Salesforce TDX 2026 highlights​ - I

-

 

After attending TDX 2026, one thing stood out clearly: this was not just another product update cycle, but a meaningful shift in how Salesforce is evolving.

The announcement that caught my attention most was Headless 360. It represents a major change in how we think about interacting with the Salesforce platform. Instead of being tied to the traditional browser-based experience, agents and developer tools can now work directly with the Salesforce ecosystem through APIs and modern interfaces. This creates new possibilities for deeper integrations, smarter automation, and more flexible composable architectures that extend well beyond the UI.

Here are a few highlights that stood out to me:

  • Salesforce Headless 360​
  • Agent Script going open source​
  • Agentforce Vibes 2.0​
  • Agent Exchange​
  • Salesforce Multi-Framework​
  • Agentforce Experience Layer (AXL)​
  • Agentforce Labs​
Agentforce Vibes 2.0– AI is moving closer to being context-aware from day one. Instead of a heavy setup, it starts understanding your org’s data and workflows early, which can speed up adoption.

https://www.salesforce.com/news/stories/salesforce-headless-360-announcement/

Agent Script (now open source + voice) – this was a big one. Salesforce opened up its agent definition language, which lets you define logic, sub-agents, actions, variables, guardrails, and transitions in a structured way. It gives developers much more control and transparency, especially as voice capabilities evolve.

https://salesforce.vidyard.com/watch/xDEXADFGPC4zs3GLjomec2

React hosting on Salesforce: Salesforce Multi-Framework is a new runtime that lets developers run React applications natively on the platform.

https://www.salesforce.com/agentforce/script/

AgentExchange – Just launched as a unified marketplace combining AppExchange, Slack Marketplace, and the Agentforce ecosystem into a single storefront. With 13,000+ listings already, it’s clear Salesforce is building a strong ecosystem around reusable AI components and integrations.

https://agentexchange.salesforce.com/new

Agentforce Experience Layer (AXL) – Build once and deploy across Slack, Teams, WhatsApp, ChatGPT, Claude, and more. This simplifies how we design and scale omnichannel experiences.

https://www.salesforce.com/platform/orchestration-platform/

Agentforce Labs + ADLC– Salesforce is also focusing on the full agent development lifecycle. Labs provides a faster way to experiment and prototype, while ADLC capabilities cover everything from authoring and validation to safety review, deployment, and observability.

https://labs.agentforce.com/

There’s honestly a lot to catch up on with these capabilities. This feels like a clear move toward an agent-driven, AI-first ecosystem where the UI is no longer the center of gravity.

Salesforce definitely keeps us on our toes 🙂 . It’s exciting, but it also pushes us to rethink how we design solutions, especially around integrations, automation, and how users (or agents) interact with systems.

Looking forward to diving deeper into these and seeing how they shape real-world implementations.

Here’s the link to the TDX 2026 main keynote

https://www.salesforce.com/plus/experience/tdx_2026/series/tdx_2026_highlights/episode/episode-s1e2

TDX 2026 Roundup : https://www.salesforce.com/blog/tdx-2026-roundup-agentforce-edition/

Comments

Post a Comment

Popular posts from this blog

Introduction to Salesforce Agent Script: Build Predictable AI Agents

-
Image
Please visit here for more details - https://ayaninsights.com/guestblogs/introduction-to-agent-script/ In my latest blog, I introduce Salesforce Agent Script and explain how it helps teams build AI agents that are more predictable, controlled, and aligned with business processes. Large language models are flexible, but relying only on natural-language instructions can sometimes produce inconsistent results. Agent Script addresses this challenge by combining the conversational capabilities of an LLM with structured business logic. The blog explains how developers can use conditions, variables, actions, topics, and transitions to control how an Agentforce agent behaves. Agent Script supports familiar logic such as if/else conditions, value comparisons, sequential actions, and checks for missing data. I also cover its core structure, including system settings, configuration, global variables, languages, connections, and topic blocks. The start_agent topic acts as the entry point for each...
Read more

Anti-Patterns in Salesforce Agentforce: What to Avoid When Building AI Agents

-
Image
Salesforce Agentforce is powerful because it allows teams to build AI agents that can understand user intent, retrieve grounded information, execute actions, and support business workflows across Salesforce. But like any powerful platform, the quality of the implementation matters. A good Agentforce implementation does not start with “How many things can the agent do?" It starts with “What problem should the agent solve reliably?” That is where anti-patterns come in. Anti-patterns are common implementation habits that look useful at first but eventually create confusion, poor user experience, inconsistent answers, or hard-to-maintain agents. Below are some of the most common Agentforce anti-patterns and how to avoid them. 1. Trying to Build One Agent That Does Everything One of the biggest mistakes is designing a single agent to handle every business process, every department, and every possible customer question. At first, this feels efficient. One agent, many use cases. Bu...
Read more

MCP vs. Traditional APIs: Choosing the Right Integration Approach

-
Image
Enterprise integration has traditionally been built around APIs. Applications send structured requests, services process them, and predictable responses are returned. This model has supported everything from payment processing and customer portals to mobile applications and large-scale system integrations. The rise of AI agents introduces a different integration challenge. An AI agent does not always follow a fixed sequence designed in advance. It may need to determine which system to use, discover the operations available to it, gather relevant context, and select the appropriate action based on a user’s request. This is where the Model Context Protocol, or MCP, becomes relevant. MCP and traditional APIs are related, but they solve different problems. APIs expose system capabilities. MCP provides a standardized way for AI applications to discover and use those capabilities as tools and contextual resources. Understanding this distinction is important when designing enterprise AI solut...
Read more