This article is contributed. See the original author and article here.
In the fast-paced world of sales, sellers are now expected to be adept multitaskers. As they engage with customers, the demands of various tasks and follow-ups can quickly accumulate. Effectively managing these aspects is crucial for streamlining processes, minimizing manual intervention and significantly enhancing the overall customer experience. By staying organized and leveraging tools to keep track, sellers can meet their goals more effectively. When we released focused view in April 2023, we had precisely this goal in mind – to transform the current user experience while working on records within Dynamics 365 Sales.
Since its launch, focused view has not only achieved remarkable success but has also gained widespread user adoption. Thousands of sellers now rely on it as a swift solution to navigate records efficiently and address open tasks promptly. A closer look at our usage analysis indicated around a 50% reduction in overall task execution time compared to the current grid view for the same set of actions.
With the new enhancements, our commitment is to further elevate the overall user experience, aiming to provide a comprehensive set of capabilities within focused view. This ensures that users can accomplish all tasks seamlessly without the need to switch contexts across multiple views.
This blog delves into the introduced changes, detailing how users can leverage these updates to streamline their daily tasks.
What is focused view?
Focused view is a new work surface which allows users to view all their records as a list, while being able to work on any of them without having to switch context multiple times between the record form and the list of records. It supports easy filtering, sorting, and card customization capabilities to ensure you see the data that matters to you.
Focused view
What are the new enhancements?
Expanding the reach of focused view
As part of the current release, we are introducing focused view for Dynamics 365 entities. It’s now enabled automatically for all users, with no set up. Thus, Dynamics 365 users can leverage it for any out of the box or custom entities that they work on. Users should be able to see the focused view button or find it within the “show as” dropdown for all their entities, as the first button of the ribbon command bar.
Maintaining user preferences
We are committed to respecting our users’ preferences to ensure they always see the view they use the most first. To achieve this, our system now seamlessly retains the last-used work surface for each user every time they log into Dynamics 365 Sales. This enables users to effortlessly pick up right where they left off, regardless of any system default settings for a given entity. At our core, we prioritize our users’ individual choices, ensuring that their preferred work surface always takes the lead.
Introducing new capabilities
We are leaving no stone unturned to make focused view the ultimate work surface to cater to all our users’ needs! With the new release, we are introducing several new capabilities to ensure users can complete all their required tasks from a single place:
Multi-select records: With the enhanced focused view, users can now multi-select records and execute bulk functionalities in a seamless manner.
Support the view level ribbon command bar: Within the focused view, users no longer need to navigate to a grid experience to make updates. Instead, we have now made available an easy access point through the ribbon command bar. It now allows users to take instant action on any record(s) without any additional navigation.
Multi-select and ribbon command bar
Advanced filtering capability: We have introduced the ability for users to create their own filter query. In addition, users can save it as a custom view from within focused view. This helps them view and work on records that matter.
Advanced filter query
How can I make focused view the default landing page?
With all the new capabilities and ease of use, users will likely want to make focused view their default worksurface. To help achieve that, we are making it the default landing page for Lead entity as an out of the box option. For the other core entities, namely Account, Contact and Opportunity, we are providing an easy option for admins to make it the default option for their org from within the focused view specific settings. These can easily be adjusted for an organization’s specific needs.
Making focused view default for Lead, Opportunity, Account and Contact
For other entities, users can use the existing custom settings option within advanced settings. They simply need to choose the relevant entity and then select focused view from the list of available controls.
Conclusion
With these updates, focused view becomes the worksurface where users can view, plan and execute all their sales related tasks in a seamless and efficient manner. It helps them with greater task success rate and faster execution speed.
We are simplifying the ability for a users to get started. There’s now no setup required at either their or admin level. With these enhancements, users will find focused view readily available as the primary option on the ribbon command bar when navigating the entity grid. This streamlined accessibility ensures a hassle-free initiation, allowing users to effortlessly view and utilize focused view as their default choice.
So go ahead and start leveraging focused view as the go-to workspace for all sales related tasks and save time to concentrate building relations and closing deals!
This article is contributed. See the original author and article here.
We are thrilled to announce that this newsletter edition officially marks one full year of Logic Apps’ Ace Aviators! From our initial newsletter and livestream in February of last year, it’s been an incredible journey witnessing this community take flight. Of course, none of this smooth flying would have been possible without YOU! So, to all our aviators, thank you for reading, watching, and participating this past year. Make sure to keep sharing and posting to #LogicAppsAviators so we can continue to navigate the skies of innovation together.
What is your role and title? What are your responsibilities associated with your position?
Although my title is Solution Architect, my role is of Practice/Competency Lead, and I lead the Microsoft Integration practice (I’m responsible for leading and growing our expertise) within Birlasoft Limited. My role is multifaceted, encompassing strategic leadership, team development, client engagement, and operational excellence.
Below is a breakdown of my responsibilities:
Strategic Leadership:
Defining the vision and direction for the practice, aligning it with the overall organizational strategy.
Identifying and pursuing growth opportunities, including new markets, services, and partnerships.
Staying abreast of industry trends and innovations to ensure our practice remains competitive (I’m not at my best now, but I’m taking steps to improve).
Team Development:
Building and nurturing a high-performing team of experts in our practice area.
Providing mentorship and coaching to help team members develop their skills and expertise.
Fostering a collaborative and innovative work environment.
Client Engagement:
Building strong relationships with clients and understanding their needs and challenges.
Developing and delivering high-quality solutions that meet client requirements.
Managing client expectations and ensuring their satisfaction.
Operational Excellence:
Establishing and maintaining efficient processes and workflows within the practice.
Managing budgets and resources effectively.
Measuring and monitoring key performance indicators (KPIs) and driving continuous improvement.
Overall, my goal is to lead the Microsoft Integration Practice to success by delivering exceptional value to our clients, developing our team, and contributing to the growth of the organization.
Can you provide some insights into your day-to-day activities and what a typical day in your role looks like?
Typical days begin with a coffee-fueled review of emails, calendar, and upcoming meetings, deadlines, and calls. A substantial portion of the day is then dedicated to collaborative meetings with project teams and clients, focusing on progress updates, challenge resolution, and recommendation presentations. Drafting proposals for new RFPs/RFIs or executing ongoing project plans occupies another significant segment of the workday. As the practice lead, I am also prepared to address any ad-hoc requests or situations that may arise within the practice.
The positive response to our proposals, built on strong customer focus and industry best practices, has ignited growth in the Birlasoft Integration Practice. To capitalize on this momentum, I’m busy interviewing and assembling a team of exceptional individuals. It’s an honor to be part of this thriving practice (and I can’t wait to see what we achieve together)!
So, my day involves doing development work, working on POC/RFP/RFI, solution designing, Interviews, handling escalations, mentoring team, resources, and project planning etc.
What motivates and inspires you to be an active member of the Aviators/Microsoft community?
I am a very strong believer in The Value of Giving Back and by nature I like helping people (as much as I can).
What Inspired: When I had started learning BizTalk, I took lot of help from the community written articles and Microsoft documentation. I will be very honest, although Microsoft documentation is very apt but the articles written by community members were more easy to understand, had a different perspective, simple ways to explain etc.
And that’s how I started with an intention of helping people like me by sharing whatever limited knowledge I have in a simplified manner (at least I try to) by various means – answering on forums, writing articles etc. I maintain a blog Techfindings…by Maheshkumar Tiwari through which I share my findings/learnings and it’s been over a decade I am doing it, over LinkedIn/Facebook answering individuals to their questions, also sometimes on groups.
What Motivates: When you receive mail/message/thank you note from someone you don’t know, saying that the content really helped them – to solve the problem, to crack the interview, to clear the understanding etc. — It warms my heart more than any award. It’s the fuel that keeps me creating, knowing I’m truly touching lives.
Looking back, what advice do you wish you would have been told earlier on that you would give to individuals looking to become involved in STEM/technology?
While theoretical knowledge is important, prioritize developing practical skills like coding, data analysis, project management, and problem-solving. Don’t wait for the “perfect” moment or project to begin. Try mini-projects, tinker with code, participate in online challenges. While doing this embrace failures as learning opportunities and steppingstones to improvement.
No one knows everything, and reaching out for help is a sign of strength, not weakness. Seek guidance from seniors, peers, online communities, or any available resources.
Focus on the joy of learning, exploring, and problem-solving, not just achieving a specific degree or job title. Curiosity and a love for understanding how things work will fuel your passion and resilience through challenges.
What are some of the most important lessons you’ve learned throughout your career?
The only thing which is constant is Change – the sooner we accept it and develop/have a mindset to adapt, the better it is.
Survival of the fittest is applicable to every phase of personal/professional life. You really can’t blame others.
Maintaining a healthy balance between work and personal life (unfortunately I am failing in this), practicing self-care, and managing stress are crucial for long-term success.
Building a successful career takes time, dedication, and perseverance. Set realistic goals, celebrate milestones, and don’t get discouraged by setbacks.
Enjoy the process, keep learning, and adapt to the ever-changing field.
Imagine you had a magic wand that could create a feature in Logic Apps. What would this feature be and why?
Without a second thought, following is what I would have created – A wizard which asks me questions about my workflow requirement and once the questionnaire ends, complete workflow should be presented.
Well, that’s from magic wand perspective :smiling_face_with_smiling_eyes:, but above is very much doable.
But, as of now following are the things which we can do at present (few points are from my team – want to share maximum ideas to make Logic app more robust)
Logic Apps should have a feature of disabling the actions from designer. This will help developers in unit testing the code efficiently. We can achieve this by commenting out Json in code view or by creating a backup workflow but that’s a tedious task.
Versioning missing in Azure standard Logic Apps
Breakpoint option should be enabled, so that it will help in debugging.
Retry from the failed step should be extended to loops and parallel branches as well
Need out of box support for Liquid Map debugging, Intellisense support would be also good to have
For now only Json schema is supported in http trigger, if xml support can be added to it.
CRON expression support in Logic app recurrence trigger
Reference documentation as to which WS plan should one choose based on number of workflows, volume of messages processed etc.(will help to justify the cost to clients)
Exact error capture for actions within loop/action within a scope inside a scope etc.
Support for partial deployment of workflows in a single logic app (adding only the new workflows and not overwrite all)
Check out this customer success story about Datex leveraging Microsoft Azure Integration Services to transform its infrastructure for a more modern solution. Azure Integration Services played a crucial role in enabling flexible integrations, data visualization through Power BI, and efficient electronic data integration (EDI) processes using Azure Logic Apps. Read more in this article about how AIS helped provide Datex with a low-code environment, faster time-to-market, cost savings, and enhanced capabilities.
Take a deeper dive into the new target-based scaling for Azure Logic Apps Standard update and how it can help you manage your application’s performance with asynchronous burst loads.
Read more on how Azure Logic Apps can unlock scenarios where it’s required to integrate with IBM i applications in another Mission Critical Series episode.
Struggling to manage your application settings during development and testing, especially when switching between local and cloud environments? Watch Sri’s video to learn how to efficiently manage your app settings.
This article is contributed. See the original author and article here.
According to our Forrester Consulting study, software that helps organizations elevate field service delivery can improve financial performance in two ways: by helping increase customer retention and expansion by exceeding service expectations, and by increasing productivity. We are pleased to share the results of a December 2023 Forrester Consulting Total Economic ImpactTM (TEI) Study commissioned by Microsoft. Forrester calculates Microsoft Dynamics 365 Field Service delivered benefits of $42.65 million over three years to a composite organization. The total investment required was $9.5 million and provided a ROI of 346% with a payback period of less than six months.
Methodology and purpose
TEI is a methodology developed by Forrester Research to assist companies with technology-related purchase decisions by providing business decision-makers with a framework to evaluate the potential financial impact of the technology on the entire organization.
Forrester Consulting interviewed 11 representatives from seven organizations with experience using Dynamics 365 Field Service to conduct this TEI study. The characteristics of these businesses and the results of the interviews were then aggregated to develop a composite organization. The key findings of the study are based on the composite organization and are summarized below.
Key challenges
The organizations that were interviewed for the study shared the following challenges prior to adopting Dynamics 365:
Lack of visibility into field service status
Communication issues among management, sales, and service teams
Technicians’ inability to complete work orders in a timely fashion
With these challenges top of mind, the interviewees sought to invest in a solution that could improve the productivity and efficiency of their field service teams, enable cost savings, and lead to customer retention and profitability.
Key findings
Dynamics 365 Field Service helps organizations deliver onsite service to customer locations. The application includes work order automation, scheduling algorithms, asset servicing, mobility, Microsoft 365 integration, and infusion of generative AI through Copilot to set up frontline workers for success when they are onsite providing service for customers. It is part of the larger Dynamics 365 portfolio of applications designed to work together to deliver efficiency and improve customer experience.
Forrester’s study revealed seven quantifiable impact areas: increased first-time fix rate, increased field technician productivity, eliminated standard time-to-invoice delays, avoided travel time, improved dispatcher productivity, enhanced management productivity, and retired legacy solutions.
We examine each of these areas below in more detail to understand how Dynamics 365 Field Service delivers value across field service organizations.
Increased first-time fix rate
Sending out field technicians to resolve customer issues is expensive even for the first visit, so many organizations want to do everything they can to avoid a second truck roll to resolve a problem. Deploying Dynamics 365 Field Service helped the organizations to increase their first-time fix rates by ensuring that technicians could quickly locate equipment, understand history and problems, tap into institutional knowledge about problems, and ensuring they had stocked the appropriate parts for service. Increasing the first-time fix rates also helped these organizations avoid 12% of second visits by additional technicians to complete a service call.
Increased technician productivity
Interviewees found that Dynamics 365 Field Service helped to remove many administrative tasks, so field technicians could spend more of their time focusing on addressing customer issues. Organizations were also able to use the solution to find the best field technician for each job, determine the most efficient route for getting to a customer site, and ensuring that technicians were carrying the right parts and tools to fix the problems. In addition, the Microsoft Dynamics 365 Remote Assist feature helped technicians use institutional knowledge, rather than having to spend time tracking down a peer or documentation. And both managers and technicians had greater visibility into technicians’ service calls, which helped them to plan for greater efficiency when scheduling customer work orders. All of this resulted in increasing field technician productivity by up to 14% once Dynamics 365 Field Service and Remote Assist were fully implemented.
Decreased time to invoice customers
An inability to integrate field service applications with key applications in finance often meant considerable time gaps between when a service order was completed and a customer was billed for service. One interviewee noted that using paper-based processes for invoicing service calls meant up to a month could go by before an invoice was sent, but after implementing Dynamics 365 Field Service, customers could be invoiced for work orders on the same day. For the composite organization, eliminating standard time-to-invoice delays resulted in $2.8 million savings in interest on accounts receivable.
Avoided travel time
One key challenge interviewees shared was that field technicians could lose significant time due to traffic delays or inefficient job routing, which required them to go out of their way to get to customer sites. With Dynamics 365 Field Service, dispatchers could ensure that planned routes were the most efficient and economical and that technicians’ routes were updated constantly to avoid potential slowdowns from traffic or road construction. The availability of mixed reality apps like Dynamics 365 Remote Assist and Dynamics 365 Guides also meant that field technicians could get assistance without subject matter experts needing to be on-site.
By using routing algorithms and traffic updates provided by Dynamics 365 Field Service, the composite organization can create more efficient schedules for technicians and save $2.1 million over three years.
Improved dispatcher productivity
Service dispatchers were often relying on highly manual processes to assign field technicians to jobs. Any change in staffing or scheduling increased inefficiency, especially since schedules were shared across whiteboards, spreadsheets, and calendar apps, meaning mistakes and deletions could be made. Dynamics 365 Field Service enables service organizations to automate scheduling and rescheduling for customer service calls. It also helps service managers match the best service technician for a work order based on time or expertise. One project manager interviewed for the study stated that having everything in one place provided better visibility for schedulers that helped them understand job progress and seamlessly include everyone in the workflow.
Overall, the composite organization saw a 40% improvement in dispatcher productivity as well as cost savings of $1.6 million.
Enhanced management productivity
optimize your field service management with proven solutions
Some interviewees had reported that field service managers spent a lot of time resolving scheduling issues, tracking missing parts inventory, and following up on incomplete jobs. With the ability to automate more processes in Dynamics 365 Field Service, those field service managers found they had more time to focus on strategic tasks that help their teams improve in other ways. Because reporting provided managers with information they didn’t have access to before, they were able to get a clearer view into technician productivity, work order status, parts inventory, and other metrics that helped them discover and address gaps so they could meet monthly targets. Service managers also had greater visibility into areas where field technicians needed more training and support, so they could improve team performance overall.
Service managers enhanced management productivity by 100 hours per year.
Retired legacy solutions
In the past, participant organizations used various combinations of email, calendar and scheduling apps, spreadsheets, or third-party field service tools to manage their field service efforts. Implementing Dynamics 365 Field Service, which integrates with Microsoft 365 apps such as Outlook and Microsoft Teams, helped to reduce licensing, administration, and maintenance costs for maintaining separate applications to support field service teams.
Other benefits
Beyond the quantified benefits detailed above, the organizations participating in the TEI study also experienced other benefits, including:
Improved customer experience through increased efficiency and more accurate updates about service calls.
Enhanced employee experience by enabling field technicians to use their mobile phones to complete most of their work tasks.
Improve service delivery speed and quality by using Copilot in Dynamics 365 Field Service in their field service operations.
Access to mixed reality applications such as Dynamics 365 Remote Assist and Microsoft Dynamics 365 Guides to help support field technicians on service calls.
Next steps
As we have seen here, Forrester’s study uncovered seven quantifiable impact areas along with several other significant unquantifiable benefits. When combined, these factors resulted in benefits of $42.65 million over three years for the composite organization. The total investment required was $9.5 million, leading to a 346% ROI with a payback period of less than six months.
This article is contributed. See the original author and article here.
Microsoft Defender for Cloud
Monthly news
February2024 Edition
This is our monthly “What’s new” blog post, summarizing product updates and various new assets we released over the past month. In this edition, we are looking at all the goodness from January 2024.
Legend:
Product videos
Webcasts (recordings)
Docs on Microsoft
Blogs on Microsoft
GitHub
External content
Product improvements
Announcements
Microsoft Defender for Cloud
We’re announcing the release of Defender for Cloud’s agentless malware detection for Azure virtual machines (VM), AWS EC2 instances and GCP VM instances, as a new feature included in Defender for Servers Plan 2. Agentless malware detection for VMs is now included in our agentless scanning platform. Agentless malware scanning utilizes Microsoft Defender Antivirus anti-malware engine to scan and detect malicious files. Any detected threats, trigger security alerts directly into Defender for Cloud and Defender XDR, where they can be investigated and remediated. The Agentless malware scanner complements the agent-based coverage with a second layer of threat detection with frictionless onboarding and has no effect on your machine’s performance.
We’re announcing the general availability (GA) of the integration between Defender for Cloud and Microsoft Defender XDR (formerly Microsoft 365 Defender). The integration brings competitive cloud protection capabilities into the Security Operations Center (SOC) day-to-day. With Microsoft Defender for Cloud and the Defender XDR integration, SOC teams can discover attacks that combine detections from multiple pillars, including Cloud, Endpoint, Identity, Office 365, and more.
Container security is an integral part of Microsoft Defender for Cloud, a Cloud Native Application Platform (CNAPP) as it addresses the unique challenges presented by containerized environments, providing a holistic approach to securing applications and infrastructure in the cloud-native landscape. As organizations embrace multicloud, the silos between cloud environments can become barriers for a holistic approach to container security. Defender for Cloud continues to adapt, offering new capabilities that resonate with the fluidity of multicloud architecture. Our latest additions to AWS and GCP seamlessly traverse cloud silos and provide a comprehensive and unified view of container security posture.
In this blog we dive deep into agentless container security for AWS and GCP.
We have added nine new Azure security recommendations aligned with the Microsoft Cloud Security Benchmark. These new recommendations are currently in public preview.
Cybersecurity risks pose a significant threat to organizations of all sizes. As a result, security teams must be diligent in their efforts to protect their networks and data from potential breaches. However, with the increasing complexity of the digital environment and the expanding attack surface, security teams are faced with more and more tasks to improve the organization’s posture as well as investigating potential incidents. This can lead to critical security risks being overlooked or delayed, leaving organizations vulnerable to cyber-attacks. It becomes increasingly more important to estimate the risk created by the security issues in the environment’s configuration and to prioritize their mitigation correctly.
Prioritized cyber risks allow security teams to focus their efforts and resources on the most critical threats, ensuring that they are addressed promptly and effectively, which ultimately helps to reduce the organization’s overall risk profile.
In this article we discuss a new feature in Defender CSPM helping customers to rank the security issues in their environment configuration and fix them accordingly. This feature is based on the presented framework and enhances the risk prioritization capabilities of Defender CSPM.
While containers have revolutionized modern software development, the complexity of dependencies in containerized environments and the expanded attack surface they present are still significant hurdles for security professionals. The initial step in securing these environments involves identifying vulnerabilities within container images. Yet, the most time-consuming task can often be identifying the right development team to address these vulnerabilities, particularly the mission-critical ones. Microsoft Defender for Cloud addresses this critical need with its container mapping feature. This blog post explores how Defender for Cloud streamlines the process of tracing vulnerabilities in container images back to their origins in CI/CD pipelines, specifically within Azure DevOps and GitHub environments. This functionality is key to facilitating effective developer remediation workflows, thereby enhancing the security posture of cloud-native applications.
This blog post explores how Defender for Cloud streamlines the process of tracing vulnerabilities in container images back to their origins in CI/CD pipeline to facilitate the vulnerability remediation process.
Microsoft Defender for Servers plans require Azure Arc deployment on AWS/GCP machines. This interactive workbook provides an overview of machines in your environment showing their Azure Arc Connected Machine agent deployment status.
Note: If you want to stay current with Defender for Cloud and receive updates in your inbox, please consider subscribing to our monthly newsletter: https://aka.ms/MDCNewsSubscribe
This article is contributed. See the original author and article here.
Do you know about AI Agents? How to apply AI Agents in different scenarios? For AI Agents, Microsoft released the open source framework Autogen. But what is its relationship with Semantic Kernel and Prompt flow? I hope this series can answer your questions. Let everyone have a clear understanding of AI Agents, how to combine Autogen, Semantic Kernel, and Prompt flow to build intelligent applications
Around artificial intelligence, humans have made many attempts in different industries and different application scenarios. With the emergence of LLMs, we have transitioned from traditional chatbots with process predefinition plus semantic matching to Copilot applications that interact with LLMs through natural language. In the past year or so, everyone has mainly focused on basic theories based on LLMs. In 2024 we should enter the application scenario of LLMs. We have a lot of papers, application frameworks, and practices from large companies to support the implementation of LLMs applications. So what is the final form of our so-called artificial intelligence applications? What you can think of is GitHub Copilot for programming assistance, Microsoft 365 Copilot for office scenarios, and Microsoft Copilot on Windows or Bing, etc. But think about the application of Copilot, which relies more on individuals to guide or correct through prompt words, and does not achieve fully intelligent applications. In the 1980s, we began to try to do fully intelligent work, and AI Agent is a fully intelligent best practice.
The agent interacts with the scene where it is located, receives instructions or data in the application scene, and decides different responses based on the instructions or data to achieve the final goal. Intelligent agents not only have human thinking capabilities, but can also simulate human behavior. They can be simple systems based on business processes, or they can be as complex as machine learning models. Agents use pre-established rules or models trained through machine learning/deep learning to make decisions, and sometimes require external control or supervision.
Characteristics of the AI agent:
Planning, divide steps based on tasks, and have a chain of though. With LLMs, it can be said that the planning ability of the agent is greatly enhanced, and the understanding of the task can be more accurate.
Memorythe ability to remember behavior and part of logic, the ability to store experiences, and the ability to self-reflect.
Tool Chain, such as code execution capabilities, search capabilities, and computing capabilities. It can be said that he has strong mobility
perceive and obtain informationsuch as pictures, sounds, temperatures, etc. based on the scene, thus providing better conditions for execution.
Technical support for realizing intelligent agents
There is considerable application practice in the application of LLMs.
There are many frameworks for implementing intelligent agents. The previously mentioned Semantic Kernel or Autogen can implement intelligent agents. The Assitants API has also been added under OpenAI to enhance the model’s capabilities in agents. Now OpenAI’s Assitants API opens up the capabilities of code interpretation, retrieval, and function calling.Assitants APIof Azure OpenAI Service is also coming soon, which can be said to provide enough wisdom for the application capabilities of agents.
Many people pay more attention to the application layer framework. People often compare Semantic Kernel and Autogen. After all, both are from Microsoft and have good task or plan orchestration capabilities. However, some people always feel that the two have many similarities.
Semantic Kernel vs Autogen
Semantic Kernel focuses on effectively dividing individual tasks into steps in Copilot applications. This is also the charm of the Semantic Kernel Planner API. Autogen, on the other hand, focuses more on the construction of agents, dividing tasks to complete goals and assigning tasks to different agents. Each agent executes individually or interactively according to the assigned tasks. Behind each agent’s task can be a streaming task arrangement, or an extended method for solving problems, or skills triggered by corresponding prompts, which can be organized in conjunction with Semantic Kernel plugins. When we want to have a stable task output, we can also add prompt flow to evaluate the output.
Use Semantic Kernel to implement AI agents.
Semantic Kernel has added support for agents in the Experimental library, introduced AgentBuilder, and combined with the Assistant API to complete the brain configuration of the agent. The corresponding planning, memory and tools are defined using different plugins.
WithOpenAIChatCompletionrequires OpenAI/Azure OpenAI Service models that support Assistants API (soon to be released). Currently supported OpenAI models are GPT-3.5 or GPT-4 models.
WithInstructionsWe need to give clear task instructions and inform the agent how to execute it. This is equivalent to a process. You need to describe it clearly, otherwise the accuracy will be reduced.
.FromTemplatecan also use Template to describe task instructions
.WithNameThe name is required to make the call more clear.
.WithPluginis based on different skills and tool chains for the agent to complete tasks. This corresponds to the content of Semantic Kernel.
Let’s take a simple scenario and hope to build a .NET console application through an agent, compile and run it, and require it to be completed through an agent. From this scenario, we need two agents – the agent that generates the .NET CLI script and the agent that runs the .NET CLI script. In Semantic Kernel, we use different plugins to define the required planning, memory and tools. The following is the relevant structure diagram.
AI Agents are an important scenario for LLMs applications, and building agent applications will be an important technical field in 2024. We currently have three main forms of intelligence, such as single AI agent, multi- AI agents, and hybrid AI agent.
Single AI Agent
Work completed in specific task scenarios, such as the agent workspace under GitHub Copilot Chat, is an example of completing specific programming tasks based on user needs. Based on the capabilities of LLMs, a single agent can perform different actions based on tasks, such as requirements analysis, project reading, code generation, etc. It can also be used in smart homes and autonomous driving.
Multi-AI agents
This is the work of mutual interaction between AI agents. For example, the above-mentioned Semantic Kernel agent implementation is an example. The AI agent generated by the script interacts with your AI agent that executes the script. Multi-agent application scenarios are very helpful in highly collaborative work, such as software industry development, intelligent production, enterprise management, etc.
Hybrid AI Agent
This is human-computer interaction, making decisions in the same environment. For example, smart medical care, smart cities and other professional fields can use hybrid intelligence to complete complex professional work.
At present, the application of intelligent agents is still very preliminary. Many enterprises and individual developers are in the exploratory stage. Taking the first step is very critical. I hope you can try it more. I also hope that everyone can use Azure OpenAI Service to build more agent applications.
Recent Comments