惯性聚合 高效追踪和阅读你感兴趣的博客、新闻、科技资讯
阅读原文 在惯性聚合中打开

推荐订阅源

H
Help Net Security
爱范儿
爱范儿
V
Visual Studio Blog
Last Week in AI
Last Week in AI
阮一峰的网络日志
阮一峰的网络日志
雷峰网
雷峰网
Hugging Face - Blog
Hugging Face - Blog
博客园 - 【当耐特】
freeCodeCamp Programming Tutorials: Python, JavaScript, Git & More
博客园 - 三生石上(FineUI控件)
博客园 - Franky
博客园 - 叶小钗
OSCHINA 社区最新新闻
OSCHINA 社区最新新闻
The Cloudflare Blog
大猫的无限游戏
大猫的无限游戏
人人都是产品经理
人人都是产品经理
M
MIT News - Artificial intelligence
罗磊的独立博客
L
LangChain Blog
Jina AI
Jina AI
IT之家
IT之家
J
Java Code Geeks
Microsoft Azure Blog
Microsoft Azure Blog
博客园_首页

TestingCatalog

SpaceXAI gearing up for upcoming Grok 4.5 release ByteDance set to launch Seedance 2.5 with 3-minute output Meta prepares Scheduled tasks for Meta AI users on web Google tests new Gemini Inbox section for Workspace triage OpenAI might be preparing GPT-5.6 for next week's release Mistral releases Leanstral 1.5 model for proof engineering xAI debuts Grok Voice Agent Builder for Enterprises Condense launches proxy to cut AI coding agent bills by 66% Early look at Anthropic's Claude Science app for researchers Google launches Nano Banana 2 Lite and Gemini Omni Flash Google might be testing Gemini Flash upgrade on LM Arena Anthropic may impose KYC restrictions for Fable 5 access Anthropic launches Claude Sonnet 5 model on Claude and APIs NoimosAI launches Creative Agent for brand assets Apify lets AI Agents pay via Coinbase x402 for web tools Bloome launches chat platform for AI agent teams Meituan launches LongCat-2.0 1.6T parameter model Cursor releases its iOS app for vibe coding on the go OpenAI prepares upgraded Office controls for Codex OpenAI tests gifting Codex credits as new growth strategy Microsoft launches MAI-Code-1-Flash on GitHub Copilot Google adds Computer Use to Gemini 3.5 Flash Google tests notebook collections for NotebookLM OpenAI launches GPT-5.6 Sol preview for select partners Microsoft adds Copilot finance tools to Excel for M365 users DeepReinforce releases Ornith-1.0 open-source coding models Gemini to get voice dictation and Magic Pointer on desktop Meta launches AI glasses with three new styles from $299 Anthropic launches Claude Tag on Team and Enterprise plans Mistral launches OCR 4 for multilingual document extraction
Vellum adds agent-to-agent AI collaboration for Slack
https://www.facebook.com/nero.soares.9/ · 2026-07-03 · via TestingCatalog

Vellum has launched agent-to-agent communication inside Slack, enabling individual AI assistants to coordinate work with one another and with the people they represent. This approach differs from a single shared assistant that an entire team interacts with. On Vellum, each person operates their own assistant, which holds its own memory, context, and permissions. These separate assistants can now converse in a common Slack channel and move tasks forward between them.

Today, we launched agent-to-agent conversations in Slack to give you real AI coworkers.

Vellum assistants now talk to each other and coordinate work with your team all inside your workspace.

We tested it with two agents in our own Slack.

They planned our offsite for 19 people… pic.twitter.com/HEZE5fAHKe

— Marina · vellum.ai 👾 (@marinatrajk) July 2, 2026

The launch demonstration focused on planning a company offsite. Two assistants, one belonging to a team member named Marina and another to a colleague named Akash, took the task into a shared channel and collaborated on it. They divided responsibilities, negotiated candidate dates, and then one assistant reached out to the wider team for venue and dietary preferences before finalizing the arrangements. The sequence demonstrated assistants communicating with each other and with humans within the same thread, rather than a single system handling every request.

This capability is aimed at teams that already coordinate through Slack and want assistants that carry personal context into shared work. Since each assistant holds one person's history, preferences, and relationships, it can act as that person's representative when a plan requires input from several people. Permissions remain isolated by default, so one assistant accesses another's information only when necessary, and routine planning does not require anyone to restate context that an assistant already holds. Multi-step coordination, such as scheduling, collecting input, and confirming details, shifts from manual back-and-forth to assistants that manage the mechanics and present decisions to the people involved.

Check agent-to-agent AI on Vellum!

Test it!

Vellum Labs, the company behind the assistant, has built its product around personal, on-device intelligence and aims to give people back the hours spent on daily logistics. Its assistant is positioned as software that runs on a user's own machine and acts on their behalf, drafting messages, managing calendars, and handling tasks while keeping data under the user's control. The Slack feature extends that personal-assistant model outward, connecting one user's assistant to others so a team of individually informed assistants can operate together. This marks a transition from a single-user helper to shared workflows, in which each participant maintains a distinct assistant rather than pooling everything into a single account.