopping assistant that shares long-term memory between a text chat agent and a real-time voice agent using Amazon Bedrock AgentCore Memory, Strands, and Amplify Gen 2. The system uses Ag…
A developer argues that large language models belong inside two layers of a four-layer recommendation stack — semantic feature extraction and evidence selection — rather than replacing the deterministic ranker that produ…