Salesforce bets on conversation as the new interface for developers

Salesforce Inc. wants to make conversation the interface for developers, bringing agents to the foreground with a “headless” version of its platform designed to let humans and artificial intelligence build from nearly anywhere. 

The new capacity, dubbed Headless 360, will usher in a new paradigm for the company. 

Every capability in Salesforce’s platform is accessible via application programming interfaces, Model Context Protocol tools for connecting models to data and tools, or the command line. That means humans and artificial intelligence models alike can build on them and compose apps across platforms with far fewer constraints. 

According to the company, this opens a whole new horizon. It also means developers can bring their favorite coding agents from any vendor to the party, including Claude Code, Cursor, Codex and Windsurf. 

AI also opens up the possibility of prompting ideas and generating code from within chat interfaces such as Slack, mobile, ChatGPT, Claude, Gemini, Teams or any client that supports MCP. 

Bringing agents to life with Agentforce 

To support those possibilities, Salesforce introduced a new way to build agents with Agentforce Vibe 2.0, an artificial intelligence builder that brings agent development natively into the Salesforce platform with multimodel support, including Claude Sonnet and GPT-5. It also provides a development partner that understands business logic, not just code. 

On top of that, developers will gain full control over the user interface, including native React support, a popular open-source JavaScript library designed for building user interfaces. That will allow them to create fully custom experiences from scratch that are fast, interactive and lively. 

The company said one enterprise customer saw Agentforce adoption jump from 22% to 78% in six weeks. The agent did not change; the experience did. 

In addition to evolving Vibe, Salesforce is also launching Testing Center, which is designed to reveal logic gaps, policy violations and inconsistent outputs before they reach users. With Custom Scoring Evals, developers can measure how something performed, not simply whether it ran or failed. They can set a series of standards and evaluate how well those standards were met, rather than relying only on pass-fail criteria. 

After launch, Observability and Session Tracing will make it possible to see not only what happened in production, but why. When an agent drifts off-task, Salesforce said it will help teams get to the root cause in hours rather than weeks. A/B testing is also rolling out, allowing multiple agent versions to run against real traffic at the same time for more data-driven testing and decision-making. 

Agent Fabric expands to scale multivendor AI faster 

In addition to the company’s agentic AI announcements, Salesforce also announced a major expansion to Agent Fabric, the company’s trusted agent control plane for companies building multivendor agentic networks. 

Agent Fabric now brings automated discovery, agent authoring and centralized large language model governance for orchestration. That allows handoffs, model selection and decision-making to happen within enterprise boundaries, with cost and risk optimized without sacrificing speed or quality. 

Salesforce said the new paradigm for controlling multivendor agent workforces often comes down to having a single “lead” agent that orchestrates the broader labor force. In practice, that can mean a central model overseeing handoffs, coordinating smaller models for reliability and speed, managing costs and token limits, and identifying optimized routes. 

The company said that since its launch in September 2025, Agent Fabric has coordinated thousands of agentic instances for customers. Those have included some of the world’s largest enterprises, including Capita plc, as well as specialized industry providers such as Alcon Inc. and Diabsolut Inc. 

 Image: SiliconANGLE/Microsoft Designer