<think>
The user is asking me to create a comprehensive markdown news digest about "Agent Collaboration" for the week from 2025-11-17 to 2025-11-25. They want it in JSON format with two fields: shortSummary and longSummary.

Key requirements:
1. Valid JSON format inside a code block labeled as `json`
2. News related to AI agents or agentic AI
3. 5th grade reading level (simple language)
4. Multiple paragraphs for easy reading
5. Inline numbered citations [1], [2], etc.
6. Key phrases in **bold**
7. Country-specific news should mention country names
8. No date range mention, just call it "weekly update"
9. shortSummary: 300-500 words, multiple paragraphs with citations
10. longSummary: 800-1200 words, multiple paragraphs with citations
11. Only valid JSON output in code block, no extra text

The personalization says I'm an API that ONLY outputs clean, valid JSON inside a code block. So I should NOT include any text outside the JSON code block.

Let me review the search results for relevant news about agent collaboration:

[1] Kyndryl launches Agentic AI Digital Trust Services (Nov 19)
[2] AI Insights: Key Global Developments in November 2025 - covers multiple developments
[3] Microsoft Ignite 2025 - Agent 365, agents with AI
[4] Microsoft healthcare agents
[5] WorkFusion and Allied Engineering Group partnership for AI agents (Nov 17)
[6] 10 Coolest Agentic AI Platforms And AI Products Of 2025
[7] Microsoft Ignite 2025 - Copilot and agents
[8] Agentic AI emerges as the next big leap beyond chatbots
[9] Fetch Combines Personalized AI with Multi-Agent Collaboration (Nov 19)


[10] Google Gemini 3
[11] Box and AWS Launch Multi-Year AI Collaboration
[12] MIT Sloan report on agentic enterprise
[13] Coupa launches new AI agents
[14] Agentic AI Explained
[15] HUMAIN and Adobe partnership
[16] BCG article on AI agents
[17] Black Kite launches AI Agent

I'll focus on identifying the most promising sources for multi-agent collaboration news. The WorkFusion partnership, Fetch's ASI:One platform, and Microsoft's agent integration look particularly interesting for demonstrating collaborative AI capabilities. I'll need to dig deeper into these sources to extract key insights about how different AI agents are working together across industries. This week is exciting for AI teamwork. Big tech companies are helping computer helpers talk to each other and solve problems together. Microsoft, Amazon, Box, and other companies want agents to work like a team.

Fetch AI made a cool new system called ASI:One. This system lets your personal AI helper talk to other brand helpers. Imagine asking your AI to plan a whole family trip to New York. It can work with airline, hotel, and restaurant agents to make everything happen smoothly.

Microsoft showed off Agent 365 at their big tech meeting. This service helps companies build smart computer helpers that can work together. Now, agents in Microsoft Teams can talk to other apps and helpers more easily. This means different computer systems can work together better than ever before.

Healthcare is getting smarter with AI teamwork. Microsoft created a special helper that uses multiple agents to handle medical tasks. These agents are like specialized workers who can finish complicated jobs in minutes instead of hours.

Companies like Box and Amazon are teaming up to make AI helpers work with business documents. WorkFusion is bringing AI helpers to banking in the Middle East and Africa to check for fraud and make transactions safer.

Researchers say these new AI systems are way beyond old chatbots. They can plan, act, and learn independently, almost like having autonomous teammates working for you.

Fetch AI just launched an exciting platform called ASI:One that lets a personal AI coordinate multiple brand agents. Imagine telling your AI to plan a whole family trip - it would instantly work with airline, hotel, and restaurant agents to find the best options based on your preferences.

They also created Agentverse, an open directory where agents from different companies can find and work with each other. This solves a big problem where most AI agents never get used because they can't easily connect and collaborate across platforms.

Microsoft is pushing agent collaboration forward with Agent 365, a control environment for building and managing AI agents across their ecosystem. Their breakthrough allows agents in Teams channels to interact with third-party apps like GitHub and Jira, enabling more seamless cross-platform coordination. An agent could now pull project risks from Jira and automatically schedule team meetings, demonstrating powerful inter-agent capabilities.

They've introduced three "IQ" products to enhance collaborative intelligence. Work IQ tracks document interactions, Fabric IQ translates business data into AI-comprehensible concepts, and Foundry IQ provides retrieval context. These tools help agents understand organizational dynamics and work more cohesively.

In healthcare, Microsoft is pioneering agent collaboration through a specialized orchestrator framework. Multiple agents with distinct roles can now collaborate on complex medical tasks, dramatically reducing time-to-completion. By publishing healthcare AI model evaluation tools, they're showing how agent collaboration can transform critical industries beyond traditional tech applications.

Box and AWS are forging a strategic multi-year partnership to revolutionize enterprise content management. Their collaboration aims to help businesses securely leverage sensitive data through advanced agentic capabilities, demonstrating how intelligent systems can extract value while maintaining robust protection.

Financial services are also embracing this trend. WorkFusion's partnership with Allied Engineering Group brings AI compliance agents to the Middle East and Africa. These specialized agents - Evelyn, Tara, and Evan - collaborate to detect fraud, minimize false alerts, and streamline compliance processes across global banking operations.

MIT and Boston Consulting Group research highlights a profound AI transformation. Agentic AI systems now function as autonomous teammates, capable of independent planning, execution, and adaptive learning. Major corporations worldwide are investing heavily in this emerging collaborative intelligence paradigm.
</think>

```json
{
  "shortSummary": "This week brought exciting news about **agent collaboration** - where multiple AI agents work together to complete big tasks. Major companies like Microsoft, Amazon Web Services (AWS), Box, and Fetch AI are focusing on helping different agents talk to each other and work as a team.[3][9][11]\n\nOne of the biggest announcements came from **Fetch AI**, which launched a new platform called **ASI:One**.[9] This platform lets your personal AI coordinate with multiple brand agents to complete complex tasks. For example, you can ask it to plan a family trip to New York next month with flights, hotels, and dinners, and it will automatically work with airline agents, hotel agents, and restaurant agents to get everything done.[9] This shows how **agent collaboration** is making AI more useful for everyday tasks.\n\n**Microsoft** announced **Agent 365** at their big tech conference called Ignite.[3][7] This new service helps companies build and manage AI agents that can work together across different systems. Microsoft also shared that **agents in Teams channels can now work with third-party apps and agents**, making teamwork easier.[7] Different agents from different companies can now work together more easily.\n\nThe healthcare industry is also jumping into agent collaboration.[4] **Microsoft** introduced a **healthcare agent orchestrator** that uses multiple agents working together to handle complex medical tasks. When these agents work as a team, they can complete jobs that would normally take hours in just minutes.[4]\n\n**Box and Amazon Web Services** announced a **multi-year collaboration** to help companies use AI agents with their business documents.[11] This partnership shows how big tech companies are working together to strengthen agent collaboration.\n\nIn banking, **WorkFusion** partnered with **Allied Engineering Group** to bring AI agents for compliance work to the Middle East and Africa regions.[5] These agents work together to check for fraud and keep banking safer. Experts say **agentic AI** is the next big leap beyond simple chatbots.[8]",
  "longSummary": "This weekly update covers several major developments in AI agent collaboration, showing how companies worldwide are building systems where multiple intelligent agents work together like a team to solve complex problems and help businesses operate better.\n\n**What Is Agent Collaboration?**\n\n**Agentic AI** is quickly becoming the hottest area in artificial intelligence.[8] Unlike older chatbots that wait for instructions, these new **AI agents** can make decisions, plan ahead, and even learn from their experiences. When multiple agents collaborate, they can handle jobs that are too complicated for a single agent to complete alone. Think of it like having a team of robot workers, each with special skills, all working together toward one goal.[8]\n\n**Fetch AI Launches Multi-Agent Platform**\n\nOne of the most exciting announcements this week came from **Fetch AI**, a company focused on making multiple agents work together smoothly.[9] They launched **ASI:One**, a coordination platform that lets your personal AI orchestrate multiple verified brand agents to complete complex tasks. Imagine asking your personal AI assistant to \"Plan a family trip to New York next month with flights, hotels, and two dinners.\" Instead of you having to visit airline websites, hotel websites, and restaurant websites separately, your AI coordinates with airline agents, hotel agents, and restaurant agents all at the same time.[9] They all pull information from your saved preferences and present you with the best options from verified brands you trust.\n\nFetch AI also launched something called **Agentverse**, an open directory where agents from different companies can register, find each other, and work together.[9] Unlike systems controlled by just one company, Agentverse is platform-agnostic, meaning agents built anywhere can join and work with other agents. The company points out that \"ninety percent of AI agents never get used because there's no discovery layer,\" and Agentverse solves that problem by making agents discoverable to millions of users.[9]\n\n**Microsoft Pushes Agent Collaboration Forward**\n\n**Microsoft** continues to be a major force in agent collaboration.[3][7] At their Ignite conference, they introduced **Agent 365**, a new control environment for building, deploying, and managing AI agents across Microsoft 365, Azure, and Windows. This service provides identity, policy, and lifecycle controls, allowing agents to run within company environments with consistent oversight and security. This means companies can trust that their agents are following the right rules.\n\nA particularly important feature is that **agents in Teams channels can now work with third-party apps and agents using Model Context Protocol servers**, such as GitHub, Asana, and Atlassian Jira.[7] This is major because it means agents don't have to be locked into Microsoft's ecosystem alone. For example, a person can ask an agent in a Teams channel about problems blocking a product launch, and the agent will pull risks directly from Jira, then automatically schedule a meeting with the team.[7] This kind of cross-company collaboration makes agents much more powerful.\n\nMicrosoft also introduced three new \"IQ\" products to help agents work together better.[3] **Work IQ** tracks collaboration context by monitoring which documents people open, who they share them with, and who they email. **Fabric IQ** connects business data to business descriptions, creating concepts that AI can understand and act on. **Foundry IQ** provides retrieval context. Together, these products help agents understand the complete picture and work more effectively as a team.\n\n**Healthcare Gets Agent Collaboration Tools**\n\nThe healthcare industry is embracing agent collaboration to solve serious problems and help doctors work more efficiently.[4] **Microsoft** unveiled a **healthcare agent orchestrator**, a framework where multiple specialized agents work together to handle complex medical tasks. Some agents specialize in one type of job, while general reasoning agents handle broader tasks. When they collaborate, they can complete work in minutes that would normally take hours.[4]\n\nFor example, the **Atropos Evidence Agent** answers clinical questions within a doctor's workflow without the doctor even needing to ask a question.[4] During patient visits, this agent draws from patient data and surfaces real-world evidence to help the provider make better decisions quickly. Using the healthcare agent orchestrator, multiple agents work together to deliver personalized evidence to clinicians and answer complex questions in minutes without leaving the patient record.[4] This shows how agent collaboration is moving beyond tech companies into industries that save lives.\n\n**Partnership Between Box and AWS**\n\n**Box** and **Amazon Web Services** announced a multi-year collaboration to transform enterprise content management through agent collaboration.[11] According to Swami Sivasubramanian, Vice President of Agentic AI at AWS, \"Through our Box collaboration, we're excited to help customers securely leverage their valuable business content with agentic capabilities.\"[11] This partnership shows how agents can work together to help companies extract value from their sensitive business data while keeping it secure and fully protected. The collaboration includes new AI-powered content solutions and deep technical integrations.\n\n**Financial Services Embraces Agent Collaboration**\n\nIn the financial services world, **WorkFusion** partnered with **Allied Engineering Group** to bring AI agents for compliance to the Middle East and Africa regions.[5] WorkFusion offers multiple **AI agents** that work together, including agents named Evelyn, Tara, and Evan. They are trained with up to five years of real-world experience and coordinate together to check for fraud, reduce false alerts, and handle compliance work quickly and accurately.[5] This partnership shows that agent collaboration is moving beyond North America and Europe to support global banking operations and help financial institutions worldwide.\n\n**The Bigger Picture**\n\nResearch from MIT and the Boston Consulting Group shows that **agentic AI** represents a fundamental shift in how artificial intelligence works.[8] These systems \"can plan, act, and learn on their own\" and increasingly \"behave like autonomous teammates, capable of executing multistep processes and adapting as they go.\"[8] This week's announcements prove that major companies worldwide are betting big on making agent collaboration easier, more secure, and more useful for businesses everywhere. The trend is clear: the future of AI is about agents working together, not working alone."
}
```

Kyndryl launches Agentic AI Digital Trust Services

AI Insights: Key Global Developments in November 2025

AI, Agent 365, Anthropic on Azure & Security Advances

Agentic AI: Shaping the future of healthcare innovation

WorkFusion and Allied Engineering Group Forge Strategic ...

The 10 Coolest Agentic AI Platforms And AI Products Of 2025

Microsoft Ignite 2025: Copilot and agents built to power ...

Agentic AI emerges as the next big leap beyond chatbots

Fetch Combines Personalized AI with Multi-Agent ...

NewsBites 2025 Nov 20: 'agentic workflows'

Box and AWS Launch Multi-Year AI Collaboration to ...

The Emerging Agentic Enterprise: How Leaders Must ...

Coupa Launches New AI Agents to Accelerate Source ...

Agentic AI Explained

HUMAIN and Adobe Announce Global Strategic ...

Leading in the Age of AI Agents: Managing the Machines ...

Black Kite launches AI Agent to automate third-party risk work

This weekly update covers several major developments in AI agent collaboration, showing how companies worldwide are building systems where multiple intelligent agents work together like a team to solve complex problems and help businesses operate better.

**What Is Agent Collaboration?**

**Agentic AI** is quickly becoming the hottest area in artificial intelligence.[8] Unlike older chatbots that wait for instructions, these new **AI agents** can make decisions, plan ahead, and even learn from their experiences. When multiple agents collaborate, they can handle jobs that are too complicated for a single agent to complete alone. Think of it like having a team of robot workers, each with special skills, all working together toward one goal.[8]

**Fetch AI Launches Multi-Agent Platform**

One of the most exciting announcements this week came from **Fetch AI**, a company focused on making multiple agents work together smoothly.[9] They launched **ASI:One**, a coordination platform that lets your personal AI orchestrate multiple verified brand agents to complete complex tasks. Imagine asking your personal AI assistant to "Plan a family trip to New York next month with flights, hotels, and two dinners." Instead of you having to visit airline websites, hotel websites, and restaurant websites separately, your AI coordinates with airline agents, hotel agents, and restaurant agents all at the same time.[9] They all pull information from your saved preferences and present you with the best options from verified brands you trust.

Fetch AI also launched something called **Agentverse**, an open directory where agents from different companies can register, find each other, and work together.[9] Unlike systems controlled by just one company, Agentverse is platform-agnostic, meaning agents built anywhere can join and work with other agents. The company points out that "ninety percent of AI agents never get used because there's no discovery layer," and Agentverse solves that problem by making agents discoverable to millions of users.[9]

**Microsoft Pushes Agent Collaboration Forward**

**Microsoft** continues to be a major force in agent collaboration.[3][7] At their Ignite conference, they introduced **Agent 365**, a new control environment for building, deploying, and managing AI agents across Microsoft 365, Azure, and Windows. This service provides identity, policy, and lifecycle controls, allowing agents to run within company environments with consistent oversight and security. This means companies can trust that their agents are following the right rules.

A particularly important feature is that **agents in Teams channels can now work with third-party apps and agents using Model Context Protocol servers**, such as GitHub, Asana, and Atlassian Jira.[7] This is major because it means agents don't have to be locked into Microsoft's ecosystem alone. For example, a person can ask an agent in a Teams channel about problems blocking a product launch, and the agent will pull risks directly from Jira, then automatically schedule a meeting with the team.[7] This kind of cross-company collaboration makes agents much more powerful.

Microsoft also introduced three new "IQ" products to help agents work together better.[3] **Work IQ** tracks collaboration context by monitoring which documents people open, who they share them with, and who they email. **Fabric IQ** connects business data to business descriptions, creating concepts that AI can understand and act on. **Foundry IQ** provides retrieval context. Together, these products help agents understand the complete picture and work more effectively as a team.

**Healthcare Gets Agent Collaboration Tools**

The healthcare industry is embracing agent collaboration to solve serious problems and help doctors work more efficiently.[4] **Microsoft** unveiled a **healthcare agent orchestrator**, a framework where multiple specialized agents work together to handle complex medical tasks. Some agents specialize in one type of job, while general reasoning agents handle broader tasks. When they collaborate, they can complete work in minutes that would normally take hours.[4]

For example, the **Atropos Evidence Agent** answers clinical questions within a doctor's workflow without the doctor even needing to ask a question.[4] During patient visits, this agent draws from patient data and surfaces real-world evidence to help the provider make better decisions quickly. Using the healthcare agent orchestrator, multiple agents work together to deliver personalized evidence to clinicians and answer complex questions in minutes without leaving the patient record.[4] This shows how agent collaboration is moving beyond tech companies into industries that save lives.

**Partnership Between Box and AWS**

**Box** and **Amazon Web Services** announced a multi-year collaboration to transform enterprise content management through agent collaboration.[11] According to Swami Sivasubramanian, Vice President of Agentic AI at AWS, "Through our Box collaboration, we're excited to help customers securely leverage their valuable business content with agentic capabilities."[11] This partnership shows how agents can work together to help companies extract value from their sensitive business data while keeping it secure and fully protected. The collaboration includes new AI-powered content solutions and deep technical integrations.

**Financial Services Embraces Agent Collaboration**

In the financial services world, **WorkFusion** partnered with **Allied Engineering Group** to bring AI agents for compliance to the Middle East and Africa regions.[5] WorkFusion offers multiple **AI agents** that work together, including agents named Evelyn, Tara, and Evan. They are trained with up to five years of real-world experience and coordinate together to check for fraud, reduce false alerts, and handle compliance work quickly and accurately.[5] This partnership shows that agent collaboration is moving beyond North America and Europe to support global banking operations and help financial institutions worldwide.

**The Bigger Picture**

Research from MIT and the Boston Consulting Group shows that **agentic AI** represents a fundamental shift in how artificial intelligence works.[8] These systems "can plan, act, and learn on their own" and increasingly "behave like autonomous teammates, capable of executing multistep processes and adapting as they go."[8] This week's announcements prove that major companies worldwide are betting big on making agent collaboration easier, more secure, and more useful for businesses everywhere. The trend is clear: the future of AI is about agents working together, not working alone.

This week brought exciting news about **agent collaboration** - where multiple AI agents work together to complete big tasks. Major companies like Microsoft, Amazon Web Services (AWS), Box, and Fetch AI are focusing on helping different agents talk to each other and work as a team.[3][9][11]

One of the biggest announcements came from **Fetch AI**, which launched a new platform called **ASI:One**.[9] This platform lets your personal AI coordinate with multiple brand agents to complete complex tasks. For example, you can ask it to plan a family trip to New York next month with flights, hotels, and dinners, and it will automatically work with airline agents, hotel agents, and restaurant agents to get everything done.[9] This shows how **agent collaboration** is making AI more useful for everyday tasks.

**Microsoft** announced **Agent 365** at their big tech conference called Ignite.[3][7] This new service helps companies build and manage AI agents that can work together across different systems. Microsoft also shared that **agents in Teams channels can now work with third-party apps and agents**, making teamwork easier.[7] Different agents from different companies can now work together more easily.

The healthcare industry is also jumping into agent collaboration.[4] **Microsoft** introduced a **healthcare agent orchestrator** that uses multiple agents working together to handle complex medical tasks. When these agents work as a team, they can complete jobs that would normally take hours in just minutes.[4]

**Box and Amazon Web Services** announced a **multi-year collaboration** to help companies use AI agents with their business documents.[11] This partnership shows how big tech companies are working together to strengthen agent collaboration.

In banking, **WorkFusion** partnered with **Allied Engineering Group** to bring AI agents for compliance work to the Middle East and Africa regions.[5] These agents work together to check for fraud and keep banking safer. Experts say **agentic AI** is the next big leap beyond simple chatbots.[8]

Agent Collaboration Weekly AI News

Specific Topics