home.social

#agent-builder โ€” Public Fediverse posts

Live and recent posts from across the Fediverse tagged #agent-builder, aggregated by home.social.

fetched live
  1. ๐ŸŸฆ Copilot Studio: Clone agents in minutes

    Clone Copilot agents into VS Code to edit, version, and redeploy them like regular code. Move from portal-only edits to local workflows for faster iteration and collaboration. Teams can use Git, CI/CD, and AI-assisted edits to accelerate development.

    ๐Ÿ’ก Speed: clone & open in VS Code in under a minute ๐Ÿš€
    ๐Ÿ” Local edits: YAML + IntelliSense, git-friendly
    โš–๏ธ Governance: audit-ready workflows and reattach to Copilot Studio

    โ–ถ๏ธŽ hubsite365.com/en-ww/citizen-d

    #MICROSOFTCOPILOT #COPILOTSTUDIO #AGENTBUILDER #LOWCODE

  2. ๐ŸŸฆ Copilot Studio: Clone agents in minutes

    Clone Copilot agents into VS Code to edit, version, and redeploy them like regular code. Move from portal-only edits to local workflows for faster iteration and collaboration. Teams can use Git, CI/CD, and AI-assisted edits to accelerate development.

    ๐Ÿ’ก Speed: clone & open in VS Code in under a minute ๐Ÿš€
    ๐Ÿ” Local edits: YAML + IntelliSense, git-friendly
    โš–๏ธ Governance: audit-ready workflows and reattach to Copilot Studio

    โ–ถ๏ธŽ hubsite365.com/en-ww/citizen-d

  3. ๐Ÿง  #AgentBuilder di #OpenAI: รจ un buon sistema? Sรฌ, ma attenzione allo SPRECO DI TOKEN (enorme)! 
    ๐Ÿ‘‰ Test e riflessioni: linkedin.com/posts/alessiopoma

    ___ 
    โœ‰๏ธ ๐—ฆ๐—ฒ ๐˜ƒ๐˜‚๐—ผ๐—ถ ๐—ฟ๐—ถ๐—บ๐—ฎ๐—ป๐—ฒ๐—ฟ๐—ฒ ๐—ฎ๐—ด๐—ด๐—ถ๐—ผ๐—ฟ๐—ป๐—ฎ๐˜๐—ผ/๐—ฎ ๐˜€๐˜‚ ๐—พ๐˜‚๐—ฒ๐˜€๐˜๐—ฒ ๐˜๐—ฒ๐—บ๐—ฎ๐˜๐—ถ๐—ฐ๐—ต๐—ฒ, ๐—ถ๐˜€๐—ฐ๐—ฟ๐—ถ๐˜ƒ๐—ถ๐˜๐—ถ ๐—ฎ๐—น๐—น๐—ฎ ๐—บ๐—ถ๐—ฎ ๐—ป๐—ฒ๐˜„๐˜€๐—น๐—ฒ๐˜๐˜๐—ฒ๐—ฟ: bit.ly/newsletter-alessiopomaro 

    #AI #GenAI #GenerativeAI #IntelligenzaArtificiale #LLM 

  4. ๐Ÿง  #AgentBuilder di #OpenAI: รจ un buon sistema? Sรฌ, ma attenzione allo SPRECO DI TOKEN (enorme)! 
    ๐Ÿ‘‰ Test e riflessioni: linkedin.com/posts/alessiopoma

    ___ 
    โœ‰๏ธ ๐—ฆ๐—ฒ ๐˜ƒ๐˜‚๐—ผ๐—ถ ๐—ฟ๐—ถ๐—บ๐—ฎ๐—ป๐—ฒ๐—ฟ๐—ฒ ๐—ฎ๐—ด๐—ด๐—ถ๐—ผ๐—ฟ๐—ป๐—ฎ๐˜๐—ผ/๐—ฎ ๐˜€๐˜‚ ๐—พ๐˜‚๐—ฒ๐˜€๐˜๐—ฒ ๐˜๐—ฒ๐—บ๐—ฎ๐˜๐—ถ๐—ฐ๐—ต๐—ฒ, ๐—ถ๐˜€๐—ฐ๐—ฟ๐—ถ๐˜ƒ๐—ถ๐˜๐—ถ ๐—ฎ๐—น๐—น๐—ฎ ๐—บ๐—ถ๐—ฎ ๐—ป๐—ฒ๐˜„๐˜€๐—น๐—ฒ๐˜๐˜๐—ฒ๐—ฟ: bit.ly/newsletter-alessiopomaro 

    #AI #GenAI #GenerativeAI #IntelligenzaArtificiale #LLM 

  5. Google Cloud just widened its Agent Builder, now offering features that rival OpenAIโ€™s Agent Development Kit. The move brings deeper AI orchestration to the openโ€‘source community, challenging AWS Bedrock and pushing the limits of AgentKit. Curious how this shifts the landscape? Dive into the details. #GoogleCloud #AgentBuilder #OpenAI #AgentKit

    ๐Ÿ”— aidailypost.com/news/google-cl

  6. Google Cloud just widened its Agent Builder, now offering features that rival OpenAIโ€™s Agent Development Kit. The move brings deeper AI orchestration to the openโ€‘source community, challenging AWS Bedrock and pushing the limits of AgentKit. Curious how this shifts the landscape? Dive into the details. #GoogleCloud #AgentBuilder #OpenAI #AgentKit

    ๐Ÿ”— aidailypost.com/news/google-cl

  7. ๐Ÿง  No, #AgentBuilder e #n8n non sono lo stesso sistema. Facciamo chiarezza. E ci sono diversi motivi per cui non uso questi strumenti (finti) no-code. 
    ๐Ÿ‘‰ L'approfondimento: linkedin.com/posts/alessiopoma

    ___ 
    โœ‰๏ธ ๐—ฆ๐—ฒ ๐˜ƒ๐˜‚๐—ผ๐—ถ ๐—ฟ๐—ถ๐—บ๐—ฎ๐—ป๐—ฒ๐—ฟ๐—ฒ ๐—ฎ๐—ด๐—ด๐—ถ๐—ผ๐—ฟ๐—ป๐—ฎ๐˜๐—ผ/๐—ฎ ๐˜€๐˜‚ ๐—พ๐˜‚๐—ฒ๐˜€๐˜๐—ฒ ๐˜๐—ฒ๐—บ๐—ฎ๐˜๐—ถ๐—ฐ๐—ต๐—ฒ, ๐—ถ๐˜€๐—ฐ๐—ฟ๐—ถ๐˜ƒ๐—ถ๐˜๐—ถ ๐—ฎ๐—น๐—น๐—ฎ ๐—บ๐—ถ๐—ฎ ๐—ป๐—ฒ๐˜„๐˜€๐—น๐—ฒ๐˜๐˜๐—ฒ๐—ฟ: bit.ly/newsletter-alessiopomaro 

    #AI #GenAI #GenerativeAI #IntelligenzaArtificiale #LLM

  8. ๐Ÿง  No, #AgentBuilder e #n8n non sono lo stesso sistema. Facciamo chiarezza. E ci sono diversi motivi per cui non uso questi strumenti (finti) no-code. 
    ๐Ÿ‘‰ L'approfondimento: linkedin.com/posts/alessiopoma

    ___ 
    โœ‰๏ธ ๐—ฆ๐—ฒ ๐˜ƒ๐˜‚๐—ผ๐—ถ ๐—ฟ๐—ถ๐—บ๐—ฎ๐—ป๐—ฒ๐—ฟ๐—ฒ ๐—ฎ๐—ด๐—ด๐—ถ๐—ผ๐—ฟ๐—ป๐—ฎ๐˜๐—ผ/๐—ฎ ๐˜€๐˜‚ ๐—พ๐˜‚๐—ฒ๐˜€๐˜๐—ฒ ๐˜๐—ฒ๐—บ๐—ฎ๐˜๐—ถ๐—ฐ๐—ต๐—ฒ, ๐—ถ๐˜€๐—ฐ๐—ฟ๐—ถ๐˜ƒ๐—ถ๐˜๐—ถ ๐—ฎ๐—น๐—น๐—ฎ ๐—บ๐—ถ๐—ฎ ๐—ป๐—ฒ๐˜„๐˜€๐—น๐—ฒ๐˜๐˜๐—ฒ๐—ฟ: bit.ly/newsletter-alessiopomaro 

    #AI #GenAI #GenerativeAI #IntelligenzaArtificiale #LLM

  9. ๐Ÿง  Un semplice test per provare l'integrazione di #ChartKit in #AgentBuilder di #OpenAI.
    ๐Ÿ‘‰ I dettagli: linkedin.com/posts/alessiopoma

    ___  
    โœ‰๏ธ ๐—ฆ๐—ฒ ๐˜ƒ๐˜‚๐—ผ๐—ถ ๐—ฟ๐—ถ๐—บ๐—ฎ๐—ป๐—ฒ๐—ฟ๐—ฒ ๐—ฎ๐—ด๐—ด๐—ถ๐—ผ๐—ฟ๐—ป๐—ฎ๐˜๐—ผ/๐—ฎ ๐˜€๐˜‚ ๐—พ๐˜‚๐—ฒ๐˜€๐˜๐—ฒ ๐˜๐—ฒ๐—บ๐—ฎ๐˜๐—ถ๐—ฐ๐—ต๐—ฒ, ๐—ถ๐˜€๐—ฐ๐—ฟ๐—ถ๐˜ƒ๐—ถ๐˜๐—ถ ๐—ฎ๐—น๐—น๐—ฎ ๐—บ๐—ถ๐—ฎ ๐—ป๐—ฒ๐˜„๐˜€๐—น๐—ฒ๐˜๐˜๐—ฒ๐—ฟ: bit.ly/newsletter-alessiopomaro

    #AI #GenAI #GenerativeAI #IntelligenzaArtificiale #LLM

  10. ๐Ÿง  Un semplice test per provare l'integrazione di #ChartKit in #AgentBuilder di #OpenAI.
    ๐Ÿ‘‰ I dettagli: linkedin.com/posts/alessiopoma

    ___  
    โœ‰๏ธ ๐—ฆ๐—ฒ ๐˜ƒ๐˜‚๐—ผ๐—ถ ๐—ฟ๐—ถ๐—บ๐—ฎ๐—ป๐—ฒ๐—ฟ๐—ฒ ๐—ฎ๐—ด๐—ด๐—ถ๐—ผ๐—ฟ๐—ป๐—ฎ๐˜๐—ผ/๐—ฎ ๐˜€๐˜‚ ๐—พ๐˜‚๐—ฒ๐˜€๐˜๐—ฒ ๐˜๐—ฒ๐—บ๐—ฎ๐˜๐—ถ๐—ฐ๐—ต๐—ฒ, ๐—ถ๐˜€๐—ฐ๐—ฟ๐—ถ๐˜ƒ๐—ถ๐˜๐—ถ ๐—ฎ๐—น๐—น๐—ฎ ๐—บ๐—ถ๐—ฎ ๐—ป๐—ฒ๐˜„๐˜€๐—น๐—ฒ๐˜๐˜๐—ฒ๐—ฟ: bit.ly/newsletter-alessiopomaro

    #AI #GenAI #GenerativeAI #IntelligenzaArtificiale #LLM

  11. OpenAI Agent Builder: ์ฝ”๋”ฉ ์—†์ด 5๋ถ„ ๋งŒ์— AI ์—์ด์ „ํŠธ ๋งŒ๋“ค๊ธฐ

    OpenAI Agent Builder๋กœ ์ฝ”๋”ฉ ์—†์ด ๋“œ๋ž˜๊ทธ์•ค๋“œ๋กญ๋งŒ์œผ๋กœ AI ์—์ด์ „ํŠธ ์›Œํฌํ”Œ๋กœ์šฐ๋ฅผ ๊ตฌ์ถ•ํ•˜๊ณ  ๋ฐฐํฌํ•˜๋Š” ๋ฐฉ๋ฒ•. MCP ํ†ตํ•ฉ, ChatKit ์ž„๋ฒ ๋”ฉ, ๋ณด์•ˆ ์ œ์•ฝ ์„ค์ •๊นŒ์ง€ ์‹ค๋ฌด ํ™œ์šฉ ๊ฐ€์ด๋“œ.

    aisparkup.com/posts/5400

  12. #OpenAI launched #AgentKit, a #toolkit for building and deploying #AIagents, at its Dev Day event. AgentKit includes #AgentBuilder for designing agent logic, #ChatKit for embedding chat interfaces, #Evals for measuring #agentperformance, and access to OpenAIโ€™s connector registry. techcrunch.com/2025/10/06/open #tech #media #news

  13. #OpenAI launched #AgentKit, a #toolkit for building and deploying #AIagents, at its Dev Day event. AgentKit includes #AgentBuilder for designing agent logic, #ChatKit for embedding chat interfaces, #Evals for measuring #agentperformance, and access to OpenAIโ€™s connector registry. techcrunch.com/2025/10/06/open #tech #media #news

  14. Agent Builder vise ร  permettre aux utilisateurs de crรฉer facilement des workflows agents visuels comparables ร  Zapier ou n8n, mais intรฉgrรฉs ร  lโ€™รฉcosystรจme OpenAI. testingcatalog.com/openai-prep #openai #chatGPT #agent #agentbuilder

  15. How To Build Custom Flow Actions For Agentforce โ€“ Planning Phase

    Salesforce Agentforce is a framework that enhances customer service and sales by integrating Salesforceโ€™s powerful capabilities with AI agents. Agentforce accelerates workflows, enhances KPIs and saves manual labor.

    The user messaging interface you build on the Agentforce platform leverages Artificial Intelligence Natural Language Processing to process customer requests. Agent builders do not need to define every fine branch in the conversation like designing an Interactive Voice Response (IVR) tree; instead, the Atlas reasoning engine handles these variations by evaluating customer requests (utterances) and matching them to topics. Once a topic is matched, Agentforce triggers the relevant actions, executes the predefined instructions, and completes the transaction for the customer.

    In short, Agentforce is a superpowered chatbot that can understand customer utterances that are not necessarily well defined, and completes transactions for the user. Voice interface for Agentforce is scheduled to come in the coming releases.

    Agentforce Deployment and Distribution

    There are two ways you can deploy Agentforce in Salesforce:

    1. Internal: Agentforce Assistant provides a conversational interface that enables internal users to efficiently complete transactions.
    2. External: Agentforce can be placed on a digital experience (community) site or on your companyโ€™s own website to complete transactions for your customers or prospects.

    You can also use Agentforce for both internal and external purposes.

    Agentforce Topics

    Agentforce topics are predefined or custom conversational subjects within Salesforce Agentforce that enable the platform to understand and categorize customer requests (utterances). These topics serve as the foundation for processing conversations by identifying the intent behind a customerโ€™s input and determining the appropriate actions to address it. Topics can be tailored to specific business needs, allowing organizations to design interactions that align with their workflows and objectives. For example, topics might include updating account details, creating support cases, or processing orders. By leveraging AI and natural language processing, Agentforce responsively matches utterances to the most relevant topic, ensuring accurate and efficient transaction handling.

    Agentforce comes with a few out of the box topics, and also a few โ€“ around 30 at the time of this post โ€“ standard actions you can choose from. The advantage of using out of the box topics and actions is that it is faster to implement. On the other hand, out of the box topics and actions are not tailored to your needs, therefore yielding potentially unpredictable results. Now, letโ€™s explore actions. Remember that you can always build custom topics and actions tailored to your needs.

    Agentforce Actions

    Salesforce Agentforce offers two primary types of actions to enhance its AI agentsโ€™ capabilities:

    1. Standard Actions: Pre-configured tasks that automate common functions within Salesforce.
    2. Custom Actions: Tailored tasks created to meet specific business needs, which can be implemented using:
      • Flow Actions: Utilize Salesforce Flows to automate processes and guide user interactions.
      • Apex Actions: Employ Apex code for complex logic and integrations.
      • Prompt Template Actions: Generate dynamic responses or trigger specific actions based on user input.
      • Service Catalog Item (Beta):  These Service Catalog actions resolve common contact reasons such as update phone number, update email address and open a support case using the conversational interface.

    While standard actions can help you to identify a record by name, query or summarize a record, you will need a flow or Apex action to complete a transaction. I wonโ€™t go into the benefits of low code in this article, but let me just say that the flow tool is more accessible for most as a solution in this case.

    How Do You Build Topics and Actions in Agent Builder?

    Salesforce already comes with an Agent built in. I am assuming you will want to add topics and actions to this Agent to handle your unique requirements. You can also build another agent in addition to the one that comes in your Salesforce Org.

    Before you jump into building in the agent builder, let me tell you that this process requires several pieces to be delicately stitched together. The building process reminds me very much of the orchestration building process with the obvious difference of agents requiring much more written instructions than orchestrations.

    Therefore it is a very good idea to do some planning before building.

    There are two main areas driving your design process:

    1. Conversation design: You need to think through and consider how the messaging interaction will go down. This will determine how you will structure your topics and actions.
    2. Automation design: This item goes hand-in-hand with the first item. Once you envision how the interaction will happen, you define topics to address the utterances, and associate the actions you build for the topic.

    ๐Ÿšจ Use case ๐Ÿ‘‡๐Ÿผ

    When the user asks Agentforce for a list of course cohort participants, the participant list will be displayed. There are courses (parent) and cohort (child) objects in the system, and contacts are enrolled in cohorts with a junction object.

    I can easily build a single flow to do this. The flow will need the course as an input, and an earliest start date. The flow will fetch the cohort best matching the requirements and display the associated participant contact information to the user.

    Conversation Design

    Here is a conversation pattern that we can expect:
    1. User: Give me a list of participants for the course starting right after 02/01/2025
    2. Agentforce: Here is the list: 1. John Doe 2. Penny White 3. Rick Smith

    The problem with this approach is that it is a closed box. A real life interaction rarely looks like this. If you build a flow automating the box on the right, you wonโ€™t be able to handle the variety of potential requests that will come from the user. Letโ€™s iterate and improve this map. How about this?
    1. User: Give me a list of participants for the course starting right after 02/01/2025
    2. Agentforce: Here is the cohort I found, is this the one? Code: C-0123 Starting Date: 02/07/2025
    3. User: Yes
    4. Agentforce: Here is the list: 1. John Doe 2. Penny White 3. Rick Smith

    The topics and custom actions needed for this design are completely different.

    I can and I should further expand on the possibilities here. What happens if there are multiple cohorts starting closely after the earliest start date? What happens if the user says no? You see the picture here, donโ€™t you?

    Iโ€™ll explore the intricacies of building my Agentforce custom flow actions in a future post. The topic of Automation Design is significant and deserves its own detailed discussion.

    Conclusion

    Preparation and conversation design are key when building agents for Salesforce Agentforce. The builder does not perfectly lend itself to easy modifications. When you build a custom flow action, and need to modify it later, you can save and activate a new version of your flow, but the custom action does not see these modifications. There is no refresh functionality for the custom action to fetch the latest version with new inputs and outputs.

    Planning your Agentforce solution will save you time when iterating and building it. Design and implementation precision will yield accurate and secure outcomes.

    Explore related content:

    Salesforce is Offering FREE AI Certification

    How to Pass the Salesforce AI Specialist Exam

    Introducing: Agentforce

    Agentforce Hackathon TDX25: My Hackathon Tips

    #Admins #AgentBuilder #Agentforce #AI #Apex #Automation #Developers #LowCode #Salesforce