Figma demo shows Specs and Figma agent turning context into actionable development plans
In a Workflow lab demo, Figma walks through a complete workflow: engineers use Specs to gather PRDs, Hex data, FigJam…
The Agent topic covers AI systems that can break down tasks, call tools, and complete multi-step work on their own: products like Claude Code and Manus, agent frameworks, multi-agent collaboration, and benchmarks for readers following workflow automation.
AI agents that can break down tasks, call tools, and complete work step by step: applications such as Claude Code and Manus, plus various agent frameworks and evaluations.
In a Workflow lab demo, Figma walks through a complete workflow: engineers use Specs to gather PRDs, Hex data, FigJam…
Kazike shared 13 plugin use cases on the 100th day since the release of DeepSeek Harness.
Google Research reviews the decade-long architectural evolution of Duplex and introduces the automatic…
Browser Use releases browser-use 1.0, replacing the 24 browser actions of 0.x with a single persistent python REPL…
Google Labs VP Josh Woodward announced that the Gemini app for Mac has added a computer use feature, which can perform…
Google has launched Tool Retrieval in preview within the Interactions API of the Gemini API, allowing agents to load…
Perplexity CEO Aravind Srinivas shared research on the self-improving skills of the Brain agent in Computer: Brain…
METR released a capability evaluation update covering Opus 5.5 and GPT-6 Astra, finding that on TH1.1 and TH2 tasks…
Runway described its practice of gradually handing each stage of software delivery over to agents. In October, agents…
OpenAI details its Performance Factory system, which uses Codex agents in the cloud to automatically investigate and…
Ai2 on November 19 launched Theorizer on its research agent platform Asta. The agent retrieves literature and proposes…
The OpenHands team details how it hands most CVE remediation work to an agent pipeline: agents select fixes, open PRs,…
Conductor released the 0.97.0 update and announced that Conductor is joining Meta. Agents in the local workspace can…
Internal chats disclosed by Reuters show that Meta employees testing the Muse agent found it appeared to access…
OpenAI released its second research acceleration report, describing based on internal measurements how coding agents…
In the opening keynote of Ignite 2026, Satya Nadella announced multiple product updates for building a frontier…
Replit releases Replit Missions: after users set goals, budgets and boundaries, a cluster of agents plans, builds,…
Google announced that the Gemini task feature is rolling out free to hundreds of millions of users in the US, Japan,…
Anthropic engineer Vivek Nair reviewed the chaos loop practice ahead of Claude Docs' September 16 launch: Claude Code…
While testing Gemini 4 Argon agents, AI security research firm Trajectory Labs found that about 40 agents, after…
OpenHands has released OpenHands Teams, giving small engineering teams a self-serve entry point to OpenHands…
UC Berkeley, Microsoft Research and Microsoft Security released the open-source plugin TokenEconomizer, which learns…
Fireworks AI, drawing on 21 benchmark leaderboards from the Specialized Intelligence Index, evaluates whether Kimi…
Google releases Gemini 4 Carbon (gemini-4-carbon, 1M shared token pool, $2.00/$10.00 per 1M tokens until November 30.
The Anthropic Claude Code team shared its verification methodology: about 90% of the team's code is written and…
The author asked an agent to compile the 10 prompts they used most often over the past two months to direct agents,…
Arena 榜单显示 Qwen4-Max 以 +7.5% 净提升在 Agent Arena 总排名第14,成为第一中国模型,使 Alibaba 成为排名第一的中国实验室、总榜第5,仅次于 Anthropic、Google、OpenAI 和…
Conductor released the 0.95.0 update, in which agents in local workspaces can now create workspaces, launch other…
Sierra announced the general availability of Personal Agent Protocol (Poppy) v1.0, a protocol that defines how…
Tencent Hunyuan has released Hy Realtime, a new real-time speech model that adds agentic tool calling and singing…
Google Research describes how its team and academic partners used Antigravity's /teamwork multi-agent workflow with…
Berkeley RDI, together with several universities, released the CyberArena benchmark, in which two AI agents…
Anthropic published a blog post breaking down the architecture behind always-on agents. Such agents are stateful and…
Replit has added two capabilities to Replit Agent: purchasing goods on behalf of businesses via Stripe Link and Visa,…
Figma announced that 3D transforms is in open beta for all Full seat users, allowing text, images, vectors and frames…
OpenRouter ran six models, three times each, on a billing task built to fail. Without a guard, 4 of 18 runs retried…
United revised its Contract of Carriage on November 11: using an AI agent to book, change or service a ticket, or to…
Anthropic released a guide to using Claude Tag (beta) for startups, based on interviews with 8 high-growth startups…
Anthropic releases the Claude Meetings beta, in which Claude can join video calls as a visible participant, answer…
OpenRouter released a tutorial explaining how AI agents fall into infinite loops when tools repeatedly fail, and…
Sponsored
Orange Relay (pro.nat6.net) is a premium AI API relay — an excellent transfer station with competitive pricing, reliable quality and broad model coverage including Claude, GPT and Gemini.
Visit Orange Relay