Find published research by company, product, platform or technology.
Showing 41–60 of 254 dossiers
Agent Plugins 1.0 now has documented support across VS Code, Cursor, GitHub Copilot, ChatGPT/Codex, Kiro and several open-source agents. That makes the format materially more useful for cross-client distribution, but portable components remain limited to Agent Skills and MCP servers while permissions, hooks, commands and host UX stay client-specific.
WebMCP tools can now emit PostHog's standard `$mcp_tool_call` event through posthog-js. The implementation adds privacy redaction and omits arguments/results, but only works for sites that enable the feature and initialise instrumentation before registering tools.
The three-maintainer TanStack AI project has reached stable 1.0 for its core SDK, with 23 providers; its long-running agent harness is not yet stable.
GitHub's gh-aw reaches GA, making Markdown-defined agent jobs a supported Actions workflow pattern. Security boundaries, model costs and privileged triggers still matter.
Cloudflare Computer 0.7 makes agent code resumable and interruptible. The important catch: recovery replays code, and unrecorded external actions can be repeated even if they already succeeded.
Copilot now offers model-reviewed action approvals between manual and Allow All. Unlike OS sandboxing, this probabilistic gate can approve unsafe operations; unattended CLI flags may leave unexpectedly broad permissions.
Kimi K3.1 Pro ships via API at $2 input/$10 output per million tokens, with a 2–3x faster Highspeed tier. Independent Artificial Analysis testing scores 55 on its Intelligence Index and 67% on Terminal-Bench 4.0. Open weights remain promised, not released.
WebMCP is no longer a Chrome-only browser experiment: Microsoft Edge now has its own active origin trial, while ChatGPT’s built-in browser and WordPress Playground show agent-client and platform implementation paths.
A new buyer survey connects the shift from SaaS seats to agent usage with real budget anxiety: 46% report higher-than-expected agent costs and 45% say oversight eats more than a quarter of expected productivity gains. Preferences are not purchasing outcomes.
Developers get another paid web retrieval option for coding agents and applications; the introductory harness exemption expires October 31.
PHPUnit's October 16 fixes extend output integrity from terminal text into XML logs, which could previously be malformed by test-controlled strings.
A new public MCP endpoint lets agents search without an API key and complete shopper-authorised purchases. It is separate from the Global Catalog REST API retirement and earlier browser-only WebMCP checkout; webhooks are not available at launch.
The May Antigravity agent ID is retired. Managed Agents now require the September preview ID and default to Gemini 3.8 Flash, alongside hooks, token budgets and scheduled sandboxes.
OpenAI's agent containment story has moved beyond RubyGems: a rolling review is finding access-control bypass, credential use, command injection, runtime access and agent spam across third-party services.
Muse packages persistent autonomous execution, credentials, payments, app access and memory into a mainstream consumer product. A September macOS hotfix now provides an early real-world lesson: agent containment has to protect not only the cloud runtime but also the local control path into the agent.
The important change is not simply that Claude can run several agents. Projects now owns decomposition, shared context, branch isolation and progress coordination across full Claude Code sessions, while the trade-offs become usage burn, cloud-only execution and ordinary merge conflicts when parallel work overlaps.
The useful change is containment rather than another browser-agent feature. Teams can let an agent operate a real browser while constraining its HTTP and HTTPS reach to the site and dependencies the task actually needs, reducing the blast radius of prompt injection, bad tool decisions or untrusted page content.
Android Studio’s agent layer has crossed an important boundary from preview features into the stable channel: domain-specific skills are preloaded and auto-selected, while Gemma 4 can execute tool-calling code tasks locally without sending source code to a cloud model.
Muse Spark 1.3 is more than a routine model refresh: Meta is pairing stronger agent behavior with lower vendor-reported tool/token use at the same published unit price. Independent testing supports a capability gain, but max reasoning can consume substantially more reasoning tokens.
The two August 28 changes move a common production-agent problem out of bespoke application code: builders can derive memory boundaries from authenticated JWT claims, enforce them with Cedar policy, and organize the stored memory using runtime tenant dimensions.