Salesforce Agentforce

Summary

Agentforce is Salesforce's platform for building AI agents that answer questions and take actions inside its CRM, using the Atlas Reasoning Engine to plan each step. It spans customer service, sales, field service and employee support, plus a coding agent, Agentforce Vibes.

Best for: Salesforce service, sales, field-service and employee-support teams that need agents to act on CRM records and have Salesforce admin or developer capacity.
Not for: Teams outside the Salesforce ecosystem, or buyers who need a CRM-neutral builder, a fast small-team setup or a flat, predictable seat price outside Salesforce licensing.

Captured 2026-08-23 · theagentsindex.com

From: Freethen $5/user per month
Free tier: YesSalesforce Foundations is a $0 add-on activated inside an existing Salesforce org (not a time-boxed trial). It includes Agentforce Builder, Agent Script, Prompt Builder, Agentforce Coworker and Service/Sales/Employee Agents. Agentforce usage consumes credits: the FAQ states a 200K Agentforce Flex credit grant while the Agentforce feature card states 445k-450k Flex Credits shared with Data 360 - the page publishes both figures. Overage fees apply and usage is tracked in Digital Wallet. Other caps include 2,000 marketing emails per org per month, and a footnote marks the credit inclusion as U.S. only with restrictions.

Visit Salesforce Agentforce Compare Find alternatives

What it does

Writes code: YesThe Agentforce Vibes coding agent turns a natural-language description into Salesforce code and metadata.Transform ideas into contextual and structured code using natural language.salesforce.com/agentforce/developers/vi…
Debugs and fixes: YesVibes runs the test or deployment, reads the failure and iterates toward a fix rather than stopping at the error.Iterates on failures. When a test fails or a deployment errors, it diagnoses the problem and attempts a fix rather than presenting an error and…developer.salesforce.com/docs/platform/…
Writes tests: YesApex test classes and LWC Jest tests are generated alongside the code, with a dedicated QA Validator sub-agent for coverage.Test class generation is time-consuming but well-suited to agent execution. QA Validator in Teams Mode handles assertions, bulk test data, and…developer.salesforce.com/docs/platform/…
Reviews code: PartlyStatic analysis with auto-fix runs over code in your own workspace and Git diffs can be attached as context, but no diff or pull-request review feature is documented and the docs state the trust layers do not replace code review.Scan large amounts of code, catch potential bugs, identify runtime efficiency errors, catch security vulnerabilities early in the development…salesforce.com/agentforce/developers/vi…
Whole-codebase work: PartlyParallel sub-agents coordinate multi-file, cross-layer changes in isolated Git worktrees, but the docs warn that context truncates, advise preferring specific files over entire folders, and claim no repository-wide index.Each sub-agent operates in an isolated context and uses distinct Git worktrees to eliminate workspace conflicts while building out features across…developer.salesforce.com/docs/platform/…
Ships it: YesIt deploys metadata to the org itself, and through the Salesforce DX MCP Server's DevOps Center tools it commits and opens pull requests; deploy and delete stay approval-gated by default.It creates files, modifies code, runs commands, and deploys metadata directly in your local workspace.developer.salesforce.com/docs/platform/…
Done-for-you service: PartlyAgentforce is software the customer configures in a low-code builder; Salesforce separately sells Professional Services that performs the hands-on build, reached through an account executive rather than bundled with the product.while we handle the hands-on build, integration, and data worksalesforce.com/services/professional-se…

How much it does unattended

Runs autonomously: YesAutonomy is a per-agent setting rather than a fixed trait; agents escalate to a human when an issue exceeds their scope.Agents can be autonomous (act without human intervention) or can be guided to involve a human in the loop.salesforce.com/agentforce/guide
Multi-agent: YesA primary agent delegates to secondary specialist agents routed by the Atlas Reasoning Engine, and can delegate to third-party agents over Agent2Agent.Multi-Agent Orchestration allows you to build a team of specialized AI agents that work collaboratively to solve complex problems.salesforce.com/agentforce/multi-agent-o…
Agent permissions: PartlyGuardrails and filters bound which topics and actions an agent may reach and data access honours existing Salesforce permissions, but an approval-before-every-action mode is documented only for the Agentforce Vibes coding agent.Agentforce Guardrails combine user-defined safeguards and Salesforce managed protections to foster trust and maintain control over agent behavior.salesforce.com/agentforce/how-it-works

Which models it runs on

Claude: YesAnthropic Claude models are named rows in the supported-model table, and the non-default AWS-Hosted Agentforce model option is a Claude model on Amazon Bedrock.Anthropic and Amazon models are operated on Amazon Bedrock infrastructure entirely within the Salesforce Trust Boundary.developer.salesforce.com/docs/ai/agentf…
GPT: YesOpenAI and Azure OpenAI GPT models fill most of the supported-model table, and the out-of-the-box Salesforce Default option is a GPT-based managed mix.The Salesforce Default model option for Agentforce is a managed mix of trusted models (currently including GPT-4o) optimized by Salesforce for…developer.salesforce.com/docs/ai/agentf…
Open models: PartlyThe Salesforce-managed model list names only Anthropic, OpenAI/Azure OpenAI, Google Vertex, Amazon and NVIDIA (beta), with no Llama or Mistral, so open-weight models arrive only through the customer's own BYOLLM connection.you can connect the Einstein AI Platform to any language model, including custom-built modelsdeveloper.salesforce.com/docs/ai/agentf…
Model choice: YesThe customer selects the model option in Setup and can override it per agent or subagent in Agent Script; leaving the default hands the choice to Salesforce's managed mix.To change the default model option for Agentforce, go to the Agentforce Agents page in Setup.developer.salesforce.com/docs/ai/agentf…

Where you use it

In your editor: YesAgentforce Vibes ships as a VS Code extension and is preinstalled in the Salesforce-hosted Agentforce Vibes IDE.This secure, AI-powered developer tool is available as an easy-to-install VS Code extension.developer.salesforce.com/docs/platform/…
On the command line: PartlySalesforce CLI drives the whole agent lifecycle from a terminal, but the Vibes coding agent itself is distributed only as a VS Code extension and a hosted IDE. There is no standalone Vibes CLI.Scaffold, deploy, preview, and test agents from the terminal or a continuous integration (CI) system.developer.salesforce.com/docs/ai/agentf…
In your pipeline: PartlyAgent tests run in a CI system via Salesforce CLI and DevOps Center tools handle pull requests and pipeline promotion, but Salesforce documents no agent that runs on a pull request by itself.Add the tests to a continuous integration (CI) system to make sure that your agent continues to work correctly in the future.developer.salesforce.com/docs/ai/agentf…
In a browser: YesAgents are built and administered in the browser inside Salesforce, and can be embedded on the customer's own website via the Agent API and messaging channels.The Agentforce Builder is located inside Agentforce Studio in the App Launcher. Access is granted by admin permissions.salesforce.com/agentforce/agent-builder

Whose machine it runs on

Self-hosted: NoAgentforce runs on Salesforce's own public-cloud infrastructure, and even default model inference is operated inside the Salesforce Trust Boundary; no on-premises or customer-VPC deployment is offered.Hyperforce is the next-generation Salesforce infrastructure architecture, built for the public cloud.salesforce.com/platform/public-cloud-in…
Open source: PartlyThe Agentforce platform is a hosted Salesforce service and is not distributed as source; the Salesforce Skills Library that grounds Agentforce coding agents is published Apache-2.0 on Salesforce's own GitHub org.Apache License Version 2.0 Copyright (c) 2026 Salesforce, Inc. All rights reserved.github.com/forcedotcom/sf-skills/blob/m…

What it costs to run

How it meters: YesConsumption is metered per action against a Flex Credit pool: 20 credits per Agentforce action, 30 per voice action, 100k credits for $500. Per-user licensing and a flat $2 per conversation are the alternatives.Each action is metered individually, so your investment aligns to the value delivered, not just the number of interactions.salesforce.com/agentforce/pricing
Free tier: YesSalesforce Foundations is a $0 add-on activated inside an existing Salesforce org, seeded with a fixed Flex Credit grant and subject to overage fees; every paid Agentforce tier routes to a sales conversation.Yes, Foundations is a $0 add-on that gives your org access to more functionality.salesforce.com/crm/foundations
API access: YesThe REST Agent API needs Agentforce enabled with an activated agent, is not supported for the 'Agentforce (Default)' agent type, and its usage draws down credits.With Agent API, you have access to your goal-oriented, autonomous AI agents from anywhere that can call a REST API.developer.salesforce.com/docs/ai/agentf…
MCP server: YesSalesforce hosts MCP servers so external agents can query an org under per-user OAuth, and Agentforce is also an MCP client consuming third-party servers attached in Agent Builder.any compatible AI client—Claude, ChatGPT, Cursor, or a custom agent—can connect to a Salesforce org and act on behalf of authorized usersdeveloper.salesforce.com/docs/platform/…
Bring your own key: PartlyOwn inference via BYOLLM from four providers with your own credentials, but requests still route through Salesforce's Models API; own encryption keys require the Salesforce Shield add-on, and the agent runtime always stays on Salesforce.With BYOLLM, you can add a foundation model from a supported provider, configure your own instance of the model, and connect to the model using your…developer.salesforce.com/docs/ai/agentf…

Buying it for a team

A company can buy it: YesSold to organisations through an account executive: every paid tier's call to action is 'Contact us', and only the $0 Foundations add-on is self-serve inside an existing org.Contact your Account Executive to learn more about what model might work best for your business and use case.salesforce.com/agentforce/pricing
Seat model: YesPer-user options are $5/user/month (metered, requires Flex Credits), a $125 add-on, a $150 Industries add-on and Agentforce 1 Editions from $550; no seat minimum or maximum is published.Choose from consumption-based pricing, with Flex Credits or Conversations, or per-user licensing — with options designed to fit how and where you…salesforce.com/agentforce/pricing
Pooled budget: YesOne fungible org-level credit balance spans teams and channels, with Agentforce 1 Editions bundling 2.5M credits per org per year, and Digital Wallet tracks it and automates internal chargebacks.Flex Credits can be applied across teams, channels, and use cases, allowing you to expand your AI strategy without renegotiating pricing or…salesforce.com/agentforce/pricing
Admin controls: YesAdmins author the agent's topics, actions and guardrails; the Trust Layer additionally masks PII/PCI and filters toxic output, and agent data access honours existing permissions and sharing rules.Agent Builder enables Salesforce admins and developers to use natural language to create jobs to be done, instructions, actions, and guardrails for…salesforce.com/agentforce/how-it-works
Audit log: YesAgent actions and outputs are recorded for governance, and Observability adds per-turn session traces; event-level logging with SIEM streaming and Field Audit Trail are the paid Salesforce Shield add-on.the Audit Trail feature provides the data you need to track AI agent actions and outputs, ensuring AI usage complies with your organization's…salesforce.com/agentforce/how-it-works
Single sign-on: YesBoth protocols are supported, and the org can act as identity provider, service provider or both; Single Logout is configured separately.Salesforce supports SSO with SAML and OpenID Connect.help.salesforce.com/s/articleView

What happens to your code

Opt out of training: YesThere is nothing to opt out of: the Einstein Trust Layer applies zero retention by default, so prompts and responses are not stored by or used to train the third-party models.Zero data retention is a strict policy where the prompts and generated responses are never stored or used to train the underlying third-party large…salesforce.com/artificial-intelligence/…
Data residency: YesRegion is selectable on Hyperforce, with in-country storage conditional on the service being available in that country; strict EU storage and processing with in-region support is the paid Hyperforce EU OZ.Select global regions on where your Salesforce applications will run with options for the U.S., U.K., Germany, India, Japan, and more.salesforce.com/platform/public-cloud-in…
Getting out: PartlyData is exportable during the term and returnable for 30 days after termination, though insights, reports and scoring may be manual-export-only; unused Flex Credits do not roll over between subscription terms.During the contract term, customers may export a copy of any Customer Data made available for export through the Covered Services.salesforce.com/en-us/wp-content/uploads…
Certifications: YesThe Agentforce-scoped audits section lists SOC 2, ISO 27001/27017/27018, ISO 42001, EU/UK Binding Corporate Rules and Data Privacy Framework; a footnote excludes Agentforce Vibes and Agentforce for Scale, and FedRAMP sits with Government Cloud Plus.Salesforce has achieved ISO 27001/27017/27018 certification for its ISMS from an independent third party.salesforce.com/en-us/wp-content/uploads…

35 sourced claims on this page. Checked 2026-09-03. How we check.

Alternatives

Where we would send a reader instead, in that listing's own words.

n8n
Workflow automation platform for building and running AI agents on a visual canvas, with code where needed.
Sierra
Conversational AI platform for building enterprise customer-service agents across voice, chat, email and ChatGPT.
Dify
Open-source platform for building agentic workflows, AI agents and RAG knowledge pipelines.
MindStudio
No-code visual builder for AI agent workflows, published as web apps, APIs, webhooks or MCP servers.
Relevance AI
Hosted low-code platform for building, evaluating and running teams of business AI agents.
Botpress
AI agent platform with a visual studio, a code-first TypeScript ADK and a helpdesk, priced per conversation.
Glean
Enterprise AI platform for building, governing and running agents on permission-aware company context.
Moveworks
Enterprise AI assistant plus a low-code studio for building agents across business systems.

Filed under

APIAutonomousClaudeEnterpriseFree tierGPTMulti-agent

Sources and updates

The pages we read29

2 of 29 independent of the vendor.

Platform record2026-08-30

Licence: Apache-2.0
Stars: 81
Forks: 22
Last push: 2026-06-02

Coverage elsewhere3

Updates4

2026-09-03Capabilities · Commercial terms · Free tier · Price
2026-08-31Capabilities · Commercial terms · Free tier · Price
2026-08-23Alternatives · Documentation link · One-liner · Repository · Summary
2026-08-19Summary