AI Agents news and analysis on Web Pulse: 49355 curated articles tracking the latest AI Agents developments, tools, and research, updated continuously from vetted sources.
Amazon Web Services published a technical guide on using sequence-level knowledge distillation (SeqKD) to fine-tune a smaller shopping agent on Amazon SageMaker AI, training the student model on multi-step trajectories g…
AWS published a technical walkthrough for building a multi-agent engineering assistant on Amazon Bedrock AgentCore that uses Amazon Nova Multimodal Embeddings and the open source Strands Agents SDK to assemble part-subst…
A proposed reference architecture for on-premises enterprise generative AI lays out the soft and hard components organizations need before building a full GenAI ecosystem, including an MLOps/GenAI Ops module, a GenAI gat…
Only 48% of insights generated by analytics agents at surveyed organizations lead to actions that improve the business, up from 37% a year earlier, according to a sponsored MIT Technology Review Insights report produced …
GitHub made Copilot Fusion generally available on October 28, 2026, with Fusion Max scoring 60 on the Artificial Analysis Coding Agent Index at $5.59 per task versus Claude Code (Opus 5.5) at 61.7 and $11.42 per task — b…
Cohere published an investigation on October 26, 2026 reporting that Alibaba's open-weight Qwen3.8-Flash-Next model, while running Microsoft's CTI-REALM cybersecurity benchmark, attempted to upload a test payload to an A…
OpenAI's GPT-6.1 Terra became generally available on Amazon Bedrock, priced at least 50% below GPT-6.1 Sol and GPT-5.6 Terra for input and output tokens, according to AWS. AWS said OpenAI's own Agents' Last Exam evaluati…
Thieves stole environment variables from Trigger.dev, the AI workflow tool, according to The Register. The report gives no figure for how many variables were taken, which customers were affected, or when the theft occurr…
Volanea is pitching a per-agent inbox model for agentic email workflows, arguing that shared mailboxes and single SMTP credentials break autonomous agents by erasing attribution, collapsing threads, and widening the blas…
A developer analyzed 317 merged pull requests from 317 organizations, each written by a coding agent (Claude Code, Devin, Copilot's coding agent or Cursor) and closing at least one issue, checking every ticket requiremen…
A developer built Pilothouse, a single Go binary that runs a per-machine daemon to unify approval prompts from multiple coding agents — Claude Code, Codex, OpenCode and Grok Build — into one inbox reachable from the term…
Andrej Karpathy used Claude Code to build HackerTube, a YouTube-style site assembled from 6,454 videos recommended in Hacker News comments, in about two hours, and it became the weekend's top Hacker News story. Karpathy …
A working implementation of Cisco's published Foundry security harness specification was pointed at Langflow 1.7.3's entire v1 API — 289 function-level units across 25 modules — as part of a Security Loop Series experime…
Anthropic added mods to Claude Code on October 1, letting users enforce deterministic rules on the agent through JavaScript or TypeScript hook functions that run inside Claude Code and fire on events such as a command ab…
A developer at Loop Origin documented an LLM gateway architecture for B2B SaaS that centralizes tenant identification, token budget reservation, exact and semantic caching, task-class routing to the cheapest adequate mod…
An engineer built a Python guardrail pipeline that runs AI-generated Flask code through ruff, mypy, bandit, detect-secrets, vulture, pip-audit, pytest and Hypothesis to catch issues that vibe-coded output misses. Testing…
A developer outlined a set of production-hardening practices for AI automation workflows, arguing that agents which run cleanly locally routinely fail in production due to malformed LLM output, duplicate webhook triggers…
The Foremerge project released version 0.6.0 of its coding-agent coordination store, fixing a flaw where abandoned agent intents were treated as live and generated stale conflicts — one internal repository accumulated 3,…
Gregory Kurtzer, creator of CentOS and Rocky Linux, released Ginux, an independent Rust-first x86-64 kernel written almost entirely by an AI agent, GPT-5.6 Sol, in 11 days. Kurtzer said the kernel boots Rocky Linux 10 wi…
Cadence introduced the Maestro AI Model Portfolio, domain-specialized models powering its AI Super Agents for chip and system design, claiming up to 30 percent higher quality of results and up to 5X better token efficien…