CoPilot has generated lot of interest, and users this year. However, for many its been a bumpy ride. Often the way with rapidly evolving, paradigm shifting technology. Earlier is the year there were concerns over performance, Last month a new Ui looked good but users generally felt it was a backward step, less easy to use and more generic answers. Microsoft just keeps fixing and improving. Last month there were negative comparisons with from Salesforce and Google .
That is the history of Microsoft. It was late to Office products, late to mobile, late to the cloud etc., but it caught up and challenged the leaders. A key gap versus competitor products is now addressed Salesforce planted their wheels firmly on the race track with Agentforce, Microsoft, Salesforce and Workday have agents at the centre of their AI plans, while Oracle and ServiceNow are also in the race.
“Move over, copilots: it’s time to make room for the AI agents.” Financial Times September 22 2024.
The ability to create autonomous AI “agents” within Microsoft’s Copilot Studio will reach the public preview stage at this month’s Microsoft Ignite conference, the company said in October.
Salesforce wants to stress how imperative AI agents are to the future of AI developments.
Agents take generative AI a step further by building upon the fundamentals of chatbots and excelling them with higher intelligence, empathy, and capabilities. Traditional bots are like pre-programmed assistants, so they can only answer questions or queries with answers that they have “stored” – agents use a blend of large language models (LLMs) and generative AI to understand the full context of customer messages. They use the wealth of data that your org has to offer more bespoke answers, providing more of a personal, humanistic service.
Microsoft sees AI agents as more nimble, programmable versions of its Copilot AI chatbot. Microsoft 365 chief marketing officer Jared Spataro described agents as “the new apps for an AI-powered world.”
“Every organization will have a constellation of agents,” Spataro predicted, “ranging from simple prompt-and-response to fully autonomous. They will work on behalf of an individual, team or function to execute and orchestrate businesses process.”
Very similar to Agentforce, Copilot’s agents allow users to enhance functionality by drawing from an organization’s data. The more (clean) data that these agents can draw from, the smarter and more tuned-in the responses and actions will be. According to Charles Lamanna, the Corporate Vice President of Business & Industry Copilot: “(Autonomous agents) will fundamentally change business processes. There will be as many agents as there are documents or SharePoint sites in an organization.”
Building Agents in Copilot Studio
Copilot Studio connects the Copilot AI to an organization’s various data sources, from the Microsoft Graph to Dynamics 365. Starting from November’s public preview, users can build their own agents within Copilot Studio and train these on those same data sources.
The agents will run on a variety of AI models, including OpenAI o1 which uses “chain of thought” reasoning to answer prompts. These may therefore take longer to solve problems, but are more likely to provide accurate outputs, specifically in response to complex, multistep problems. “Through training, they learn to refine their thinking process, try different strategies, and recognize their mistakes,” OpenAI said, which is optimized for reasoning through complex problems. Agents are meant to run largely without human intervention. The Agents can be scheduled to run at set intervals, or be programmed to perform actions in response to specific triggers from other applications or tools.
Though agents act autonomously, Microsoft users can view their internal logic for each task that they resolve. Knowing why an agent reacts to a trigger will help users reinforce correct behavior, or debug undesired behavior. Additionally, an “Activity” tab will keep a running log of each time an agent is triggered into action, with details such as task completion, decisions and more.
Prebuilt Agents for Dynamics 365
For Microsoft’s CRM and ERP customers, the company has announced a set of 10 specialized, prebuilt AI agents in Dynamics 365. These agents are meant to “build capacity for sales, service, finance, and supply chain teams,”
Microsoft will roll out public previews of these agents starting in late 2024 and into early 2025:
- Sales Qualification Agent (for Dynamics 365 Sales)
- Sales Order Agent (for Dynamics 365 Business Central)
- Supplier Communications Agent (for Dynamics 365 Supply Chain Management)
- Financial Reconciliation Agent (for Microsoft 365 Copilot for Finance)
- Account Reconciliation Agent (for Dynamics 365 Finance)
- Time and Expense Agent (for Dynamics 365 Project Operations)
- Customer Intent Agent (for Dynamics 365 Customer Service)
- Customer Knowledge Management Agents (for Dynamics 365 Contact Center)
- Case Management Agent (for Dynamics 365 Customer Service)
- Scheduling Operations Agent (for Dynamics 365 Field Service)
Microsoft is developing more Dynamics 365 agents for 2025, it said.
Key Features and Benefits of Microsoft Copilot
- Intelligent Writing Assistance: Microsoft Copilot leverages AI to provide intelligent writing suggestions and assistance across Microsoft Office apps like Word, PowerPoint, and Outlook. It can help draft documents, refine content, create compelling presentations, and compose emails, boosting productivity and quality.
- Data Analysis and Visualization: In Excel, Copilot empowers users to explore and analyze data more efficiently. It can generate formulas, create visualizations, and provide insights based on the data, enabling faster and more informed decision-making.
- Meeting and Collaboration Enhancement: Copilot integrates with Microsoft Teams to transcribe meetings, summarize discussions, capture action items, and even suggest relevant files or information. This streamlines collaboration and ensures important details are not missed.
- Customizable AI Assistant: Microsoft Copilot offers a unified “Copilot” experience that allows users to access data across their Microsoft Graph and leverage LLM functionality through natural conversations. Users can customize prompts and actions to align with their specific needs and workflows.
- Seamless Microsoft 365 Integration: Copilot is deeply integrated into the familiar Microsoft 365 suite, providing a consistent and intuitive AI-powered experience across Word, Excel, PowerPoint, Outlook, Teams, and other apps. This tight integration minimizes disruption and facilitates rapid adoption.
- Contextual and Personalized Assistance: By grounding prompts in a user’s business data from the Microsoft Graph, Copilot delivers contextual and personalized assistance tailored to the individual’s role, projects, and organizational context.
