# Microsoft 365 Copilot Published articles for Microsoft 365 Copilot. This is one page of public article previews, not the complete archive. Follow Next page to continue. Summaries are not the original full articles. ## The Microsoft 365 Copilot Agent's Playbook: A Practical Livestream Series for Building Better Agents DevFeed: [The Microsoft 365 Copilot Agent's Playbook: A Practical Livestream Series for Building Better Agents]() Original publisher: [Read original article]() Author: Shavonna Jackson Published: 2026-07-23T19:03:53Z Content type: release Language: en Sources: [Developer Blogs]() Topics: [microsoft 365](), [Model Context Protocol](), [Tooling]() Tags: [agents](), [build](), [developer-tools](), [developers](), [evals](), [evaluation](), [extend](), [flow](), [microsoft-365-copilot](), [microsoft-for-developers]() ### AI overview Microsoft is launching a four-part livestream series about building, extending, grounding, and evaluating declarative agents for Microsoft 365 Copilot. The sessions include presentations, demos, and live Q&A for developers, makers, architects, and technical teams. ### Source excerpt Building on Microsoft 365 Copilot? Here's your playbook. Declarative agents are quickly becoming one of the most exciting ways to extend Microsoft 365 Copilot and bring organizational knowledge, workflows, and tools directly into the flow of work. But as agent capabilities grow, so does the need for practical guidance: How do you build agents that [...] The post The Microsoft 365 Copilot Agent's Playbook: A Practical Livestream Series for Building Better Agents appeared first on Microsoft for Developers. ## GPT-5.6 is now the preferred model in Microsoft 365 Copilot DevFeed: [GPT-5.6 is now the preferred model in Microsoft 365 Copilot]() Original publisher: [Read original article]() Published: 2026-07-09T13:00:00Z Content type: release Language: en Sources: [OpenAI News]() Topics: [microsoft 365](), [Artificial Intelligence](), [Microsoft](), [OpenAI](), [API]() Tags: [ai](), [api](), [copilot](), [gpt](), [microsoft](), [microsoft-365-copilot](), [openai](), [product](), [productivity](), [update]() ### AI overview OpenAI announced that GPT-5.6 will become the preferred model in Microsoft 365 Copilot, supporting work in Word, Excel, PowerPoint, Chat, and Cowork. ### Source excerpt Learn how GPT-5.6 powers Microsoft 365 Copilot with stronger AI capabilities across Word, Excel, PowerPoint, Chat, and Cowork for faster, higher-quality work. ## New in Edge for Business: AI for work, safe from day one DevFeed: [New in Edge for Business: AI for work, safe from day one]() Original publisher: [Read original article]() Author: Patrick Brosset Published: 2026-05-20T16:00:11Z Content type: article Language: en Sources: [Microsoft Edge Blog]() Topics: [Edge for Business](), [agentic browsing](), [Artificial Intelligence](), [Edge](), [secure enterprise browser](), [browser](), [Security](), [data loss prevention](), [Multi-tab reasoning](), [Purview](), [Microsoft]() Tags: [agentic](), [agentic-browsing](), [ai](), [ai-at-work](), [compliance](), [copilot](), [data-loss-prevention](), [edge](), [edge-for-business](), [enterprise](), [enterprise-data-protection](), [microsoft](), [microsoft-365-copilot](), [microsoft-edge](), [multi-tab-reasoning](), [purview](), [secure-enterprise-browser](), [security](), [shadow-ai](), [tenant-data-protection](), [uncategorized]() ### AI overview Edge for Business introduces agentic browsing in limited preview, alongside new AI experiences such as a Copilot-inspired new tab page and mobile support for multi-tab reasoning and YouTube summarization. The article emphasizes enterprise controls, including policy-based enablement, site scoping, user oversight, Purview data protection, and data loss prevention. ### Source excerpt TL;DR: Edge for Business adds agentic browsing in limited preview, a Copilot-inspired new tab page, and mobile availability for multi-tab reasoning and YouTube summarization. These experiences are built on a secure enterprise browser foundation w The post New in Edge for Business: AI for work, safe from day one appeared first on Microsoft Edge Blog. ## The next layer of AI security DevFeed: [The next layer of AI security]() Original publisher: [Read original article]() Author: info@1password.com (Jacob DePriest; Nancy Wang; Jeff Malnick) Published: 2026-03-19T00:00:00Z Content type: article Language: en Sources: [Blog on 1Password Blog]() Topics: [AI Bots](), [AI Chat]() Tags: [ai](), [ai-agent](), [ai-security](), [developers](), [microsoft-365-copilot](), [security](), [unified-access](), [vulnerabilities]() ### AI overview The article examines prompt injection risks in AI agents that act with user-level permissions. Using the EchoLeak vulnerability in Microsoft 365 Copilot as an example, it argues that correct authentication and authorization do not prevent unsafe actions after access has been granted. ### Source excerpt Identity establishes trust. The next problem is how that trust is used. In June 2025, Microsoft patched EchoLeak (CVE-2025-32711), a zero-click vulnerability in Microsoft 365 Copilot that allowed an attacker to exfiltrate sensitive enterprise data, including API keys, confidential documents, and internal conversation snippets, without human intervention. The attack was deceptively simple. An attacker sent a normal-looking email with hidden instructions embedded in it. A human would not notice them, but the model could interpret them. The email remained dormant until Copilot later pulled it into context for another task. At that point, the instructions triggered, and the agent used the victim's existing permissions to retrieve and disclose sensitive information. The specific vulnerability matters, but the broader lesson matters more. A system can authenticate correctly, authorize correctly, and still produce the wrong outcome. Microsoft patched EchoLeak before it was publicly disclosed. Since then, researchers have identified similar patterns across AI-assisted workflows, including additional Copilot-related vulnerabilities in 2026. These are not isolated issues. They point to a broader, repeatable pattern. When AI systems process untrusted content and act with user-level permissions, prompt injection and unintended data access become systemic risks rather than edge cases. This is not a failure of authentication or authorization. It is what happens after both succeed. Systems are behaving exactly as designed, and still producing the wrong outcomes. Prompt injection breaks the execution model Prompt injection isn't just a model issue. It's a signal that something is breaking between how systems reason and how they act. The industry sees the same thing. OWASP Top 10 for LLM applications ranks prompt injection as a primary attack vector, and research from OpenAI and others shows that models cannot reliably distinguish between legitimate instructions and malicious ones e