Agents

AIArtificial Analysis has released Harvey LAB-AA, an evaluation built on Harvey's LAB dataset and developed in collaboration with Harvey. Full results are published on the Artificial Analysis evaluations page, alongside Harvey's commentary on the benchmark and human expert preferences.

AIAmazon Bedrock AgentCore payments lets AI agents pay for model inference one request at a time, using x402 with USDC on the Base network. Incarna used the service to connect its agents to BlockRun, a pay-as-you-go router serving more than 90 models from more than 15 providers. Spending limits are enforced at the infrastructure layer, outside the model.

AIThe NVIDIA KGMON team placed second in the KDD Cup 2026 Data Agents competition with a system built around a smaller, clearer, and easier-to-verify agent harness. The competition required agents to answer natural-language questions over heterogeneous sources, including databases, CSV and JSON files, prose documents, PDFs, and briefing videos.

AILauren Tan invites users of Grok Bot on Omarchy and developers building plugins for it to share feedback and feature requests. The post points to the Omarchy plugin catalog and asks what integrations could be supported. Background from DHH says SpaceXAI joined the Omacom Foundation as a Founding Corporate Patron, contributing $1,500,000 in Grok tokens for Omarchy's maintenance and development.

AITessl argues AI code review is slow because generated code outpaces trust, and proposes executable specs that let agents check preview environments against product intent. Its spec reviewer splits work between a planner agent that extracts requirements and parallel verifier agents that test each one against the code and base branch.

AIGoogle announced at a Google Cloud event a unified Gemini agent that can plan and complete tasks from a single interface, starting with businesses. The agent has its own Workspace account, connects to systems including Google Workspace, Microsoft 365, Slack, and Jira through MCP, and writes an audit trail attributed to the agent. Google said consumers will get access later, after it addresses security, scale, and performance.

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.

AIPocketty is a $99 iPhone and iPad SSH terminal, with a 14-day free trial, that notifies you when an herdr-managed agent is blocked or done. The alert is sealed on your computer for your phone only, and tapping it opens that exact Pane over SSH so you can answer in a real terminal. The source says the relay forwards only sealed bytes and that terminal traffic goes directly between the app and your computers.

AIX's Scotty Beam says Grok Bot, in public beta since August 11, 2026, now gets its own email address, a main bot that coordinates other bots, and expanded access to subscription plans starting at $20 per month. The post says the bot can organize inboxes, research topics, build software, and keep working after users close their laptops. The post also claims the entry price dropped 90%, but does not give the prior price.

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.

AIA five-person sales team built Rasp, an AI sales agent on OpenRouter's Ori, to research every inbound lead. Many leads reportedly get a response in under 60 seconds, saving about 600 hours per month at roughly $30 per day in cost.

AIStepFun's flagship model Step 5 Preview is free to use in Cline for one week. The quoted background says it scores ahead of Kimi K3 and GLM-5.3 on DeepSWE, positioning it among the strongest open-weights coding models.

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.

AIA solo founder used Teamily AI, a platform where humans and AI agents share one group chat, to automate a multi-step project. A research agent analyzed the author's 20 most-saved posts, a writer agent drafted content, a web agent built a live website in Website Builder, and a custom Verification Editor agent blocked the launch twice over a misquoted Anthropic doc. The team can be saved as a Loop that reruns weekly and waits for human approval before publishing.

AIAI SRE Arena is an open, vendor-neutral benchmark that injects faults into a disposable Kubernetes fixture and scores AI SRE investigations with a configurable judge. In its first published comparison across 21 incident scenarios, Edge Delta's native AI investigations detected 18 of 21 incidents, and Grafana's detected 12. Claude, run through each vendor's observability CLI, reached 90.5% root cause analysis accuracy with Grafana's CLI and 85.7% with Edge Delta's.

AICognition engineered its marketing operations around Devin by building each workflow in code with tests, so Devin can run and debug it. Devin connects to nine systems, including Salesforce, HubSpot, Meta Ads, and LinkedIn Ads, and each change shows the exact edit, waits for a confirmation phrase, and reads the result back before reporting it. Cognition says it is hiring marketers and GTM engineers to extend the system.

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.

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.

AIShopify has launched new connectors that let merchants connect Grok to ask questions about their business. The connectors also allow Bot to build a team of agents that help run the business.

AIUnsloth now supports OS-level sandboxing on Linux via bwrap, on Mac via seatbelt, and on Windows via Microsoft's MXC. Per-tool-call latency is under 100ms across all three, and its software-style sandboxing with regex AST checks adds about 3ms. The Windows integration was built in collaboration with Microsoft.

AILauren Tan (@poteto) asks a bot to monitor interesting ways people use Grok Bot on X and send a daily 9am Slack digest. The request also asks for the coolest relevant ideas plus suggestions for improving her workflow.

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.

AIVercel says StepFun's flagship Step 5 Preview, built for agentic coding, research, and finance, is now live on AI Gateway. The model offers a 1M-token context window, accepts text and image input, and uses a 600B-parameter mixture-of-experts design with 27B parameters active.