“Why should you ever log into Salesforce again?” Salesforce Co-Founder Parker Harris asked that question out loud last month. Not as a provocation. As direction.

For 25 years, using Salesforce meant working inside Salesforce. A customer service rep opened a console, clicked into a case, and manually updated its status. A human, navigating a platform, to get work done. But in the Agentic Enterprise, humans aren’t the only ones doing the navigating. Agents are too, and they don’t go to a browser or click through UIs. They call APIs, invoke MCP tools, and run CLI commands directly. So two and a half years ago, we made a decision: Rebuild Salesforce for agents. Instead of burying capabilities behind a UI, expose them so the entire platform will be programmable and accessible from anywhere. If your platform requires humans to click through UIs or write code directly to make progress, it is not ready for the Agentic Enterprise. 

The result, which we’re introducing today, is Salesforce Headless 360: the capabilities your agents need most, exposed as an API, MCP tool, or CLI command so humans and agents can build, act, and deliver experiences on any surface. This extends across the full breadth of what Salesforce has built, from the processes that resolve customer support cases to the workflows that help sales teams close deals.

Salesforce Headless 360 delivers three new innovations: 

• New MCP tools and coding skills that give your coding agent full access to your platform 
• A new experience layer that renders rich, native interactions across every surface, from Slack to Voice to WhatsApp 
• New tools that give you control over how agents behave in production, before launch and after

Salesforce is the platform that powers how humans and agents work together, whether using Customer 360 apps, Slack, Headless 360, or other surfaces. Agents now orchestrate your apps, your workflows, your business logic, and they inherit all of it without having to rebuild any of it. Both humans and agents need the same thing: the data, the workflows, the trust layer. The surface changes. The platform doesn’t.

“With Agentforce, we’ve been able to deploy sophisticated, production-ready AI agents in just 12 days, driving millions in savings while significantly increasing our technical velocity. This unified platform proves that we can scale our most complex service needs without adding operational complexity.” — Elia Wallen, CEO, Engine

Build any way you want

For developers, headless means you can build on Salesforce any way you want. More than 60 new MCP tools and 30+ preconfigured coding skills give your coding agent complete, live access to your entire platform, including all of your data, workflows, and business logic, directly in the coding agents you already use like Claude Code, Cursor, Codex, Windsurf, and more.

Agentforce Vibes 2.0 brings that same power natively inside Salesforce, adding full org awareness from the start, multi-model support including Claude Sonnet and GPT-5, and an AI development partner that understands your business, not just your code.

“As a dev team lead, I’ve seen firsthand how Agentforce Vibes is supporting our Salesforce development. It’s been especially valuable for speeding up day-to-day tasks like metadata updates and quick tweaks, reducing manual work and boosting efficiency. We primarily use it for repetitive, time-consuming work, from config analysis and metadata adjustments to generating boilerplate code, tests, and handling small refactors or pre-deployment checks. Vibes acts as a strong assistant that streamlines our workflows, and we’re excited to see how it evolves and drives even greater impact over time.” — Adones Guerra, Tech Lead, Grupo Globo

In the agentic enterprise, the conversation is the interface

The goal is simple: Work that used to pull people out of the conversation now happens inside it. Not just text back and forth, but approvals, decisions, rich data, full workflows, all surfaced inside the channels where your people already are. That’s what it means for the conversation to be the interface. And Slack is increasingly where that conversation lives. Custom AI agents on Slack have grown 300% since January, and Slackbot is the front door to the Agentic Enterprise.

That’s also why we built the Agentforce Experience Layer. Some work needs more than text. A card to approve, a workflow to complete, a decision to make. The Experience Layer is a new UI service that separates what an agent does from how it appears, so your agents can deliver rich interactive components like flight status cards, rebooking workflows, decision tiles, and data layouts. They render natively inside Slack, and across Mobile, ChatGPT, Claude, Gemini, Teams, or any client that supports MCP apps. Build once, render everywhere your people already work.

“At Indeed, our mission is to help people get jobs, and the faster we can innovate, the faster we can connect job seekers to the right opportunities and employers to the right talent. By building on Agentforce, we’re able to give coding agents live access to our entire platform, directly within the tools we already use, so we can move from idea to implementation quickly. This paired with proper gating and human-in-the-loop best practices, the results are faster delivery, more consistent execution, and a much clearer path from experimentation to production impact.” — Oliver Bodden, Senior Product Manager, Indeed

Build agents you can trust at scale

Shipping an agent is the easy part. Knowing it will behave the way you designed it, reliably, across every edge case, weeks after launch, is where most enterprises struggle.

That is because agents are fundamentally different from traditional software. They are probabilistic, not deterministic. They do not behave the same way every time. They encounter unanticipated scenarios and reason their way to unexpected outcomes. There is no bug to fix but behavior to observe, evaluate, and tune.

We built an entirely new set of tools to give you that control, across every stage of the agent lifecycle.

Before launch, Testing Center surfaces logic gaps, policy violations, and inconsistent outputs before they reach users. Custom Scoring Evals go further. Instead of telling you whether something ran, they score whether it made the right decision. You define what good looks like for your use case. A customer service agent that declines an out-of-policy refund while clearly explaining alternatives, for example. Every response is evaluated against that standard, not just whether it is executed. Agent Script gives you control over the agent itself before it ever sees a test. Define exactly which parts of its behavior must follow explicit business logic and which parts can reason freely.

After launch, Observability and Session Tracing show not just what happened but the why. When an agent drifts, you find the cause in hours, not weeks. A/B Testing lets you run multiple agent versions against real traffic simultaneously, with data-driven decisions about what to promote to production.

And for enterprises running agents across multiple platforms and vendors, the new Agent Fabric brings them under one governed control plane, with deterministic orchestration and centralized agent, tool, and LLM governance across your entire AI landscape.

Launching used to be the finish line. In the agentic era, it is the starting line.

Agents are only as good as the platform they run on

If agents can call any API, if the models are already powerful, why does the platform matter?

Because intelligence alone is just inference. It needs context, workflows, trust, and the right engagement layer to actually do anything.

The best coding agents and LLMs are extraordinary. But a coding agent connected to a raw database doesn’t know that a customer has an open escalation, a renewal due in 30 days, a breached support SLA, and a relationship owner with a personal connection to their CFO. That context took years to accumulate. It lives in Salesforce. And now, Data 360 exposes it as an API, an MCP tool, a CLI command, so your coding agent can reach it from anywhere, without touching a UI. That’s what separates a coding agent that writes code from one that understands your business.

Context is only part of it. Agents also need workflows. The approval chains, the business rules, the edge-case logic that someone built years ago and that legal still depends on. When an agent operates inside Salesforce, it inherits all of that. It does not have to rediscover it or approximate it. It works within it.

Then there is trust: the permissions, sharing rules, and compliance controls that your IT and security teams already approved. In most platforms, you rebuild that trust layer from scratch every time you deploy something new. In Salesforce, it is already there. The guardrails your organization relies on are the same guardrails your agents operate within.

Most vendors can give you one layer. Some can give you two. Only Salesforce gives you all four, already integrated, already running inside your enterprise.

Developers are not starting from scratch. They are building on infrastructure that is already running inside their enterprise, with the data, the workflows, the permissions, and the engagement layer already in place. That is what nobody else can offer.

One marketplace. Every tool your agents need.

AgentExchange brings together 10,000 Salesforce apps, 2,600+ Slack apps, and 1,000+ Agentforce agents, tools, and MCP servers from partners including Google, Docusign, and Notion, all discoverable through AI-guided search and activated in one click.

After listing, Notion cut its average sales cycle from four months to three weeks. Docusign processed 200+ private offers in Q4 2025 with 60% faster time to signature. MeshMesh closed its first Fortune 500 customer six weeks after listing.

A new $50M Builders Fund provides investment, engineering support, and go-to-market pathways for Agentblazers ready to scale. 

Build any way you want. Deploy anywhere your users are.

Welcome to Salesforce Headless 360. 

APPENDIX

100+ new tools and skills. Available today.

Salesforce Headless 360 spans the full development lifecycle with purpose-built capabilities at every stage.