Bringing Progress Agentic RAG To Microsoft Teams

Ask questions and get answers in Microsoft Teams with Progress Agentic RAG
by Michael Marolda Posted on October 05, 2026

The October release adds a native Microsoft Teams application to Progress Agentic RAG, giving any AI experience your organization has already built a direct path into the tool your employees use every day. It's available through the Microsoft Teams store, runs on the same knowledge layer and governance your deployment already has in place, and requires no rebuild to turn on.  

A good deployment that nobody uses 

You've likely already seen this pattern play out. A team builds a genuinely capable AI assistant — strong retrieval, accurate answers, solid governance — and deploys it to a portal or a standalone application. Usage never takes off. Employees already move between roughly nine applications a day, and asking them to add a tenth just to consult an AI assistant is a real cost, not a minor inconvenience. The assistant that gets used is the one that's already where people are working. 

That puts you in an uncomfortable position. You approved the AI investment, and the number you're evaluated on isn't retrieval accuracy: it's usage. A technically excellent deployment that nobody opens reads to the board and the CFO as a failed bet, no matter how sound the underlying architecture was. And every additional delivery surface your organization wants (Teams today, something else tomorrow) has historically meant scoping a new front-end project, which slows the roadmap and adds cost that has nothing to do with improving the AI itself. 

The assistant moves to where the work already happens 

Progress Agentic RAG now deploys directly inside Microsoft Teams as a native application, distributed through the Microsoft store. Nothing about the underlying deployment changes — the same indexed content, the same access controls, the same source-cited and quality-scored answers your team already trusts. What changes is that employees can now ask questions inside the application they already have open, instead of being asked to visit somewhere else first. 

In practice, this opens up a few different ways to put the same deployment to work: 

  • Internal knowledge assistant. Employees query Teams directly for policy questions, product documentation, or anything else your organization has indexed — no separate login, no new habit to build. 

  • Frontline and field reach. Because Teams is the standard collaboration surface across a huge share of enterprises, this also reaches frontline and field employees, or workers on shared devices, who were realistically never going to open a browser-based tool during a shift extending a deployment you've already paid for to people it couldn't reach before. 

  • Sales enablement and competitive intelligence. Reps can ask Teams for the latest battlecard, pricing guidance, or how to position against a specific competitor without digging through a wiki or pinging a colleague surfacing the same governed, source-cited content in the moment a deal actually needs it. 

A capability every future deployment inherits. For organizations running more than one internal AI use case, each one built on Progress Agentic RAG inherits the same Teams delivery automatically — this isn't a one-time integration project, it's a capability every future deployment gets by default. 

What this means for you 

The most immediate benefit is that the adoption objection you've been fielding on every AI proposal now has a real answer, and it costs nothing further to implement. Delivery surface becomes a configuration choice instead of a new project, which means the engineering investment your team already made finally reaches the people it was built for without asking for another dollar of budget to get it there. 

It also changes the shape of your next roadmap conversation. Instead of defending a caveat about usage, you're presenting a distribution story backed by a number people already understand: hundreds of millions of Teams users across a huge base of organizations already standardized on Microsoft. And because this is inherited automatically by any future AI experience built on the same knowledge layer, you're not solving distribution once you're solving it permanently, for whatever your team decides to build next. 

For a deployment you've already justified to the board once, that's the difference between defending it again next quarter and pointing at a track record instead. 

Learn more about Microsoft Teams in Progress Agentic RAG today.


Author Michael Marolda in front of Niagara Falls
Michael Marolda

Product Marketing Manager, Senior

Michael Marolda is a seasoned product marketer with deep expertise in data, analytics and AI-driven solutions. He is currently the lead product marketer for the Progress Agentic RAG solution. Previously, he held product marketing roles at Qlik, Starburst Data and Tellius, where he helped craft compelling narratives across analytics, data management and business intelligence product areas. Michael specializes in translating advanced technology concepts into clear, practical business terms, such as Large Language Models (LLMs), Retrieval-Augmented Generation (RAG) and modern data platforms.
More from the author

Related Products:

Agentic RAG

Progress Agentic RAG transforms scattered documents, video, and other files into trusted, verifiable answers accelerating AI adoption, reducing hallucinations, and improving AI-driven outcomes.

Get in Touch

Related Tags

Related Articles

Progress Agentic RAG Adds a Smart Agent Plus Native Teams and WordPress Support
The October release adds three capabilities to Progress Agentic RAG with nothing to install: a Smart Agent that answers questions using both indexed content and live business apps like a CRM, a native Microsoft Teams app, and a WordPress plugin that keeps content current. Built-in citations, quality scoring and audit logs let reviewers trace each step the agent takes. The blog ends by inviting readers to an October 22 walkthrough or a demo.

Michael Marolda October 01, 2026
Smart Agent Is Here: Retrieval That Plans, Verifies, and Reaches Beyond Your Knowledge
Introducing the Smart Agent, a new capability in Progress Agentic RAG that breaks complex questions into sub-questions, decides where to look for each one, and keeps searching until the answer is complete. It works on existing setups with no new pipeline or re-indexing. The blog highlights two additions: live data from business apps like Zendesk, Salesforce and ServiceNow through MCP, and a built-in web search tool backed by Perplexity and Google Gemini. Both are cited alongside internal content in a single answer.
How Progress Agentic RAG Reached #1 on the Snowflake MADQA Leaderboard
Progress Agentic RAG ranked #1 on Snowflake's MADQA Leaderboard, an independent benchmark built with Oxford, UNC-Chapel Hill, and Hugging Face that tests whether AI answers are accurate and properly grounded in real documents, not just plausible-sounding. The win validates a year of work since the Nuclia acquisition building the Agentic Knowledge Layer (agentic capability embedded across ingestion, retrieval, and evaluation) and lands as the broader market shifts toward trust and governance as the deciding factor for enterprise AI.
Prefooter Dots
Subscribe Icon

Latest Stories in Your Inbox

Subscribe to get all the news, info and tutorials you need to build better business apps and sites

Loading animation