Another TrailblazerDX is in the books for the Lane Four team, and as always, the Salesforce ecosystem has a lot to talk about. From long-awaited updates to some we weren’t even expecting (but gladly welcome), this year’s conference brought announcements that will shape the way admins, consultants, and developers work with Salesforce tools—especially Agentforce (to no one’s surprise).
If you missed the event or just need a refresher, our team of architects and devs gathered the most meaningful takeaways from TDX 2025. Let’s get into it.
Source: Lane Four
Left to right: Mathieu Hubbard, Anthony Mottola, Amy Blackburn, Nupur Patel, Pete Gilbert
For Anyone Working with Agentforce…
Agentforce 2DX
Agentforce isn’t undergoing a full rebrand, but Agentforce 2DX signals that Salesforce isn’t done evolving its AI-powered assistant. While some of the announcement felt like a marketing refresh, a few key improvements hint at bigger things on the horizon. Here’s what Agentforce 2DX is expected to bring:
- Proactive engagement based on data changes. Think of it as an AI that doesn’t just react—it takes action when something significant happens.
- Autonomous operation within business processes. The long-term vision seems to be AI that handles workflows without needing constant human input.
- Multi-interface interactions with rich content and media. Agentforce could soon move beyond simple chat responses, incorporating more visual and interactive elements.
That said, don’t expect to see these features overnight. The timeline points to at least April 2025, and given how AI rollouts tend to go, we wouldn’t be surprised if some capabilities a bit longer to materialize or become fully reliable. For now, developers and admins shouldn’t expect any immediate workflow disruptions—though they might want to start thinking about how these new capabilities could fit into their long-term strategy.
Free Developer Edition for Agentforce
One of the biggest barriers to working with Agentforce has been the lack of a free, hands-on environment. Until now, sandboxes consumed production credits, discouraging experimentation and opportunities to learn. That changes with the new Agentforce Developer Edition, which makes it possible for admins and developers to explore features without worrying about extra consumption costs.
Variables Within Agents
Finally! This one’s for developers building Agentforce solutions and clients who need stricter response control. This long-overdue feature gives teams better control over how Agentforce handles prompts and responses. With variables, developers can fine-tune behaviours, making debugging easier and ensuring responses align with business needs.
Custom LWCs Inside Agentforce
For developers and clients who need custom UI elements in Agentforce, this update allows you to fully customize how Agentforce responses appear in Salesforce. While no official release date was given, the ability to embed Custom Lightning Web Components (LWCs) inside Agentforce will be a major advantage for teams that need tailored “visualizations” in addition to the conversational elements.
CLI for Agentforce
A Command Line Interface (CLI) for Agentforce is coming! Before this, deploying and managing AI-powered agents without CLI support has been cumbersome, especially for teams with strict deployment processes. Now, with CLI for Agentforce, teams can integrate it into CI/CD pipelines, automate deployments, and manage configurations more efficiently. While this update isn’t as flashy as some of the others, it removes a significant pain point for developers—one that should have been addressed in the initial release. For organizations that rely on structured deployment workflows, this will make Agentforce a much more viable and scalable solution.
Agentforce Test Tooling in VS Code
Testing Agentforce interactions inside VS Code sounds exciting, but in reality, this looks like a reskinned version of the existing testing center. For developers and QA teams, this will improve usability but won’t dramatically change how testing is done—at least not yet. Expect more meaningful updates when Salesforce introduces more advanced testing capabilities, like chaining multiple test cases, which could make AI model validation much more effective.
Interaction Explorer
One of the biggest challenges in early Agentforce projects was the lack of transparency into how AI interactions were happening. Debugging, optimizing, and refining Agentforce behavior was often a guessing game.
That’s why Interaction Explorer is one of the most exciting updates to our team. This tool will give teams deeper insights into Agentforce activity, making it easier to troubleshoot issues, track AI decision-making, and refine agent performance.
For developers, consultants, and admins, this solves a major visibility problem, providing insights that help ensure AI-driven processes align with business needs. The timeline for release (~Spring 2025) is ambitious, and given the current reporting challenges in Agentforce, there’s some skepticism about how well it will work at launch. But if it delivers? This could be a massive step forward for AI-powered operations inside Salesforce.
AgentExchange
Salesforce is introducing AgentExchange, a marketplace where users can share and discover Agentforce use cases, templates, and best practices. In theory, this could become a valuable resource for admins and ISVs looking to accelerate AI adoption.
The big question? Will the community embrace it? If AgentExchange gains traction, it could shorten development time, improve collaboration, and make Agentforce more accessible to a wider audience. But if adoption is low, it may end up as another underutilized Salesforce feature.
For now, admins and consultants should keep an eye on it—but we don’t expect it to replace hands-on experience anytime soon.
Modular Flow Design
One of the recurring themes at TDX 2025 was modularity in automation, particularly in Flow design. Miss the session? Check it out on Salesforce+! The emphasis is now on breaking down complex workflows into smaller, reusable subflows—a shift that will make Agentforce-driven processes cleaner, more efficient, and easier to manage.
For admins and consultants building flows, this reinforces Salesforce’s push for simplicity and scalability. The more modular the design, the more effective Agentforce can be in executing workflows without unnecessary complexity. This isn’t a revolutionary change, but it’s a best practice shift that will make long-term maintenance much easier.
Agents Can Read Business Rules Engines
A major update for Revenue Cloud users—Agentforce can now read Business Rules Engines (BRE), just as it does with flows. Since BRE houses pricing logic and validation rules, this means Agentforce can now analyze and apply pricing conditions dynamically.
For admins and consultants managing pricing structures, this reduces manual intervention and ensures AI-driven interactions align with existing pricing frameworks. This is a fairly big deal for teams that rely on BRE for complex pricing and validation logic—AI-powered pricing guidance is no longer just a concept, but a reality.
Agentforce Agent for Setup
Managing user permissions has always been one of the most tedious tasks for Salesforce admins. The new Agentforce-powered setup assistant is designed to automate permissions comparisons, troubleshoot access issues, and even suggest configurations.
For admins handling user management, this could save countless hours—especially when onboarding or troubleshooting why one user has different access than another. Future enhancements, like cloning users and object/field creation, could take this even further. This update brings AI-powered efficiency to one of the most frustrating parts of Salesforce administration—and that’s a big win.
Prompt Builder 2.0
Salesforce’s Prompt Builder 2.0 brings a redesigned UI and new functionality that makes it easier to develop, iterate, and manage prompts. One of the most significant improvements is the ability to compile prompts to resolutions without sending them to the LLM, which means no consumption credits are used during the initial testing and refinement phase. This drastically reduces the cost of prompt development, making AI-driven interactions more accessible.
For admins and consultants, the update provides greater flexibility in aligning prompt inputs with flow logic, removing previous limitations that required direct flow input bindings. This opens up new possibilities for customizing AI-driven processes without costly workarounds. For clients hesitant to experiment with AI due to cost concerns, this change could make Salesforce’s AI tools a far more attractive option.
Agentforce for Developers (A4D) Enhancements
Salesforce is bringing AI automation to LWC development with key updates to Agentforce for Developers (A4D), set to start rolling into GA between Summer 2025 and Winter 2026. One of the biggest improvements is A4D Aura Conversion (GA in Winter ’26), which will automatically analyze and convert Aura components into LWCs while preserving their original functionality. This will ease the transition away from Aura and help developers modernize applications with minimal manual work.
In addition, A4D Prompt LWC (GA in Winter ’26) introduces natural language-based LWC generation, allowing developers to describe components in plain text and have A4D generate the necessary code, including missing imports, methods, and functionality. To further streamline development, A4D Test Case Generation (GA in Summer 2025) will scan existing code and automatically create unit tests, significantly reducing the time spent on test coverage. These updates will enable developers to work faster, reduce errors, and focus more on innovation rather than repetitive coding tasks.
Headless Agents via Agentforce API
Agentforce is breaking free from traditional chat interfaces with headless agents, allowing AI to be embedded directly into workflows, applications, and backend processes. These agents handle real-time text-based prompts and responses without needing a visible UI—perfect for custom automation and scaling operations without disrupting user experiences.
The new Agentforce API makes integration straightforward: just create a Connected App and add it to the Service Agent Configuration. A Service Agent is required for setup, and these agents can be used as invocable actions in Apex and Flow, making automation even easier. For developers, admins, and consultants, this update removes friction from AI deployments, making it faster and more flexible to integrate smart automation into existing systems.
General Callouts For Salesforce Admins and Consultants...
While Agentforce stole the spotlight, there were a couple other takeaways that make everyday admin work smoother.
Improved User and Permission Management
Managing users and permissions in Salesforce has historically been a cumbersome process, but upcoming updates promise to simplify and enhance control over access management. Some of the biggest improvements include:
- Permission Set Summaries for better visibility into assigned permissions.
- Field History Tracking for Users, set to enter beta this summer and go GA in winter.
- More flexible permission set assignments, including the long-requested ability to set expiration dates on permissions.
For admins responsible for user management, these changes will make it significantly easier to track, audit, and adjust permissions without tedious manual work. While much of this is still forward-looking, the roadmap indicates that Salesforce is committed to improving the admin experience in a meaningful way.
Dark Mode (Yes, Really)
After more than a decade of requests, Salesforce is finally introducing Dark Mode with the Cosmos theme. The impact? Functionally minimal, but psychologically significant. While it doesn’t change how the platform works, it does provide a more comfortable viewing experience for users who spend long hours in Salesforce.
For admins, consultants, and developers, this may not be a workflow-altering update, but for those accustomed to staring at bright screens well past midnight, we’re celebrating with you. Sometimes, it’s the little things that make the biggest difference.
Source: Lane Four
Left to right: Anthony Mottola, Mathieu Hubbard, Pete Gilbert, Amy Blackburn, Nupur Patel
For Data Specialists...
Tableau Next
Salesforce is retiring CRMA (formerly Einstein Analytics) and replacing it with Tableau Next, a BI platform built on Hyperforce and Data Cloud architecture. Unlike its predecessor, Tableau Next is designed to be natively integrated with Agentforce, allowing businesses to take direct action from within their data analysis workflows. It also supports the same connectors as Data Cloud, including Zero Copy, ensuring seamless data movement without unnecessary duplication.
For BI teams, admins, and consultants who have relied on CRMA, this will require an adjustment period, as the tools and workflows will differ significantly despite some compatibility. For clients still using CRMA, this update signals that migration planning should begin sooner rather than later—though Salesforce has yet to announce an official sunset timeline.
Search and Retrievers
Salesforce is enhancing its retriever search capabilities, allowing for more precise, customizable, and context-aware data queries. Updates include:
- Enhanced filtering on retrievers
- Pre filter-retrievers (currently available)
- Ranking Factors; recency, relevancy and popularity (coming soon)
- Search across multiple retrievers, expanding search scope across various data sources
- Ability to combine and join DLOs, making cross-source searches more powerful
For consultants and developers working with Data Cloud, these improvements mean greater precision in how data is queried and surfaced—a critical need for organizations with strict data governance policies. For clients with highly specific audience segmentation needs, these changes unlock new possibilities for refining search parameters where previous limitations existed.
And last, but most definitely not least (since this conference was all about these individuals)…
A Few More Takeaways For Salesforce Developers
Formula Evaluation in Apex
Salesforce is introducing Formula Evaluation in Apex, allowing developers to store formulas in Custom Metadata Types and evaluate them dynamically in Apex. This means business logic can be modified without requiring a developer to update or deploy new code—an especially useful enhancement for business-critical automations that need frequent adjustments.
For admins and developers, this brings more flexibility and responsiveness to workflows. Instead of hardcoding conditions in Apex, teams can update logic on the fly, ensuring that automations adapt to evolving business requirements without waiting on development cycles.
Javadoc-Style Code Documentation in Apex
While developers have always been able to document Apex code with comments, Salesforce is now adding official support for Javadoc-style annotations, along with linting validation and auto-generation tools in VS Code. This change helps Agentforce for Developers by making it easier to understand method functionality at a glance, without digging through code.
Most modern IDEs will display these docs when hovering over methods, offering context on parameters, expected outputs, and usage recommendations. While self-documenting code should always be the goal, this feature improves code maintainability—especially for teams working on large-scale, collaborative projects.
Apex Cursors
Currently, using OFFSET in SOQL queries limits developers to retrieving only the first 2,000 records—making it difficult to work with large datasets efficiently. Apex Cursors, now in beta, change that by allowing processing of up to 50 million records per cursor.
For developers working with massive data operations, this is a huge performance boost. Cursors are also serializable, meaning they can be passed to Queueable classes—allowing for chained processing of large datasets without hitting governor limits. This update is essential for high-volume automation and reporting use cases.
Delegated Polling for Async Actions
Salesforce didn’t announce this one directly, but a TDX session that our team attended highlighted a powerful design pattern for delegating polling while waiting for deployments to complete. In traditional CI/CD workflows (e.g., GitHub Actions, Bitbucket Pipelines), the system continuously polls for deployment status—often wasting valuable compute time while waiting for tests to finish.
With delegated polling, CI/CD pipelines can offload the polling task and receive a notification once the deployment is complete, significantly reducing unnecessary resource consumption. This is especially valuable for teams working under monthly execution time limits on CI/CD platforms. Developers looking to implement this approach can reference the example implementation here.
For teams focused on deployment efficiency, this pattern saves time, reduces costs, and optimizes CI/CD workflows, making Salesforce deployments far less resource-intensive.
TrailblazerDX 2025 delivered a mix of long-awaited improvements, promising new features, and a few announcements that left us wondering, “Will this really work as advertised?” Now, we wait to see how these changes roll out. If Salesforce sticks to its roadmap, 2025 is shaping up to be a pivotal year for the ecosystem. Want to experience the possibilities with trusted guidance? Let’s chat.
Let's chat!
