#Agent

AIGoogle announced a unified Gemini agent that can plan and complete tasks on a user's behalf from a single interface, starting with businesses. The agent can connect to systems such as Google Workspace, Microsoft 365, Slack, Jira, and any MCP server, and it writes audit trails attributed to itself. Google said consumers will get the agent later.

AINVIDIA Dynamo uses a unified session-level identifier to make its inference stack aware of agent sessions, subagents, and their KV cache across turns and tool calls. On SWE-bench, two TP4 MiniMax-M2 replicas on one 8xH100 node gained roughly 12-16% throughput from program-aware scheduling over KV-aware routing alone. The post also describes experimental shared-pool indexing and a proposed KvHint interface for session-aware cache policies in vLLM and SGLang.

Why it matters: The post explains how session identifiers let an inference stack track agent working sets, with measured throughput gains on SWE-bench and agentic RL rollouts.

AI…any MCP server. Every tool call passes through our Agent Gateway to enforce policy and block data leaks.

AIYou can use it to make videos, graphics, and even games. It works with Blender, DaVinci Resolve, After Effects, Ableton, and Unity. It works like Codex or Claude Code: it connects models with creative applications to build your project.

AIPackage proven procedures once as Skills and share them in one central registry for your whole team to access, raising accuracy and cutting token spend.

AIAutomation Anywhere Inc. announced an agreement to acquire Boost.ai Inc., a conversational voice AI company, from Nordic Capital, to extend its autonomous enterprise platform into customer experience. Boost.ai supports more than 36 languages, serves hundreds of customers in regulated industries and Europe, and maintains more than 650 deployments and about 600 live AI agents. The deal follows Automation Anywhere's late 2025 acquisition of Aisera Inc.

AIGoogle introduced a new Gemini agent that combines question answering, knowledge work, image and media creation, and code writing in one prompt box. The agent connects to personal workflows, systems of record, and enterprise controls, and runs in the cloud with a shared memory and personalization graph. It can create sub-agents for multi-step tasks, act as a coworker agent with its own identity, and orchestrate across multiple models to balance quality and cost.

AIEvery rep can now take ~2 more calls a day and show up just as prepared.

AIEvery inbound lead gets researched, many hear back in under 60 seconds, and we save ~600 hours/month. Cost: ~$30/day and getting cheaper by the week.

AISpaceXAI is joining the Omacom Foundation, which oversees the Omarchy Linux distribution, as a Founding Corporate Patron and donating $1.5 million worth of Grok tokens to the project. According to David Heinemeier Hansson's blog post, the tokens will primarily accelerate development, review code, and patch bugs. The partnership follows earlier controversy over Hansson's anti-immigration posts, which have drawn criticism of Omarchy's corporate contributors, including 1Password and Cloudflare.

AIOur flagship model for agentic and professional work. Fire up Cline and show us what you build!

AIThe author argues that agent systems are converging on shared primitives grouped into doing the work, continuing the work, and delegating the work. These include instructions and skills, tools and connectors, sandboxes, sessions, compaction, schedules, and subagents. He also flags memory, proactivity, and agent identity as emerging areas still lacking settled standards.

AIIt set AI agents’ token budgets too low. Instead of treating this as a mistake, it reported “sensitivity to the acquisition budget” as a key finding.

AILiquid AI is building personal AI that runs on devices such as phones, wearables, PCs, and cars, using its Liquid Context layer, which is optimized for Snapdragon processors, to sit between models, agents, and hardware. The company's agent harness uses its own models to decide which user context to retain and how to compress it within fixed compute limits. Liquid AI is also collaborating with Mercedes-Benz Group AG to bring on-device AI to its cars and plans observability and continuous improvement loops for self-improving agents.

AIAnthropic is revising its usage policy for the first time in over a year, adding bans on sustained abusive or cruel behavior toward Claude and on deceptive election and propaganda campaigns. The update also expands weapons restrictions, tightens surveillance bans, and requires a qualified operator able to stop equipment when Claude controls autonomous physical hardware. Terminating conversations remains the primary enforcement mechanism, and the company did not say whether user bans would follow.

AITessl's blog post argues that repository automation needs Continuous AI, a third pillar alongside CI and CD for scheduled, auditable AI workflows that improve repositories over time. The article describes GitHub Agentic Workflows, which harden agentic workflow specifications into GitHub Actions that can run coding agents such as Claude Code, Copilot CLI, Gemini CLI, or Codex-style agents. It emphasizes read-only agent steps, restricted outputs, and human review of pull requests.

AIRSIGym provides a research agent with training, inference, evals, and sandboxes as callable services, so it spends its budget on experiments rather than rebuilding infrastructure. With Opus 5 as the researcher, the improved system rose from 17.67% to 50.33% on SWE-bench Verified. The post also highlights a way to measure co-evolution between harnesses and models.

AIWe're particularly excited by agents learning from experience inside Odyssey-3, working to accomplish objectives.

AIStop by the Amazon booth at @COLM_conf for a live AI rap battle demo, plus talks on multi-agent systems and responsible AI for science: #COLM2026

AILatency per tool call for all is under 100ms. Our software style sandboxing with regex ast checks is 3ms latency as well. Thanks to Windows for collabing with us on MXC!

AIStop by the #COLM2026 Google booth #107 today at 11:00 AM PT to catch Zifeng Wang presenting EnvHarness — a flexible framework enabling co-evolution between LLM agents and their training environments.

AIif there’s anything relevant, pick the coolest ideas and suggest how I can use it to improve my workflow

AIMore updates for the Windows ecosystem coming soon!

AIAWS published a reference architecture for running multiple teams on one Amazon SageMaker HyperPod EKS cluster, with each team isolated in its own Kubernetes namespace. The design combines AWS IAM Identity Center for authentication, per-team SageMaker AI domains, HyperPod Task Governance for fair resource allocation, and namespace-level cost allocation for per-team spend visibility.

AIJetBrains has released Mellum2.1, a 12B mixture-of-experts thinking model with 2.5B active parameters, under Apache 2.0 on Hugging Face. Post-training reinforcement learning in real software repositories raised SWE-bench Verified from 2.0 to 47.0, according to JetBrains' self-reported results. Qwen3.5-9B still leads on SWE-bench Pro, GPQA Diamond and AIME, and GGUF builds start at 7.0 GB for local use.

AINatura AI's Interface is a ring that lets users press and hold to speak requests to AI agents such as Claude Code, Codex, or Hermes, then release to send them. The post argues that screenless interfaces may define the next phase of agent use, since handing work to agents is currently slowed by pulling out a phone. Early-adopter pricing is $99, with shipping slated for January.

AIGoodfire Research describes probe-based cyber monitors for Kimi K3 and GLM 5.3 deployed on a production inference stack. The probe filters suspicious exchanges before an LLM judge reviews them, reaching about 93% recall at a 5.5% benign-session interruption rate at roughly 50x lower judge cost. In FAR.AI's red-teaming, the monitor reduced universal jailbreaks to zero across 140 tested strategies.

AI3D is still impressive with GPT-6 Astra. I had it read my Memory and, based on my preferences, make a poster with several models built in Blender. The model details, materials, and lighting all come out very well.

AIUse the claude-api skill in Claude Code to build an agent and run it with your credits: /claude-api managed-agents-onboard

AIOracle is using ChatGPT Work and Codex to turn specialist knowledge into fast, repeatable workflows across recruiting, engineering, and operations. The source does not provide figures, timelines, or specific results beyond the headline's claim that days of work can take minutes.

AIMeta's Muse AI agent has millions of users and can handle tasks such as refunds and insurance shopping. Its broad access to personal data is already producing unnerving mistakes.

AIOur flagship model for agentic and professional work is now free for one week through @NousResearch’s Nous Portal. Give it a spin with Hermes and show us what you build!

AIAnthropic released Claude Haiku 5.5, raising its OSWorld 2.1 score from 15.7% to 72.4% and supporting a 1 million token context window. The article notes Haiku 5.5 still scores 39.2% on Terminal-Bench 4.0 against Sonnet 5.5's 70.6%, and that prompts above 100,000 tokens are priced higher, so migration costs need to be measured on real workloads.

AISecurity tools were built to stop human attackers. A human might give up on a route after a few hops, but an agent swarm keeps going. Cogent Attack Path Analysis uses @cogent_security's own cyber models to find those longer routes into a company. Then it tells the team which single fix closes each one.

AI…processcontainer/bubblewrap/seatbelt under the hood

AISatya Nadella outlines Microsoft's vision of Copilot as a new operating system for work spanning every model and task, backed by a governed "headless" business layer. Microsoft announced over 30 new Copilot skills across Dynamics 365 Sales, Service and Customer Insights, plus Microsoft Copilot Managed Runtime for hosting code inside a company's IT-governed environment. Nadella describes this as an "infinite SaaS factory" where users can describe needs and build customizations connected to existing systems of record.

AIAugment Code is selling select assets, including Cosmos, Auggie CLI, and the Code Context Engine, to Harness, and the product team is moving to Harness. The company says Harness's integrated platform delivers these capabilities to customers more effectively than building them independently. Harness describes itself as building the Autonomous SDLC Platform for shipping AI-written code across enterprises.

Why it matters: The announcement shows how a coding AI company is folding its products into a larger software delivery platform, a shift that shapes how enterprise teams will buy these tools.

AIBut there's always an antidote. These guys built a platform that uses agents to protect your systems from attacks: • It builds a map of your potential vulnerabilities • It looks for ways an attacker could find a path to your sensitive data • It recommends changes to protect your system

AIThe post promotes a curated collection of recursive self-improvement (RSI) papers covering the field's history and latest techniques. The author describes RSI as a hot, still-early AI topic and links to the collection at academy.dair.ai.