Overview
The Salesforce AI Sales Agent is a purpose-built AI agent designed to supercharge enterprise sales productivity by integrating directly with Salesforce through a secure MCP server. It empowers sales representatives to work smarter by automating routine CRM activities, such as generating account summaries, creating new opportunities, retrieving and updating open opportunities, and logging sales tasks, all without leaving their preferred workspace.
With real-time access to Salesforce data, the Salesforce AI Sales Agent provides instant account context and opportunity management, reducing manual data entry and minimizing context switching. The agents intuitive interface and robust automation help sales teams focus on building relationships and closing deals, not on administrative work. Built for deployment on AWS, it leverages containerization for scalability, reliability, and enterprise-grade security. Whether your team needs to quickly update pipeline status, review key accounts, or log critical follow-up tasks, the Salesforce AI Sales Agent delivers a seamless and efficient sales experience.
Highlights
- Eliminates manual CRM work, giving your sales team more time to sell and less time on data entry, unlocking higher productivity and faster deal cycles.
- Seamlessly integrates with Salesforce, enabling instant access to account data, opportunity updates, and task logging, all from a single, intuitive interface.
- Empowers sales teams with real-time insights and automated workflows, accelerating deal cycles and improving pipeline visibility across the organization.
Details
Unlock automation with AI agent solutions

Features and programs
Financing for AWS Marketplace purchases
Pricing
- $0.00/month
Vendor refund policy
not applicable
How can we make this page better?
Legal
Vendor terms and conditions
Content disclaimer
Delivery details
Marketplace Agentic Delivery
- Amazon Bedrock AgentCore - Preview
Container image
Containers are lightweight, portable execution environments that wrap server application software in a filesystem that includes everything it needs to run. Container applications run on supported container runtimes and orchestration services, such as Amazon Elastic Container Service (Amazon ECS) or Amazon Elastic Kubernetes Service (Amazon EKS). Both eliminate the need for you to install and operate your own container orchestration software by managing and scheduling containers on a scalable cluster of virtual machines.
Version release notes
Deploy for arm64
Additional details
Usage instructions
Follow these steps to configure and use the Salesforce Agent.
Configure Environment Variables
Before running the agent, you must set the following four environment variables in your environment. These variables allow the agent to securely authenticate with your Salesforce instance.
SF_USERNAME: Your Salesforce username. SF_PASSWORD: Your Salesforce password. SF_SECURITY_TOKEN: Your unique Salesforce security token. For help obtaining your Security Token, please refer below. SF_DOMAIN: Your Salesforce domain. This is typically login.salesforce.com for production environments or test.salesforce.com for sandboxes.
Example: You can set these variables in Step 2 when creating the agent runtime. --environment-variables '{ "SF_USERNAME": "username@acmecorp.com ", "SF_PASSWORD": "password1234", "SF_SECURITY_TOKEN": "randomtoken", "SF_DOMAIN": "acmecorp.develop.my.salesforce.com", }'
Note: To use the agent, you need your Salesforce username, password, and a security token.
Username and Password: Use the same credentials you use to log in to Salesforce. Security Token: If you don't have your security token, you can reset it from your personal settings within Salesforce. Log in to Salesforce.
Go to Settings > My Personal Information > Reset My Security Token. Click the Reset Security Token button. The new token will be emailed to you.
Note: When authenticating, Salesforce requires the security token to be appended directly to the end of your password. However, this agent handles the concatenation for you. Simply provide the password and token in their respective environment variables.
Once the agent is running in Step 3, you can send requests to it using a JSON payload. The payload should contain an input object with a prompt detailing your request.
Example Payload:
{ "input": { "prompt": "account summary for CustomerA" } }
Support
Vendor support
AllCloud is here to assist and answer questions regarding GenerativeAI. Contact us at info@allcoud.io and a team of AllCloud experts will assist you quickly. Email: info@allcloud.io Contact Us URL:
AWS infrastructure support
AWS Support is a one-on-one, fast-response support channel that is staffed 24x7x365 with experienced and technical support engineers. The service helps customers of all sizes and technical abilities to successfully utilize the products and features provided by Amazon Web Services.