#Agent

AIElvis Saravia argues that building good evals on top of AI systems can put a practitioner at the frontier of their domain or task quickly. He advises readers to learn eval construction, calling it worth the investment. The post responds to Garry Tan's point that agents writing markdown skills on cron jobs can handle most knowledge work.

AICline says users can now run security-related tasks in Cline that were previously impossible with GPT or Claude. The post gives install commands for the CLI via npm and a link to the desktop app.

AIScale AI has released AgentEnv, an open source framework for building high-fidelity reinforcement learning environments. Modal says its Sandboxes can deploy these environments in seconds at the scale RL rollouts require.

AIAnthropic is expanding its Cyber Verification Program to give verified security professionals broader access to its most capable models. Through the program, they can use Claude Mythos 5.1, Opus 5.5, and Sonnet 5.5 with safeguards designed for defensive work. New tiers will also allow authorized offensive work such as penetration testing and red-teaming.

AIClaude Code v2.1.292 adds a --marketplace option to claude plugin install, which adds the marketplace if needed and then installs the plugin from it. The release also adds an effort parameter to the Agent tool and fixes several security issues, including permission prompts bypassed for network (UNC) file reads and a sandboxed read path that could return files outside approved access.

AILangChain is promoting a LangChain Academy course that teaches developers how to build long-running agents for complex workflows using Deep Agents. The post links to the course page and invites readers to enroll today.

AIGitHub has released ReviewBench, a new open benchmark for evaluating AI code review agents, shaped by analysis of 103.9M GitHub pull requests. It contains 219 PRs across 19 languages, and developers can bring their own code review agent, evaluate it, and submit their results.

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.

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.

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.

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.

AIDex Horthy (@dexhorthy) announced episode #77 of his AI That Works series, titled "Building a Memory Pipeline," as a live broadcast. The post provides no further technical details about the pipeline's design, tools, or results.

AIAllie K. Miller suggests giving an AI agent a separate email address, which Instinct does automatically, and using it for junk signups so the agent filters that mail away from your main inbox. She compares it to Google Voice for email and argues retail emails will get less attention unless they give people a reason to reach the human inbox.

AIZeroset announces a $5.2M pre-seed round, co-led by GradientVC and 2048VC with participation from Leblon Capital, to deploy world models in enterprises. The company says it will build models of each enterprise's decisions, dependencies, and unwritten processes from the traces people and agents create across systems, and that companies should own those models. Its first system, Nebula, captures state and traces as work happens.

AILangChain's Sydney Runkle presents a four-step method for building a model router into a coding agent harness: understanding tasks, understanding models, building the router, and tracking task outcomes. The background post says the router cut costs by 64% without reducing quality by sending tasks that do not need a frontier model to cheaper models.

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%.

AIAi2 applied scientist Shashank Gupta says he will attend COLM 2026 from Tuesday through Friday and invites people to talk with the Ai2 Agents post-training team. Topics include post-training for coding and long-horizon agents, such as agentic RL, OPD, data and infrastructure, and multi-agent training, plus opportunities at Ai2. He lists an Ai2 booth session Tuesday 1:30–3pm and an Ai2 mixer Tuesday 6–9pm.

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.

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.