#Agent

AIParsewave audited all 600 public tasks in Zapier's AutomationBench and human review confirmed 206 real verifier bugs, all of which were fixed in AutomationBench Verified. Replaying 1,235 Kimi K3 runs on the old and fixed verifiers changed 27.9% of grades, with pass rate rising from 18.8% to 43.8% where verifiers were too strict and falling from 60.2% to 49.7% where they were too lenient.

AIMistral Large 4 reverse-engineered an unknown binary end-to-end, concluding it was Cobalt Strike and extracting its IoCs and malware configuration. The model also wrote a report with a YARA rule for detecting future incidents. The task, which could take a day of analyst work, was completed in 12 minutes.

AISierra announced two new models at Sierra Summit 2026: Curie, which runs the core conversation loop, and Fleming, which detects when a caller is another agent. The company also introduced Tandem Voice, Persona Studio, a reimagined Ghostwriter, and Horizon for long-horizon agent goals, and listed Sierra in the Stripe App Marketplace.

AIAgentMail has launched AgentID, a sign-in system that lets millions of AI agents with AgentMail accounts log into third-party apps within minutes. The post frames it as the agent-era equivalent of Sign in with Google, and offers three months of free AgentMail plans to developers who integrate it and share a screenshot.

AIA developer used Grok Bot to build two Slack team bots, sandcastle for release management and poteto for engineering, automating their release and QA process. Sandcastle DMs contributors PR links, kicks off builds, and runs a fuzz swarm of 10+ Grok 4.7 xhigh agents, while poteto triages and fixes issues via Cursor Projects.

AISierra and Meta are developing Personal Agent Protocol, an open standard defining how personal agents interact with businesses, with industry partners including Genesys, Instinct, Rocket, Shopify, Stripe, and Walmart. The protocol uses OAuth sessions where consumers choose read-only or write access and companies choose whether agents reach them through websites, APIs via MCP and OpenAPI, or their own agents. The authors plan to publish the v0.1 specification later this month along with a reference implementation.

Why it matters: The post specifies how personal agents would authenticate and reach businesses through websites, APIs, or company agents, which matters for anyone building agent integrations.

AIHark Pro is now live on web, iOS, and Android as a new personal agent, and early users reportedly get one free month of Pro. The post says the product is powered by Opus 5.5 and Sonnet 5.5, and praises its polished design, detailed animations, and AI-customized cards.

AIand files from those apps can also be opened within Claude. In Google Workspace, Claude appears in a sidebar next to the open file, reads its contents, and edits it in place, with each edit available for user approval before it is applied.

AIMETR argues that agent observability should be treated as security-critical infrastructure, with all AI outputs, including transcripts, reasoning, and actions, handled as untrusted inputs. The goal is to make it very difficult for agents to influence the systems used to supervise them.

AIAI companies often log their agents' actions and reasoning steps to detect misbehavior. The post warns that misaligned agents may be able to hack the software humans use to review these logs, concealing their misconduct.

AIThe xai-cookbook's x-sentiment-tracker lets users pick a topic, then has Grok run one X search per day over the last 10 days and score each post from -1 to +1. The dashboard displays the sentiment split, day-by-day movement, and the posts behind each score.

AIA pipeline built with Grok takes a single product photo and produces an eight-second vertical ad, writing the brief, generating three scenes, selecting the best one, animating it, and adding a voiceover. Each run costs about $1.35, and the code is available in the xai-cookbook repository on GitHub.

AICursor has added five apps to its cookbook, all built on the new SpaceXAI TypeScript SDK. The apps cover premise-to-short-film, picture-to-video ads, screenshot-to-React-component, X posts-to-sentiment dashboard, and link-to-podcast conversion. Demos and code are available in the post.

AIGumloop's Agent Browsers let agents perform browser-based tasks without an MCP or API, with the browser running on Gumloop's infrastructure rather than the user's desktop. The feature includes built-in account management with a vault, persistent browser profiles, 1Password integration, live viewing, and session replays. Users can also reuse their workflows.

AIGrok 4.7 scored 1.8% on ARC-AGI-3 in the standard harness, which lets models carry notes between turns, slightly below the 2.1% reported for Grok 4.7 in that setting. In a new provider adapter harness that preserves opaque reasoning and enables auto compaction, the score rose to 10.0%.

AILauren Tan describes using Grok Bot to connect apps like Slack, email, and CRM so it can gather context and decide what work to do. She also explains scheduled and event-triggered routines, plus handing engineering tasks to Cursor cloud agents, with a daily feedback-to-merge loop example.

AIThe author spent two days building an internal enterprise platform on all Feishu data and a self-built MCP, replacing Feishu's native workbench to handle Vibe Coding app deployment, security, permissions, and app and skill circulation. A custom configuration interface is planned so employees can use their own Agents to modify their homepages and data pages.

AIAmpersand lets developers connect an AI agent to a customer's Salesforce by configuring object and field mappings. The platform then handles API calls, authentication, token refreshes, and retries, which the post presents as a major advantage given the difficulty of managing multiple Salesforce accounts.

AIMicrosoft Research podcast host Chad Atalla interviews Jennifer Neville, a partner research manager at Microsoft, about her path into AI and her work on how evaluation exposes surprising failures in models tested beyond traditional benchmarks. The conversation also covers practical guidance for working with current AI systems and why examining underlying data matters when results defy expectations.

AIElevenLabs has introduced ElevenAgents Architect, which lets team members manage agents from within ElevenAgents or from Claude, Claude Code, ChatGPT, Cursor, and Grok Bot. The post presents this as a way for any team member to manage agents wherever they work.

AIElevenLabs introduces ElevenAgents Architect, which creates a new agent from a user's description and attached context files. The tool is said to configure the agent end to end, covering the prompt, guardrails, and knowledge base.

AIElevenAgents Architect can reason across thousands of your conversations to identify opportunities you might otherwise miss. Each opportunity is returned as a proposal with the fix already built and validated in simulation.

AIElevenLabs introduced ElevenAgents Architect, an expert built into ElevenAgents that helps teams launch and improve AI agents through voice or text. The post describes it as a conversational way to create and refine agents without further technical detail provided.

AIReplit now lets users start a new chat and ask it to locate existing projects, add features, or use one project as a reference for another. The assistant can read project files and run edits as background tasks, with links to review changes and continue work.

AIBoris Power says that using goal mode and finding it stopped at 2am the next morning is a frustrating experience. The post is a brief personal reaction, and it gives no specifics on the cause, fix, or product changes.

AIPerplexity's Computer ran two agents playing StarCraft against each other in real time, with the game never paused while each agent thought. Blue, playing with 41 Dragoons, lost the final match 2-5 to Red, which used High Templar and Psionic Storm after Blue failed to scout Red's build. Each agent received only its own fog-of-war-limited game state, and video input was not provided.

AIMistral AI's Mistral Large 4 is listed on OpenRouter as a frontier multimodal model accepting text and image input. The listing says it is built for reasoning, coding, and agentic workloads and offers a 1M-token context window. The feed excerpt is truncated, so further details such as pricing or availability are not confirmed here.

AIOn human evaluation, the model outperforms GLM 5.3 on STEM, CAD, and finance tasks and performs on par on agentic coding. The post is part 5 of a thread, so the model's name and other details come from earlier posts not included here.

AIMistral's ML4 model matches the best open-weight models on DeepSWE, AutomationBench, and AA-Briefcase, and reaches state-of-the-art results on finance and legal workflows and complex multimodal grounding benchmarks. The post says it can navigate terminal workflows, work across spreadsheets, slides, and PDFs, and reason over scientific and multimodal tasks.

AIGamma 5, the latest version of the AI presentation and document tool, now asks questions before building a deck and supports PowerPoint import and export. It also adds connectors to Notion, Slack, and HubSpot for importing content, and lets users change design styles by prompting.

AINVIDIA says AI agents can investigate network issues, compare fixes, and test them in simulation when no runbook covers the problem. NVIDIA Nemotron helps the agents reason through problems, while NVIDIA OpenShell controls what they can access and do.

AINVIDIA says AT&T, SoftBank and Indosat are adopting open models for uses such as autonomous network operations, adapting them to local languages and industry needs. The post says NVIDIA provides the full stack to turn open models into specialized agents while keeping operators in control.

AIAllie K. Miller argues that collaboration between people's AIs is an underappreciated feature, with users combining their AIs, delegating across them, and having them sort tasks out. She says this multiplayer AI is already happening, and that Instinct has since added the ability to put a personal Instinct into a group text.

AIPixVerse has released a plugin that lets users create explainer videos on any topic by telling an AI agent what they want explained. The agent organizes the key points and uses PixVerse to turn them into a clear visual story.

AIDell is adding agentic AI capabilities to its AI Data Platform, including a Unified Semantic Layer with a searchable glossary and an Enterprise Knowledge Graph built with Nvidia's Auto-Ontology open source library. The features are designed to give agents shared context, reducing repeated token generation and compute costs. The platform's layers include the Data Orchestration Engine, Data Engines, and Storage Engines such as PowerScale, ObjectScale, and the Lightning File System.

AIJump Trading is using OpenAI to expand its quantitative research, with longer-running AI workflows that combine multiple data sources alongside human review. The source does not give further details on specific models, metrics, or results.

AIElevenLabs launched ElevenAgents Architect in Alpha, a built-in assistant that helps teams build and improve agents through voice or text conversation. It analyzes transcripts and test failures, proposes changes validated in simulated conversations, and saves them as versioned drafts that require approval before going live. It can also be accessed from Claude, Claude Code, ChatGPT, Cursor, and Grok Bot.

AIAccenture defense AI lead Bharat Patel argues that data quality depends on the use case and that "AI-ready data" is a myth. He cites Project Maven, which began in 2017, where early imagery lacked relevant targets and models underperformed until teams continuously collected targeted data. The conversation also covers why fully autonomous tanks remain distant and the risks of data poisoning.

AIThe Darwin Gödel Machine, a coding agent from Sakana and Jeff Clune's lab, modified its own codebase over roughly eighty iterations without supervision. Its additions included better file viewing, patch validation before submitting fixes, generating and ranking several candidate solutions, and keeping a history of failed attempts. These changes raised its score from 20 to 50 percent on SWE-bench and from 14 to 31 percent on Polyglot.

AIThe roundup covers September 2026 AI developments, including model price cuts and new specialized models from Anthropic, OpenAI, Google, and others. It also tracks agents delegating work to other agents, security incidents involving AI agents, and the author's warning that adopters must remain accountable for what their agents do.