MLOps news and analysis on Web Pulse: 3310 curated articles tracking the latest MLOps developments, tools, and research, updated continuously from vetted sources.
Docusign engineers have built more than 220 internal AI agents, called Krewmates, on its Krew agent orchestration platform in just the past few months, saving thousands of engineering hours, according to a company blog p…
Amazon published best practices for administering Amazon SageMaker HyperPod through Amazon SageMaker Unified Studio, laying out four layers of control — organization, project, cluster, and workload — for ML teams sharing…
Amazon Web Services added the ability to create and manage Amazon SageMaker Spaces on Amazon SageMaker HyperPod EKS clusters directly from the Amazon SageMaker Studio UI, letting data scientists and ML engineers launch J…
A developer benchmarked six AWS LLM inference backends — Amazon Bedrock, a SageMaker real-time endpoint, vLLM on two EC2 GPU families, and a hand-ported Gemma 4 build on Inferentia2 and Trainium — all driven by a single …
A developer benchmarked the Serena MCP tool, which gives coding agents IDE-style code navigation and refactoring via a Pyright language-server backend, against an agent's ordinary tools on ten refactorings in the HTTPX P…
RigMark released a reproducible serving benchmark that measures local AI stacks on agent-shaped code and prose workloads, structured output, cache-busting prefill and concurrent requests rather than a single headline num…
Karmendra Pandey, a Practice Architect in AI & ML at TEK Systems, published a line-by-line cost breakdown of a single production-style AI agent task running on AWS Bedrock, showing roughly $0.051 in raw inference cost ve…
Arize Phoenix contributor Ashwin Govind Ugale released tracelint, an open-source linter that runs deterministic structural checks on OpenInference traces and returns a CI-usable exit code, avoiding LLM judges for failure…
Coherent Solutions released a whitepaper introducing a 'continuous delivery loop' framework that replaces fixed handoffs between development phases with recurring feedback across problem identification, validation, engin…
New Relic announced the Ground Truth CLI, augmented with the New Relic Autopilot API, which brings headless observability to developers and AI agents directly in the terminal. The command-line interface lets teams invest…
A developer argues that quantizing small language models for on-device deployment functions as an uncontrolled, unsupervised fine-tune rather than a lossless compression step, silently degrading narrow behaviors like too…
A developer argues that failures in AI-assisted software development stem from poor environment setup rather than the AI tools themselves, describing their own fully autonomous "AI factory" that only became reliable once…
A developer built @vijaypjavvadi/bdd2pw v4.3.2, an MIT-licensed Gherkin .feature-to-Playwright TypeScript scaffolder built on Microsoft's Playwright MCP server, with a paper published in Elsevier SoftwareX in October 202…
A developer published a production checklist for shipping large language model features, arguing that the gap between a working demo and a reliable product comes down to defensive engineering rather than model quality. T…
Meta research found that pairing two AI coding agents to review each other's patches improves bug detection more than increasing a single agent's budget, according to a study tied to the company. Meta's internal RADAR re…
A developer built the official Postman data-source connector for Cognee, an open-source memory layer for AI agents, during Mergetober 2026. The connector ingests Postman collections into Cognee as queryable knowledge gra…
A developer tested how much cloud engineering work could be delegated to AI across AWS, Azure, and Google Cloud, running live Level 2 deployments of a Layer 7 load balancer fronting two private VMs and a Level 3 design-d…
A developer describes how an AI safety platform vendor moved beyond publishing Helm charts on GitHub to solve the broader enterprise software distribution problem, as customers demanded deployments inside their own VPCs,…
A developer built mcpspan, an MIT-licensed, self-hosted analytics tool for MCP servers, after measuring how AI agents actually interact with a demo flight-booking server. The measurements surfaced five failure patterns i…
Snowflake's Cortex Agent GA enhancements add Personal Database sandboxes, session-scoped temporary agents, and COPY GRANTS to the developer-to-production pipeline, letting developers build and validate agents without CRE…