#Agentforce315 discussing

Hi @Souvik Dutta Looking at the error, it seems to be a VS Code extension compatibility issue rather than a Salesforce configuration issue.

I would suggest trying these steps:

1. Check Extensions: Verify that Agentforce Vibes and Salesforce extensions are compatible.
2. Update CLI: Run sf update and restart VS Code.
3. Check Apex REST: Make sure the REST class and HTTP methods are properly defined.
4. Extension Logs: Check VS Code → Output for detailed errors.
5. Test New Project: Try generating the OpenAPI document with a simple Apex REST class.
6. Reinstall Extensions: If needed, reinstall compatible Salesforce extension versions.

The error showCommandWithTimestamp is not a function looks like an internal extension issue, so I would focus on extension versions first.

If it still fails, I suggest reporting it on GitHub with the error logs and extension versions.

Hi @Galla Rajeswari Yes, I believe LWC will remain important even in the AI era.

A few reasons:

1. Custom UI: Companies still need custom components based on business requirements.
2. User Experience: LWC helps build interactive and user-friendly screens.
3. Agentforce: LWC can be used to build custom interfaces for AI-powered solutions.
4. Complex Requirements: Not everything can be achieved using standard Salesforce features.
5. AI-Generated Code: AI can write code, but developers still need to review, debug, and optimize it.
6. Security & Performance: Developers must ensure components are secure and work efficiently.

In my view, AI will reduce repetitive coding, but it won't replace strong development skills.

LWC + Apex + Agentforce + AI skills will be a valuable combination for Salesforce developers in the coming years.

Hi @Galla Rajeswari Deploying Agentforce to production can be tricky, especially when multiple subagents and actions are involved.

I would check these key points:

1. Dependencies: Make sure all Flows, Apex classes, and Prompt Templates are deployed.
2. Subagents & Actions: Verify all subagents and actions are properly configured.
3. Permissions: Check the agent running user's access, object permissions, and field access.
4. Agent Version: Confirm the correct version is active.
5. External Connections: Verify APIs, Named Credentials, and authentication.
6. Data Differences: Production data may affect agent responses differently.
7. Testing: Check subagent routing, action execution, and response accuracy.
8. Deployment Errors: Watch for missing components and activation issues.

I would recommend testing with a small group of users before making the agent available to everyone.

Key Point: A successful deployment doesn't mean the agent is ready. Proper testing and monitoring are equally important.

Hi @Galla Rajeswari An agent working fine in a sandbox doesn't mean it will work the same way in production.

I would focus on these key points:

1. Agent Activation: Make sure the correct agent version is active.
2. Permissions: Check running user access, field permissions, and sharing rules.
3. Subagent Routing: Verify the agent selects the right subagent.
4. Actions: Test Apex, Flow, and API actions with real scenarios.
5. Response Accuracy: Compare agent responses with actual Salesforce data.
6. Negative Testing: Test invalid inputs, missing data, and unexpected questions.
7. Security: Make sure the agent doesn't expose sensitive data.
8. Monitoring: Review session traces, errors, timeouts, and failed actions.

I would also recommend starting with a small group of users and collecting feedback before a full rollout.

Key Point: Deployment is not the final step. Regular testing and monitoring are important to keep the agent reliable.

Hi @Galla Rajeswari Agentforce is powerful, but there are some challenges we need to consider in real projects.

1. Response Time: Complex requests can take longer to process.
2. Action Timeouts: Apex, Flow, or API actions may fail if they exceed time limits.
3. Subagent Selection: Sometimes the agent may choose the wrong subagent.
4. Response Accuracy: Even with correct data, the agent may give incorrect or incomplete answers.
5. Data Access: Permissions and sharing settings can affect agent responses.
6. Testing: Testing different user questions and scenarios is not always easy.
7. Cost: Usage costs can increase with frequent agent interactions.

In my view, clear instructions, proper testing, and monitoring are very important before production deployment.

Agentforce is useful, but we should not depend on AI alone for critical business decisions.

Hi @Galla Rajeswari I feel Agent Script is a useful addition to the New Agentforce Builder, especially for complex business requirements.

A few key advantages:

1. Better Control: Define clear business rules and conditions.
2. Consistent Results: Helps agents follow the expected steps.
3. Action Execution: Control when actions should run.
4. Subagent Routing: Manage how agents move between subagents.
5. Less AI Guesswork: Reduces unexpected agent behaviour.
6. Easy Debugging: Makes it easier to understand and fix logic issues.

I believe Agent Script will become an important skill for Salesforce developers, along with Apex, Flow, and LWC.

My View: Canvas is good for visual design, while Agent Script gives developers more control over agent behaviour.

Hi @Galla Rajeswari Good question! Data 360 is not just about combining data. It helps businesses use customer data more effectively.

1. Identity Resolution: Combines customer records to create a unified customer profile.
2. Data Graphs: Connect related data and help Agentforce access customer information faster.
3. Segmentation: Helps businesses identify and target the right customers.
4. Real-Time Activation: Helps businesses take action using updated customer data.
5. Agentforce: Provides better customer context, helping agents give more relevant and accurate responses.

In my view, Identity Resolution and Data Graphs are especially useful for Agentforce.

Key Point: Data 360 provides the right customer context, while Agentforce uses that data to answer questions and perform actions.

Hi @Vivek Dayafule Looks like you've completed most of the setup. I suggest checking a few things:

1. Email Difference: Different Slack and Salesforce emails are usually fine, but verify the user mapping and authorization.
2. Agent Activation: Make sure your Agentforce agent is active and connected to Slack.
3. Slack Approval: Check whether the agent is approved and available in your Slack workspace.
4. Permissions: Verify that the user has the required Agentforce and Slack permissions.
5. Trailhead Org: Confirm you're using the same Salesforce org for the challenge.

If everything looks correct, try reconnecting the agent.

Could you share the exact error message or where you're getting stuck? That will help identify the issue.

Great update, @Akshata Sawant Thanks for sharing.

HXL looks like a useful step forward for building interactive AI experiences.

The biggest advantage is building one reusable UI widget instead of creating separate versions for different platforms.

Really interesting to see how the same JSON-based widget can work across Agentforce, ChatGPT, Claude, and Slack.

Looking forward to exploring the Playground and trying some real-world use cases!