
Master cloud code for Salesforce by moving from fundamentals to building a full-scale agent team, while optimizing memory, context, tokens, plan mode, and safe automation with MCP integration.
Learn how cloud code, an AI-powered command line tool, operates inside your terminal with full project awareness, generating integrated files and coordinating parallel subagents for Salesforce development workflows.
Set up cloud code for Salesforce development by creating a cloud account, upgrading to pro, and installing VS Code, Salesforce CLI, and the cloud code extension, and authorize your org.
Explore essential slash commands in Claude Code for Salesforce development, including init to build a cloud.md memory, clear and compact for context management, and model switches between Opus and Sonnet.
Initialize a Salesforce sfdx project with Claude code by cloning a repo and running init to generate cloud.md, then explore the project to document components and apply AgentForce vibes rules.
Build an Apex batch class to archive beer records by tag equals archive, and create a status field with available and archive values; deploy to org via SF project deploy.
Update the cloud.md memory to reflect beer underscore C and batch objects, keep the project memory current, and optimize prompts to reduce token waste.
Create a validation rule on soft drink orders to prevent edits when the related soft drink is expired or the order quantity exceeds the remaining stock. Learn to deploy with Salesforce MCP and manage context with sub agents and memory files.
Use plan mode in Claude Code to plan a record-triggered flow for SoftRankOrder that creates a task linked to the account with a three-day due date when status is open.
Explore context, tokens, and scope in Claude code, and master read or plan mode and write mode; learn dynamic context cleanup and best practices for efficient prompts.
Learn how to generate a production-ready lwc from a UI mockup image using cloud code, including parsing the image to create HTML, js, and apex, and deploying the component.
Learn essential Claude terminal shortcuts for cloud code: escape stops or exits, up recalls history, and tab enables auto completion and file references with at-rate.
Explore how cloud code creates checkpoints during edits and enables rollback to a safe code state. Use rewind or escape twice to restore code and conversation while preserving context.
Create custom slash commands in Claude Code by storing prompts as markdown files under the dot cloud commands folder; automate tasks like SOQL queries and Apex triggers with reusable prompts.
Explore the risks of running Claude with full permissions, using bypass mode with the dangerously flag, and using doctor and debug modes to diagnose MCP setups.
Learn to configure Claude Code for safe automation by using settings.local.json and user-level settings.json to grant selective permissions, deny destructive commands, and auto-approve safe file operations.
learn how the model context protocol (mcp) acts as an open source bridge between ai agents and external data sources, enabling tools from Salesforce, Slack, and PayPal.
Configure Salesforce MCP for cloud deployments, update cloud.json and cloud.md, and use AI-friendly deployment tools to replace standard SF commands.
Expand cloud code access by linking the MCP server to Jira and GitHub alongside Salesforce, enabling reading Jira stories and LWC components or Apex classes for deployment to GitHub branches.
Automate end-to-end workflow across Jira, GitHub, and Salesforce using MCP, creating repositories and branches, pushing code, issuing pull requests from dev to main, then deploying metadata and running Apex tests.
Explore subagents in Claude Code to run task-specific workflows in their own context windows, preserving main context while exploring, planning, and deploying code with read-only and restricted tool access.
Create a Salesforce admin sub agent from scratch using an md file in an agent folder and a main clod.md agent, configuring tools, model, memory, and a detailed description.
Coordinate a three-agent workflow with design, admin, and developer agents under a main cloud agent. Design analyzes requirements and returns a plan; admin creates files; developer builds code and lwc.
Orchestrate a seven-agent Salesforce workflow from design to DevOps, with parallel and sequential steps, to deliver an end-to-end account health indicator using AI agents.
Install the cloud code for VS Code and switch from terminal based workflows to a UI based extension, enabling prompts, slash commands, and access to previous conversations within VS Code.
Learn to extend cloud code with skills, an enhanced version of custom commands, by creating skill.md to teach cloud to parse BRD documents and generate user stories.
Learn how to create a Claude Code skill that parses BRD PDFs into Salesforce user stories, maps requirements to components, and outputs an Excel workbook using Python scripts.
Develop and test a Claude code skill to parse a BRD PDF into Salesforce user stories, using a skill.md, Python scripts, and phased validation to generate an Excel report.
Claude Code for Salesforce Development: MCP & Agent Workflows
Salesforce development is evolving.
This course teaches you how to move beyond basic prompting and start building production-grade AI workflows inside real Salesforce projects using Claude Code.
This is a complete, end-to-end guide to mastering Claude Code for Salesforce development, from fundamentals to building a coordinated Salesforce Agent Team that can deliver a full user story.
If you are a Salesforce Developer, Salesforce Admin, Technical Architect, or AI enthusiast working in the Salesforce ecosystem, this course will show you how to leverage Claude Code, MCP (Model Context Protocol), and multi-agent systems to build faster, smarter, and more structured workflows.
What You Will Learn
Foundation and Setup
What Claude Code is and how it works inside a terminal-first workflow
Step-by-step setup of Claude Code for Salesforce DX projects
Essential slash commands and custom commands
Efficient context management and token optimization
Plan Mode vs Edit Mode and structured AI reasoning
Core Salesforce Development with Claude Code
Building Apex classes including Batch Apex
Creating Validation Rules and Record-Triggered Flows
Managing CLAUDE. md memory for persistent project context
Using image mockups to generate Lightning Web Components
Understanding Context, Tokens, Scope, and best practices for LLM-driven development
Checkpoints and rollback strategies for safe AI-assisted coding
Permission management using settings json for secure automation
Advanced AI Workflows and Productivity
Building reusable custom slash commands
Running Claude safely with controlled read and write permissions
Designing structured AI workflows instead of ad-hoc prompts
Optimizing token usage and reducing unnecessary context consumption
MCP (Model Context Protocol) and Enterprise Integrations
Introduction to MCP architecture
Enabling Salesforce MCP for intelligent deployments
Connecting Claude Code with Salesforce, Jira, and GitHub
Reading Jira user stories directly from Claude
Creating Git branches and raising Pull Requests automatically
Executing end-to-end workflows across multiple enterprise systems
This course teaches real-world DevOps workflows integrated with Salesforce DX, GitHub repositories, and Jira-based agile processes.
Multi-Agent Systems and Salesforce Agent Teams
Understanding Sub Agents in Claude Code
Creating specialized Salesforce agents (Design, Admin, Dev)
Defining workflows using claude . md
Scaling from a core team to a 7-Agent Salesforce architecture
Coordinating Design, Development, Testing, Code Review, DevOps, and Documentation agents
Delivering a complete Salesforce user story using shared memory and structured collaboration
You will learn how to architect and orchestrate AI-driven Salesforce teams using modern agent-based workflows.
Why This Course Is Different
This is not just another AI tutorial.
It focuses specifically on:
Salesforce DX development
Apex and Flow automation
Lightning Web Components
Enterprise Git workflows
Agile Jira integration
AI agent architecture
Context engineering
Token-efficient AI workflows
By the end of this course, you will be able to:
Use Claude Code professionally inside Salesforce projects
Connect Salesforce, GitHub, and Jira using MCP
Optimize context and token usage
Build reusable slash commands
Implement safe automation permissions
Design and deploy multi-agent Salesforce systems
Deliver real user stories using AI coordination
Who This Course Is For
Salesforce Developers who want to integrate AI into their daily workflow
Salesforce Admins exploring automation and AI-assisted configuration
Technical Architects designing AI-enabled enterprise workflows
DevOps engineers working with Salesforce DX and GitHub
Anyone interested in Agentic AI within the Salesforce ecosystem
AI-driven development is the future of Salesforce.
This course shows you how to implement it correctly.
If you are ready to move from basic AI prompts to production-grade AI workflows and agent-based Salesforce systems, this course is for you.