Salesforce AI

⚡ 1-Minute Summary (Key Points) The Model Context Protocol (MCP) is an open standard that lets AI models like Anthropic's Claude and Salesforce Agentforce safely plug into external business databases and apps. Every MCP server is built on three foundational building blocks (called primitives): Tools , Resources , and Prompts . Tools are executable actions controlled by the AI model (e.g., creating a Salesforce Lead or running a live SOQL search). Resources are read-only files and context controlled by the application (e.g., reading an Account profile or PDF contract). Prompts are pre-built instruction templates controlled by the user (e.g., a slash command that formats an executive sales briefing). The Golden Memory Trick: Tool = DO (Model-Controlled), Resource = KNOW (App-Controlled), Prompt = GUIDE (User-Controlled). With Salesforce's native MCP support in Agentforce and MuleSoft, enterprise architects...

💬 In plain words: Running AI in Salesforce is like running the air conditioning in your house—every time an agent thinks, looks up a document, or runs a background action, the electric meter spins. In Salesforce, that meter is called the Digital Wallet . Every customer chat, automated action, vector search, and batch test eats up your prepaid balance of Flex Credits , Einstein Requests , and Data Cloud Credits . As a smart architect or developer, your #1 rule is to write down your starting meter reading on Day Zero before you build anything, so you can calculate the exact cost of a single conversation before going live. ⚡ Key Points The Digital Wallet is your command center: Found right inside the Salesforce App Launcher, it gives you near-real-time tracking of your organization's consumption-based credits across production and sandboxes. Modern 2026 Agentforce Pricing Models: Salesforce has evolved beyond rigid flat-rate conversation c...

💬 In plain words: Think of managing a live Salesforce AI agent like visiting a doctor. Agentforce Studio gives you two distinct tools that answer two completely different questions. Agentforce Analytics is the thermometer in the waiting room—it tells you whether your agent looks healthy overall ("Is it working?"). Agentforce Optimization is the MRI scanner—it opens up the brain of your agent to show you the exact Topic, utterance, or missing Knowledge article that caused a conversation to fail ("Why is it breaking?"). ⚡ Key Points Two Tools, Two Jobs: Use Agentforce Analytics for high-level trend reporting (volume, deflection, escalations) and Agentforce Optimization for root-cause debugging (intent clustering, knowledge gaps, and session traces). Deflection Alone Is a Vanity Metric: A 75% case deflection rate looks great on a slide deck, but it counts angry customers who rage-quit the chat window the exact same way i...

💬 In Plain Words: Imagine if every AI app needed its own custom connector for Salesforce, GitHub, your databases, and your files. That's a lot of code to build and maintain. The Model Context Protocol (MCP) fixes this. It's an open standard that works like a "USB-C port for AI." Build one MCP connector for a system, and any MCP-compatible AI app can discover and use its data and tools.

⚡ Key Points: 1-Minute Summary Assistants vs. Agents: AI Assistants primarily answer questions and provide information. AI Agents understand goals, plan out steps, use tools, and take autonomous action. The Core Engine: True AI Agents combine contextual reasoning, decision-making logic, and external tool integration to complete multi-step tasks. Workflow Automation: Agents shift the paradigm from requiring users to drive every step manually to having the AI manage and execute the workflow. Claudeforce Vision: By merging Anthropic's Claude models with Salesforce's data layer (often using the Model Context Protocol or MCP), enterprises can build intelligent, autonomous business workers. 💬 In plain words: An AI Assistant gives you answers when you ask a question. An AI Agent receives a high-level goal and actually works to complete it. For example, you ask an Assistant, "Which customers need follow-up?" and it gives you a l...

⚡ 1-Minute Summary Instructions resolve top to bottom. Logic lines run. Prompt lines become English. The model never sees your script. It sees only the finished prompt your logic built. Shorter reasoning instructions produce more accurate agents. Verbosity is not thoroughness. Module map MODULE 2 root: 'What actually happens in one turn?' ├─ 2.1 Anatomy of one turn ├─ 2.2 How the prompt gets built └─ 2.3 Why shorter instructions win Anatomy of One Turn 💬 In plain words: Every message follows the same seven steps: router, before-reasoning, instructions, model, tools, after-reasoning, reply. Learn this sequence and every design decision in Agentforce explains itself. 📌 Example: A Meridian customer says "is my power back yet?". The router picks the outage subagent. Before-reasoning verifies their meter. Instructions run a status action and branch. The model phrases the answ...

💬 In plain words: An instruction tells an AI model what it should do. A filter (or guardrail) controls what an AI model can do. A determined user can always manipulate an AI into ignoring what it "should" do, but nobody can bypass hard-coded system filters that dictate what it "can" do.

💬 In plain words: The Agentforce AI model chooses which action to call by reading its description. It does not look at the action's name, and it does not read the underlying code. Therefore, an action description is not documentation for human developers—it is the strict selection criteria the model uses to choose between a dozen different tools. 📌 Example: Naming an action "Creates an appointment" is incredibly weak. A strong description looks like this: "Books a field crew visit for a specific meter on a chosen date. Returns the booking reference and confirmed date. Use only after checking whether the fault is on the customer's side." 🎬 Real-Life Example: The Action That Never Got Called The Old/Bad Way: A development team built a flawless Apex action to check for system outages. They lazily set the description to: "Outage utility method." Why it failed: The AI model relies purely on description...

💬 In plain words: A user needs two separate grants before an agent is useful to them. One lets them use the agent at all. The other lets the agent reach data. They fail in completely different ways. 📌 Example: A Meridian rep is granted every object the agent touches, but not Agent Access. The agent simply does not appear for them. Nothing is wrong with the data model. 🎬 Real-Life Example: The Agent Nobody Could Find The Old/Bad Way: An admin built an agent, activated it, tested it in preview, and told the team it was live. Nobody could see it — including the admin, outside preview. Why this fails: Agent Access is a separate grant inside a permission set. Building an agent does not grant you the right to use it. Preview bypasses this, which is exactly why the gap goes unnoticed. The New/Good Way: In the permission set, find the Agent Access section. Add the specific agent to the enabled li...

💬 In plain words: An agent can only do what its user can do. Field-level security applies, sharing rules apply, and there is no override. The only question is which user, and that is decided by the agent type. 📌 Example: A Meridian rep asks the Employee Agent about a meter on an account they cannot see. The agent says it cannot find it. The meter exists — the rep just has no access. Concept This is the single most useful fact in Agentforce, and the most commonly got wrong. Employee Agent: Runs as the logged-in user. Service Agent: Runs as its own dedicated user ( default_agent_user ). Field-level security (FLS) is enforced normally. Sharing rules are enforced normally. Apex actions inherit this through with sharing and WITH USER_MODE queries. The failure mode is silent. There is no error, no exception, and no error banner. The agent simply says it cannot help, in a perfectly polite sentence. That s...

⚡ 1-Minute Summary Employee Agents run with the logged-in user's permissions. Service Agents have their own user. default_agent_user is required for a Service Agent and ignored for an Employee Agent. Two separate grants: Agent Access to use the agent, data access to reach the records. Module map MODULE 1 root: 'Which user is this agent, and what may it touch?' ├─ 1.1 Employee Agent vs Service Agent ├─ 1.2 Which user the agent runs as ├─ 1.3 Agent Access vs data access └─ 1.4 Designing permissions for agents Employee Agent vs Service Agent 💬 In plain words: Two agent types. One serves your staff, one serves your customers. The difference is not the skin — it is whose permissions the agent borrows, and that changes how you secure everything. 📌 Example: Meridian has two. The call-centre panel in Lightning is an Employee Agent. The chat window on meridianpower.com is a Service Agent...

💬 In plain words: About twenty core words carry most Salesforce Agentforce conversations. Learn these fundamental terms once, and every technical module, architectural diagram, and certification guide will read significantly faster. Each entry below points directly to the system component that powers it. 📌 Key Points Covered in This Guide The difference between internal Employee Agents and external Service Agents . How the Agent Router intelligently hands off conversations to specialized Subagents . Why developers must understand the technical divide between Actions and Tools . How Grounding and the Data Library connect Large Language Models (LLMs) to your private CRM data securely. The role of the Einstein Trust Layer in maintaining data privacy. 🤖 Core Architecture: Agents & Routing To build effectively on Salesforce's modern AI stack, you must understand the primary actors in the system. An Agent is ...

💬 In plain words: Abstract concepts are hard to memorize. To understand how Salesforce Agentforce really works, we use one single running example throughout this guide: Meridian PowerPack . Meridian is a fictional electricity utility company. They sell power, read meters, dispatch repair crews, and handle billing disputes. By applying Agentforce features to Meridian's daily operations, the technical architecture becomes instantly clear. 📌 Key Points Covered in This Guide How to map standard Salesforce objects (Accounts, Cases, Work Orders) to an AI Agent's thought process. The difference between good AI use cases (unpredictable language) and bad ones (deterministic batch processes). How to use Data Libraries to ground your agent in reality, preventing dangerous hallucinations. Why you must split massive business requirements into specialized Subagents rather than building one mega-agent. How strict guardrails prevent your ...

⚡ 1-Minute Summary An agent understands language, decides what to do, and acts. A chatbot only answers. Every example in this notebook uses one company: Meridian Power. Same company, every module. Learn the 360 Card first (0.5). It is the shape of every good answer: rule, gain, price, limits. Module map MODULE 0 root: 'What is Agentforce, and how do the modules fit together?' ├─ 0.1 The map: one agent, six layers ├─ 0.2 Meridian Power — the example company ├─ 0.3 Key terms in plain words ├─ 0.4 The rename map (2024-2026) └─ 0.5 The 360 Card — how to answer any question 0.1 The Map: One Agent, Six Layers 💬 In plain words: Agentforce looks like many products. It is not. It is one agent with six layers stacked under it. Each layer answers one question, and each module of this notebook lives on one layer. 📌 Example: A customer types "my power is out." Identity decides whose dat...

In plain words: Salesforce AI combines historical pattern recognition (predictive AI) with conversational content creation (generative AI). Powered by Salesforce Einstein, Data Cloud, and autonomous assistants, it drafts customer replies, scores leads, writes code, and summarizes support cases directly inside your CRM workflows. Artificial Intelligence in Salesforce has evolved from background statistical algorithms into an enterprise-wide generative engine. Modern Salesforce architectures bring together real-time customer data, large language models (LLMs), and automated workflows to deliver contextual, secure, and personalized business interactions across Sales, Service, and Marketing clouds.

In plain words: Generative AI is artificial intelligence that creates brand-new content—like personalized customer emails, case summaries, code snippets, or product descriptions—instead of just analyzing numbers. In Salesforce, it connects large language models directly to your live CRM records so the AI writes accurate, company-specific responses safely. Generative Artificial Intelligence is transforming how businesses communicate with their customers. While traditional AI excels at predicting numerical scores (like whether a deal will close), Generative AI produces human-like text, conversation drafts, summaries, and synthetic media grounded in real-time enterprise data. Integrated natively into the Salesforce Einstein 1 Platform and Agentforce , it turns manual administrative tasks into automated, one-click workflows.

In plain words: Natural Language Processing (NLP) is how Salesforce understands everyday human language. Instead of forcing customers or reps to use exact keywords or rigid dropdown menus, NLP allows the system to read incoming emails, chats, or search queries, understand the customer's intent and emotion, and automatically route tickets, score leads, or draft replies. Customer communication rarely arrives neatly organized in structured database fields. Support requests, web inquiries, and emails come as conversational text filled with slang, varying tones, and complex questions. By embedding Natural Language Processing (NLP) directly into the Salesforce platform via the Einstein 1 Platform and Agentforce , organizations can interpret unstructured customer messages, categorize records instantly, and automate responses at scale.

In plain words: Salesforce Einstein GPT (which has evolved into the generative AI engine of the Einstein 1 Platform and powers Agentforce ) embeds enterprise-grade generative AI directly into your CRM workflows. It drafts personalized sales emails, generates service chat replies, summarizes cases, and automates code—all while protecting sensitive customer data through the Einstein Trust Layer . Generative Artificial Intelligence has reshaped how modern businesses create content, analyze information, and assist customers. However, public large language models (LLMs) lack real-time business context and pose data privacy risks if customer records are leaked to train third-party models. Salesforce bridges this gap by unifying generative AI with real-time CRM metadata and Data Cloud , giving teams powerful AI capabilities grounded in verified enterprise data.