AI News Archive: June 17, 2026 — Part 15
Sourced from 500+ daily AI sources, scored by relevance.
- AI Is Taking Over Hospitals
This is health care’s Uber moment.
- Amazon backs AI start-up developing models to simulate physical world
Company joins investment arms of Nvidia and AMD in $310mn funding round for Odyssey
- Scientific research start-up CuspAI to raise $400m with Jeff Bezos among backers – FT
UK start-up CuspAI is set to raise $400m in a funding round that includes Amazon’s Jeff Bezos, according to the Financial Times. Read more: Scientific research start-up CuspAI to raise $400m with Jeff Bezos among backers – FT
- AI material discovery startup CuspAI reportedly raising $400M round
CuspAI Ltd., a startup working to speed up material discovery, is reportedly in the process of raising a $400 million funding round. The Financial Times reported today that the term sheet has been signed but the transaction is still being finalized. According to the paper, Amazon.com Inc. founder Jeff Bezos’ Bezos Expeditions and Kleiner Perkins […] The post AI material discovery startup CuspAI reportedly raising $400M round appeared first on SiliconANGLE .
- We have to manage the AI revolution
There must be a global agreement on how the technology is controlled
- AI dominates conversations at VivaTech
VivaTech's 10th edition draws 200,000 visitors to Paris, with Jeff Bezos and Emmanuel Macron among the guests. AI dominates conversations on the show floor. Euronews finds a personal survival capsule for when the robots take over.
- 효성중공업·STT GDC 합작법인, AI·클라우드 수요 겨냥한 데이터센터 서울에 개소
STT GDC는 16일 서울 금천구 가산동에 위치한 STT 서울 1의 개관을 발표했다. 해당 시설은 2021년 STT GDC(지분 60%)와 효성중공업(지분 40%)이 설립한 합작법인 STT GDC 코리아가 개발·운영한다. 회사는 STT 서울 1을 한국 시장 진출의 전략적 거점으로 활용해 동북아 지역 고객의 AI 및 클라우드 인프라 구축 수요에 대응한다는 계획이다. 허철회 STT GDC 코리아 대표는 “AI 인프라는 디지털 역량과 전력 수급 여건, 고객 수요가 높은 시장을 중심으로 빠르게 발전하고 있다”라며 “동북아 지역에서 워크로드 규모와 복잡성이 증가하는 가운데 안정성과 효율성, 장기적인 확장성을 갖춘 인프라에 대한 요구도 높아지고 있다”라고 밝혔다. 이어 “STT 서울 1은 STT GDC가 국내 입지를 구축하고 동북아 주요 시장으로 사업을 확장하기 위한 핵심 거점이 될 것”이라고 설명했다. 조현준 효성그룹 회장은 “오래전부터 데이터가 ’21세기의 원유’가 될 것임을 확신하고, AI 경쟁력이 곧 국가 경쟁력인 시대를 내다보며 대한민국의 ‘브레인’인 수도권에 AI의 ‘심장’ 역할을 할 데이터센터 구축에 나섰다”라며, “STT 서울 1은 STT GDC의 전문성과 효성의 전력 솔루션 역량이 결합된 결실로, 대한민국 AI 산업의 핵심 인프라이자 효성의 새로운 성장동력이 될 것이다”고 밝혔다. 서울 금천구 가산동 소재의 STT 서울 1은 연면적 약 4만㎡ 규모로, 최대 30MW IT 부하를 지원하며 2026년 6월부터 상업 운영을 전면 시작됐다. 또한 고집적 워크로드를 포함해 다양한 하이퍼스케일 및 엔터프라이즈 환경을 지원할 수 있도록 설계됐다. 개관식에는STT GDC 대표이사 겸 CEO 브루노 로페즈와 조현준 효성그룹 회장이 참석했다. 또한 박지혜 국회의원, 주한싱가포르대사 웡 카이 지운등이 참석해 경제 발전과 국가 간 협력에 있어서 디지털 인프라의 중요성을 강조했다. 박지혜 국회의원은 “우리나라가 글로벌 AI 톱 3를 지향하고 있는 상황에서 고품질의 효율적인 데이터센터 인프라를 가져가는 것은 매우 중요한 국가적인 과제라고 생각한다”며, “STT 서울 1이 보다 효율적이고, 전문적이고, 지속 가능한 데이터센터 모델을 만듦으로써 우리나라가 진정한 AI 강자로 자리매김할 수 있도록 지원해주길 바란다”고 말했다. 웡 카이 지운 주한싱가포르대사는 “싱가포르와 한국은 무역, 기술, 혁신 분야에서 오랜 기간 긴밀한 관계를 이어왔다”며, “디지털 및 AI 역량을 지속적으로 고도화하는 가운데, 신뢰할 수 있는 디지털 인프라는 양국 간 유대와 협력을 한층 강화하는 중요한 역할을 할 것”이라고 말했다. 이어 “STT 서울 1은 국가 간 협력을 통해 회복탄력적인 디지털 인프라를 구축하고, 지역간 연결성을 강화하며, 혁신과 성장을 위한 새로운 기반을 마련한 사례”라고 덧붙였다. dl-ciokorea@foundryco.com
- Allbirds rebrands as Smartbird in AI pivot, hires former AWS executive as CEO
Allbirds is now Smartbird. The company has a new president and CEO, Nadia Carlsten. Smartbird is shifting focus to AI infrastructure and cloud computing. This move follows a significant surge in its share price. The company aims to provide AI infrastructure as a managed service. It is in discussions with potential customers and planning its first deployments.
- BIRD takes flight: Allbirds pivot to AI company Smartbird is a huge change—that’s good for the stock
From shoes to AI to . . . Smartbird? It’s been a strange, winding path to an entirely new strategy for the company formerly known as Allbirds. On Wednesday, the company made two big announcements: It has named a new CEO, Nadia Carlsten, and it changed its name from Allbirds to Smartbird. It’s also identifying itself as “an AI infrastructure provider,” which, again, is a huge change from its previous iteration as a footwear maker. Carlsten will also join the company’s board and replace current CEO Joe Vernachio, who had taken the helm of the company in March 2024. She was previously leading Amazon Web Services’ quantum computing center, and was CEO at AI company DCAI. The news was evidently welcomed by the markets, as shares took flight after the announcement—BIRD stock was up roughly 45% midday Wednesday, and was up 37% at the time of market close Wednesday. (However, the stock is still down 50% over the past year.) In addition to a pivot to AI from the footwear industry, Smartbird had previously sold off its footwear-related assets for almost $40 million. In all, it’s been an incredible turn of events for the company, which was, at one time, valued at $4 billion —today, its market cap is around $50 million. Perhaps that’s why it makes some sense that Smartbird is trying to get in on the AI gold rush—and its new CEO says that she sees an opportunity to do so. “Smartbird is entering the market at a pivotal moment in the evolution of AI infrastructure,” said Carlsten, in a statement. “There is a clear opportunity to meet the growing need for enterprise-grade AI infrastructure that delivers control and performance without the capital and operational burden of hardware ownership. With a differentiated strategy, significant capital, and the opportunity to build an exceptional team, we are uniquely positioned to capitalize on one of the most significant infrastructure opportunities of the next decade.”
- Allbirds' AI makeover includes a potential move out of San Francisco, along with a new CEO and name
New CEO Nadia Carlsten will lead the shift to enterprise AI infrastructure, and a potential move south.
- ChatGPT’s market share dips below 50%: Key AI trends to know
Hit by Google Gemini's continued expansion and Claude's recent growth, ChatGPT's share of the AI assistant market fell below 50% for the first time in March 2026, as per a report published by market intelligence firm Sensor Tower.
- ChatGPT falls below 50% market share despite its lead
ChatGPT falls below 50% market share despite its lead YourStory.com
- ChatGPT market share slips below 50% as Gemini, Claude gain ground: Report
ChatGPT reached one billion users faster than any platform in history, but rivals are growing faster and reshaping the AI assistant market, according to Sensor Tower's Start of AI 2026 report
- ChatGPT market share falls below 50% for first time, but remains top AI assistant: Report
ChatGPT market share falls below 50% for first time, but remains top AI assistant: Report
- ChatGPT’s AI market share slips to a historic new low
For the first time since its explosive debut, ChatGPT has slipped below a crucial market share threshhold.
- ChatGPT Market Share Dips Below 50% for First Time: Here's Why
ChatGPT Market Share Dips Below 50% for First Time: Here's Why PCMag UK
- ChatGPT Market Share Dips Below 50% for First Time: Here's Why
ChatGPT Market Share Dips Below 50% for First Time: Here's Why PCMag
- Wipro Opens Anthropic Claude AI Centre in Bengaluru
Wipro Opens Anthropic Claude AI Centre in Bengaluru YourStory.com
- Anthropic's design assistant now works better with its coding agent
Anthropic's tools are getting chummy with each other.
- Anthropic Is Bringing Together AI Design and Coding in Claude
New updates mean you should be able to go back and forth between coding and designing without interruptions.
- Samsung’s pet tech only needs a picture to detect health issues hurting your furry friends
Samsung's next Galaxy AI feature takes a photo of your dog or cat and uses AI to flag potential health issues before they become a vet emergency.
- Samsung phones will soon let you check your pet’s health with a photo
Galaxy owners can soon take a photo of their pet and use AI analysis to spot any health issues.
- Copilot Cowork becomes generally available
Copilot Cowork is now generally available
- Estonia intends to recognize AI agents with digital IDs
I am not a number! I am a free agent (that just happens to have a number)
- Apple investors are tired of AI promises, want tangible progress
Apple investors are tired of AI promises, want tangible progress The Mercury News
- SpaceX Acquires Cursor, the AI Coding Startup Competing With Claude Code and OpenAI Codex
SpaceX has acquired AI coding startup Cursor in a $60 billion (roughly Rs. 5,66,500 crore) all-stock deal. The companies confirmed the acquisition on X and said they have been jointly training an AI model that will be released through Cursor and Grok Build. The deal follows a partnership announced in April that gave SpaceX the option to buy Cursor. Founded in 2022 as ...
- Why SpaceX is spending $60 billion to acquire AI coding startup Cursor
Why SpaceX is spending $60 billion to acquire AI coding startup Cursor
- Cursor officially joins the SpaceX AI machine
PLUS: Conduct better stock research with Perplexity Finance
- First Take: SpaceX’s Cursor Acquisition Gives Its Enterprise AI Ambitions a Launch Vehicle
First Take: SpaceX’s Cursor Acquisition Gives Its Enterprise AI Ambitions a Launch Vehicle Gartner
- SpaceX, Cursor, and the Race to Build the Best Coding LLM in the World
SpaceX’s $60 billion acquisition of Cursor is the largest deal in the history of AI software and one that reshapes the competitive landscape for agentic coding. The all-stock transaction, filed with the SEC and expected to close in Q3 2026, follows an option SpaceX secured in April and exercised just two trading days after its […] The post SpaceX, Cursor, and the Race to Build the Best Coding LLM in the World appeared first on IDC .
- SpaceX to take over Cursor in $60bn play for AI coding market
A new coding model will come to Cursor and xAI's Beta-stage Grok Build platform.
- SpaceX strikes $60bn deal for AI coding agent Cursor
SpaceX has signed an agreement to acquire Anysphere, the company behind the AI coding agent Cursor, in an all-stock deal valued at $60bn.
- SpaceX’s First Big Move After Its Record IPO: Buying a $60 Billion AI Coding Startup
SpaceX’s First Big Move After Its Record IPO: Buying a $60 Billion AI Coding Startup entrepreneur.com
- Everpure announces Data Stream to expand AI-ready data offerings
Everpure Data Stream, based on NVIDIA AI Data Platform reference design, brings advanced AI capabilities directly to enterprise data
- Everpure unveils data-primacy architecture for AI era
New capabilities shift enterprises from app-centric to data-centric model with enhanced governance and AI-ready intelligence
- Data primacy puts Everpure at the center of enterprise AI: theCUBE’s Pure Accelerate 2026 keynote analysis
As artificial intelligence transforms the enterprise, the old model of managing data in application-controlled silos is breaking down. The companies that will win the AI era are those that embrace data primacy by treating data itself, rather than the applications sitting on top of it, as the primary asset. That shift was on full display […] The post Data primacy puts Everpure at the center of enterprise AI: theCUBE’s Pure Accelerate 2026 keynote analysis appeared first on SiliconANGLE .
- Companies question cost of AI as tokenmaxxing spending adds up
Companies question cost of AI as tokenmaxxing spending adds up CBC
- Z.ai pitches GLM-5.2 for long-running software engineering tasks
Z.ai pitches GLM-5.2 for long-running software engineering tasks InfoWorld
- Z.ai pitches GLM-5.2 for long-running software engineering tasks
Z.ai has released GLM-5.2, an MIT-licensed open-source AI model designed for long-running software engineering tasks, as the Chinese company seeks to challenge proprietary coding models on cost and performance. The company said GLM-5.2 ranked just behind Anthropic’s Claude Opus 4.8 on FrontierSWE, a long-horizon coding benchmark, trailing it by 1%. Z.ai said the model also edged out OpenAI’s GPT-5.5 by 1%. Z.ai said GLM-5.2 supports a one-million-token context window with up to 131,072 output tokens, positioning it for agentic coding workflows that require reasoning across large codebases. The company is also making an efficiency argument. It said GLM-5.2 uses a technique called IndexShare, which reduces per-token compute by 2.9 times at a one-million-token context length. It also said changes to the model’s multi-token prediction layer increased the acceptance length for speculative decoding by up to 20%. The changes are aimed at a practical problem for developers: long-context coding agents can be expensive to run when they are asked to work across large repositories. Enterprise appeal GLM-5.2’s clearest appeal is that it pairs stronger coding capabilities with the cost advantages of an open-source model. But capability alone will not be enough to make it a credible alternative. “Western enterprises will want independent benchmark validation, successful deployments at global enterprises, strong security and governance controls, and long-term support commitments,” said Pareekh Jain , CEO of Pareekh Consulting. Jain said the fastest route to enterprise credibility would be hosting by a major cloud provider like AWS. That would allow customers to use the model under standard enterprise terms, with service-level commitments and compliance certifications. Tulika Sheel , senior VP at Kadence International, said GLM-5.2 would also need to prove it can operate as a stable enterprise product. “Demonstrated success in real-world deployments and transparent governance will be just as important as benchmark scores,” Sheel said. The performance and cost claims will also need to hold up against established models. “Enterprise leaders generally consider two major factors when evaluating new models,” said Lian Jye Su , chief analyst at Omdia. “First, they look at overall performance against competitors, where GLM-5.2 performs well in long-horizon agentic coding and software engineering. Second, they look at the cost of adoption. As an open-source model, GLM-5.2 has clear cost advantages.” Su said the model could appeal to engineering teams under pressure to control AI costs. It may also attract open-source advocates and companies with significant operations in the Asia-Pacific. But the claims still need wider validation, particularly around hallucination control and coherence during extended tasks. These are critical issues for enterprises considering AI coding agents, which may need to work across large codebases and multi-step software engineering workflows. Jain said the one-million-token context window could be useful for large codebase analysis. It could also help with legacy modernization projects and complex engineering documentation. He said long-context capability may also help with audit logs or legal contracts, where splitting material into smaller chunks can create errors across document boundaries. But for everyday coding tasks, effective retrieval systems may matter more than very large context windows, making some of the benefits more limited in practice. Governance risks The governance question depends largely on where the model runs. Sheel said enterprises should evaluate GLM-5.2 as they would any strategic technology partner, rather than as a standalone model. That means looking at where data is stored and whether the model can be used in environments that customers control. That deployment choice is central to the risk calculation, according to Jain. Because GLM-5.2 is available under an MIT license, companies can download the weights and run them on their own infrastructure, reducing the need to send sensitive data to Z.ai. “The risk flips completely if you use Z.ai’s hosted API instead,” Jain said. He said Chinese national security rules could require domestic companies to cooperate with government requests, making hosted use difficult for regulated industries or workloads involving sensitive data. Su said the issue is not limited to Chinese vendors. Recent restrictions affecting access to some Anthropic models have also highlighted the risk that enterprises may have limited control over the availability of AI services from foreign providers. “Selecting solutions from American and Chinese AI vendors does expose non-US Western enterprises to additional risk of having zero control over the availability and uptime of these models,” Su said. The article originally appeared on InfoWorld .
- Vercel Releases Eve: An Open-Source AI Agent Framework Where Each Agent is a Directory of Files Mapped to Capabilities
Vercel Releases Eve: An Open-Source AI Agent Framework Where Each Agent is a Directory of Files Mapped to Capabilities MarkTechPost
- Introducing eve
Today, we are proud to introduce eve , an open-source agent framework for building, running, and scaling agents. eve is designed around the idea that building an agent should mean defining what it does without assembling all of the pieces that it needs to run in production. Instead, eve comes with production already built in: Durable execution Sandboxed compute Human-in-the-loop approvals Subagents Evals And more eve is the framework that we build and run our own agents on. Agents today are where the web was before frameworks, with everyone hand-rolling the same plumbing and nothing carrying over to the next one. Next.js ended this for the web, and eve is doing the same for agents. An agent is a directory This is an eve agent. Each file describes one component of the agent, so at a glance, the tree tells you what an agent is, what it does, where it lives, and when it acts on its own. Create an eve agent in minutes Every agent starts with its definition. The agent.ts file is where you configure the agent itself. You can define the model with one line, with provider fallbacks supported through AI Gateway , and compaction, model options, and other optional fields are there when you need them. Giving your agent a job and personality is as simple as creating an instructions.md file, which serves as the system prompt that eve puts in front of every model call. You create files for what your agent does, like post_chart.ts and revenue-definitions.md for tools and skills, and eve wires them into a working agent without any boilerplate or plumbing to manage. You can just focus on what your agent does instead of how it does it. Why we built eve We had built agents for years at Vercel, v0 among them. But once coding agents made building one something anyone could do, everyone did. We shipped hundreds of agents and internal apps, and it looked like a productivity revolution. But underneath it, every team was building and rebuilding the same plumbing before their agent could do anything, and none of it carried over from one use case to the next. Each agent was designed for a different task, but they all had the same needs, and the same structure kept emerging to meet them. Agents have a shape. eve is that shape made into a framework. Every generation of software earns its abstractions once enough people have built the same thing the hard way, and agents are there now. Batteries included Everything an agent needs in production ships with the framework. A durable session for every conversation Agents wait on people, call slow systems, and run for hours, days, or weeks. In eve, every conversation is a durable workflow with each step checkpointed, so a session can pause, survive a crash or a deploy, and resume exactly where it stopped. This durability is built on the open-source Workflow SDK . A sandbox for every agent The code your agents write should be treated as untrusted, so eve keeps agent-generated code out of your application runtime entirely. Every agent gets its own sandbox, an isolated environment for shell commands, scripts, and file reads and writes, running in a separate security context from the harness that controls the agent. The backend behind this sandbox is an adapter. When deployed, it runs on Vercel Sandbox . Locally, it runs on Docker, microsandbox, or just-bash , and you can write an adapter for any other provider. Human-in-the-loop approvals Agents act on real systems, and some of those actions should require a person to approve them. Any action in eve can be configured to require approval, and the agent will pause there and wait, indefinitely if it has to, without consuming any compute. Once approved, eve continues the task right from where it left off. Secure connections to tools, data, and services Agents need to connect to your backends, data, and other third-party services. In eve, a connection is a file that points at an MCP server or any API with a compatible OpenAPI document. eve discovers the remote tools, hands them to the model, and brokers the auth, and the model never sees the connection's URL or credentials. Vercel Connect handles interactive OAuth with consent and token refresh built in. At launch, eve agents can connect to Slack, GitHub, Snowflake, Salesforce, Notion, and Linear, plus anything else you can reach over OAuth, an API key, or an MCP server. The same agent on every channel Most agents live in exactly one place because every new surface is its own integration to build. In eve, the same agent serves every surface, and each channel is just a small adapter file. The HTTP API is on by default, with Slack, Discord, Teams, Telegram, Twilio, GitHub, and Linear included, and defineChannel covers custom channels. One channel can also hand off to another, so an incident webhook can open an investigation thread in Slack. Tracing and evals built in When an agent gets something wrong, the first question is what the agent actually did. In eve, every run produces a trace. Each model call and tool call appears in order with its inputs and outputs, down to the commands the agent ran in its sandbox, so you can replay the run instead of piecing it together from logs. The spans are standard OpenTelemetry and export to any tracing service you already run, whether that is Braintrust, Honeycomb, Datadog, or Jaeger. On Vercel, they surface in an Agent Runs tab under Observability, giving you one place to watch every session and drill into any run. Evals let you go further, with scored test suites you can run locally or wire into CI. That leaves the part no framework can write for you: what your agent actually does. Extend an agent one file at a time The most common way to give an agent capabilities is to give it tools, and to teach it how to do things with skills. Today that means building the tool, writing the skill, and then wiring both into whatever runs your agent loop. With eve, a tool is one TypeScript file and a skill is one markdown file. Notice what is missing. Instead of writing all of the boilerplate to wire these up and register them with your agent, eve handles it for you. A file's name and place in the tree are its definition. eve picks up the tool and skill at build time, hands the model their descriptions, and the model takes it from there. Just as Next.js turns a folder into a route by owning the routing, eve turns a file into an ability by owning the agent loop. Add human-in-the-loop approval Requiring approval for an action is one field on the tool. Now you can guard the expensive query, the destructive write, or anything else you would not want running unsupervised. Let the agent write its own code The tools you define aren't the ceiling. eve gives your agent a real computer with a shell, so it can run bash, grep, and anything else you'd run in a terminal. When a job calls for code that doesn't exist yet, the agent writes and runs it. Your agent can solve problems on its own in a secure sandbox, reshaping a dataset, running a one-off analysis, or writing whatever code a job needs that no tool covers. Delegate work to a subagent An eve agent can also delegate. A subagent is the same shape one level down, a directory inside subagents/ with its own instructions, tools, and sandbox. The parent calls it just like it calls a tool. The child starts with a clean context window and only the tools you gave it, does the work, and hands the result back to the parent. Start and interact with your agent Now comes the part every developer looks forward to, testing their agent. That used to mean starting the process, asking a question, and reading logs, with no simple view of which tools were used, what the model loaded, or why it answered the way it did. You wanted to talk to your agent and watch it work, and what you got was stdout . With eve, the dev loop is one command. Run the agent locally To start an eve agent, you run its dev server. Everything the agent did is visible in the TUI. The agent loaded the skill, ran the query, answered by the team's rules, and each of those lines is a checkpointed step in the durable session. The terminal UI is just a client, and the agent serves the same structured events over HTTP, so curl , a test script, or CI can drive it and check exactly what it did. Test the agent with evals Talking to the agent proves one run at a time. Evals test your agent the way you test the rest of your software, with scored checks written in files like everything else in the project. You can run eve eval locally or point it at a deployed app, so a prompt change or a model swap shows you what it broke before your users do. Ship it The agent has lived on your laptop long enough. Shipping it is normally the step where the agent work stops and the infrastructure work begins. With eve there is nothing to provision, because the agent is an ordinary Vercel project, and it deploys the way any other frontend or backend does. Nothing about your agent changes when you deploy, because eve was designed from the ground up with adapters in mind. At launch eve deploys to Vercel, with support for other platforms on the way. The same directory runs in production exactly as it ran on your laptop. The sandbox swaps to Vercel Sandbox without a code change, and the agent you were talking to in dev is now reachable at a public URL. Deploying does not even interrupt the agent; a session that is mid-task when you push finishes on the version it started on. There is no dashboard step required in any of this. The same coding agent that built your agent can ship it and verify its work. But deployed is not the same as done. In production, an agent has users to meet and work to do on its own schedule. Introduce the agent to your team Getting an agent into Slack used to mean building a Slack app first, including the app config, bot token, event subscriptions, webhook endpoint, and signing secret, all before the agent said a word. With eve, a channel is one command. The command writes channels/slack.ts , a single file that ships like any other code change, and the agent you just deployed now answers in Slack. The platform affordances come with the channel, so approvals render as Slack buttons, questions as select menus, and the agent posts typing indicators while it works. Route the credentials through Vercel Connect and there is no bot token to copy into a .env file. Run the command again with discord or teams , and the same agent is there too, one file per channel. Channels are the user interface of your agents, and sessions move between them. A question asked in Slack can continue on the web, and an incident webhook arriving over HTTP can open an investigation thread in Slack and finish the work where the team already is. Put the agent on a schedule The Monday revenue report should not wait for someone to ask. A schedule is one more file, a cron expression and a handler that starts the agent on its own clock. On Vercel, each schedule deploys as a Vercel Cron Job , so the report posts every Monday with nobody on the hook to remember it. Run the agent like the rest of your software An agent your team depends on is production software, and a change to its instructions can break it as surely as a change to its code. Because an eve agent is files in a directory, it lives in Git like the rest of your code, and a new prompt, tool, or skill is a commit with a diff, a review, and a history. Wire eve eval into CI and the suites you wrote become the deploy gate, scoring every commit so a regression stops in CI rather than in production. Every commit also gets its own preview deployment, and it carries the agent's channels with it. The team can talk to the next version of your Slack bot before it replaces the one they use every day. And when a change goes bad in a way no eval caught, you can roll production back to the previous version instantly. How we run Vercel on eve We run more than a hundred agents in production at Vercel, and they are part of how the company operates every day, each one taking on a role in the business. Here are a few of them. The data analyst The most-used internal tool at Vercel is an agent, handling more than 30,000 questions a month. Anyone can ask d0 anything in Slack and get an answer from the warehouse. Every query is scoped to the asker's own permissions, so d0 can never show you a table you could not already see. The autonomous SDR Lead Agent runs the playbook of our best rep around the clock. It works every new lead the moment it comes in and follows up on its own, so none go cold overnight. It costs about $5,000 a year to run, returns 32 times that, and one engineer maintains it part-time. The sales cockpit RevOps built Athena in six weeks without engineers. It answers pipeline and forecast questions from Snowflake and Salesforce in plain language, and pipeline coverage nearly doubled after it went live. The support engineer Vertex is our support agent that handles tickets across the help center, docs, and Slack around the clock, ensuring people get a fast response no matter when they ask. It reads the ticket, finds the right answer, and responds, solving 92% of tickets on its own and escalating the rest to the support team so they can focus on the problems that most need their attention. The content agent Anyone at Vercel can write, not just the content team. draft0 runs a full review pipeline, catching the most glaring issues and building up an analysis of what the piece is actually about before it ever reaches us. By the time it does, the obvious work is done and we have a much clearer picture of what it needs. That means smaller pieces move fast, and we can give our full attention to the ones that demand it, like this one. Routing agent We rely on hundreds of agents every day, but keeping track of which one handles what workloads is not efficient. So instead of routing tasks ourselves, everything goes to V in Slack first. V figures out which agent can actually answer the task and routes it there, which means the whole fleet works like one agent instead of a hundred different options. These agents all began as separate projects on separate stacks, each with its own way of holding state, brokering credentials, and emitting logs, which is where most teams find themselves after their second or third agent. Today they live in one monorepo, and are built, observed, and upgraded the same way, no matter which team owns them. Because they all share the same shape, a hundred agents run with the same tools and the same conventions as one. Get started A year ago, agents triggered less than 3% of the deployments on Vercel. Now, they trigger around 29%, and we expect half of all deployments to come from agents soon. You have probably built an agent already, and the next one does not have to start from scratch. The public preview is open today, and the CLI wizard walks you through your first agent, from picking a model to a running dev server, in under a minute. Coding agents just need a prompt: Everything eve can do is at eve.dev/docs and development happens in the open at github.com/vercel/eve , where issues, discussions, and contributions are welcome. Hundreds of agents already run on eve at Vercel. What will you build? Read more
- Vercel launches a new framework and enterprise controls for agentic AI infrastructure
Front-end software development startup Vercel Inc. introduced a set of new products today at Ship, its annual conference, to deepen its agentic artificial intelligence infrastructure platform to align how enterprises deploy, run and scale with AI agents. “Each new generation of software needs a new generation of infrastructure. For the agent era, that’s Vercel,” said […] The post Vercel launches a new framework and enterprise controls for agentic AI infrastructure appeared first on SiliconANGLE .
- GLM-5.2 🤖, DeepSeek raises $7.4B 💰, Android MCP 📱
GLM-5.2 🤖, DeepSeek raises $7.4B 💰, Android MCP 📱
- MolmoMotion: Language-guided 3D motion forecasting
MolmoMotion: Language-guided 3D motion forecasting
- Inquiry about MCP setting (w/ Claude)
Inquiry about MCP setting (w/ Claude) Atlassian Community
- Apple investors are tired of AI promises, want tangible progress
Apple investors are tired of AI promises, want tangible progress East Bay Times
- Anduril Wins Production Contract for U.S. Air Force CCA Program
Anduril Wins Production Contract for U.S. Air Force CCA Program
- G7 leaders vow closer ties on AI as they hash out 'trusted partners' scheme
G7 leaders vow closer ties on AI as they hash out 'trusted partners' scheme The Straits Times
- G7 pitches trusted partnership to AI chiefs in a bid for frontier model sharing
G7 pitches trusted partnership to AI chiefs in a bid for frontier model sharing The National
- G7 leaders vow closer ties on AI
Hash out 'trusted partners' scheme.