Atlas Reasoning Engine

• Agentforce Assistant, which has now evolved into an Agentforce Agent for customer relationship management (CRM).
• Agentforce Assistant was a generative AI-powered conversational assistant that derived its intelligence from a mechanism called Chain-of-Thought reasoning (CoT) - In this mechanism, the AI system mimics human-style decision-making by generating a plan containing a sequence of steps to attain a goal.
• This made it quite advanced compared to traditional bots, but it fell short of truly mimicking a human-like intelligence. It generated a plan that contained a sequence of actions in response to tasks, and then executed those actions one by one. If the plan was incorrect, however, it did not have a way to ask the user to redirect it.
• This led to Agentforce development - industry-first, enterprise-grade conversational automation solution that can make proactive and intelligent decisions at scale with little or no human intervention.
• Orchestration based on ReAct prompting vs. CoT- Reasoning and Acting (ReAct) - style prompting yielded much better results compared to the CoT technique. In the ReAct mechanism, the system goes through a loop of reason, act, and observe until a user goal is fulfilled.
• This kind of looping approach lets the system consider any new information and ask clarifying questions or confirmations so that the user’s goal is fulfilled as precisely as possible. This also leads to a much more fluid and natural language-like conversational experience.
• Topic classification - introduced a new concept called topics, which maps to a user intent, or job to be done.
  When a user input comes in, it gets mapped to a topic, which contains the relevant set of instructions, business policies, and actions to fulfill that request. This mechanism helps define the scope of the task and the corresponding solution space for the LLM, allowing the system to scale effortlessly. Natural language instructions embedded in topics provide additional guidance and guardrails for the LLM.
  These concepts allow agents to scale to thousands of actions safely and securely.
• Use LLMs for responses - Previously, we restricted the system to respond only with action outputs, which severely constrained its ability to respond based on the information available in the conversation.
  By opening up the system to let the LLM respond using the context in conversation history, we’ve allowed for a far richer conversational experience. Now, users can ask for clarifications and ask follow-up questions to prior outputs, leading to an overall higher goal-fulfillment rate.
• Thoughts/reasoning - Prompting LLMs to share thoughts or provide reasons for selecting certain actions prevents hallucinations tremendously.

Email Marketing

• Is push channel - doesn't have to wait to reach out to customer.
• Gives customers and leads the opportunity to communicate with the business.
• Allows customers to reply — to give direct feedback, to ask questions, and to engage with company.
• It is one out of many inbound marketing method.
• Generic approach to email marketing might get you an average return on investment.
• Targeted email specific to customer interest and needs, impacts metrics and people.
• Emails are sailboats, your email marketing strategy is the wind.
• Marketing strategies provides direction and momentum.
• Is often seen as a technology-driven channel, not a marketing channel, but it's not.
• Email is a dynamic platform for the inbound marketer.

Inbound Marketing

• Is all about engaging with people in a helpful and human way.
• It’s about sharing value in order to receive understanding.
• Is about listening to our prospects and customers, so that we can deliver what will be beneficial to them.
• Delivering value to your customers, you want your messaging to be helpful to them.

Email Marketing Strategy

• That fits your business and attracts, engages, and delights your customers.

Preparation Phase

• Preparing email for sending and its purpose.
• Selecting your ESP is a part of the preparation phase of your email marketing strategy.
• Inbound marketing is about generating genuine connections with your leads and customers.

SMART Goal

• SMART goal is specific, measurable, attainable, relevant, and time-bound.
• Specific: making your goal specific ensures that it's clear for all involved.
• Measurable: include tangible metrics when setting goals.
• Attainable: should be in the realm of possibility.
• Relevant: should contribute to your overall business strategy.
• Time-bound: giving your goal a due date or time frame.

Email Marketing Strategy

• ESP’s IP address affects your sender reputation.
• Connecting your CRM and ESP allows for cleaner data, avoid duplication and mitigate the risks of losing important behavioral data.
• CRM helps you to organize all the data you gain from contacts, and behavioral data, such as email engagement, is extremely valuable.
• Some common ESPs: Constant Contact, MailChimp, Campaigner, Sendinblue, Drip, AWeber, and HubSpot.
• Selecting ESP look for education, customer service available, the design features, the potential integrations, and the capabilities for automation.
• Also, check integration option with CRM. Tool like HubSpot works as CRM and ESP.

Additional References and Resources

Refer to the additional references and respurces below for the exam preparations.

• How to Build an AI Agent
  
• How the Atlas Reasoning Engine Powers Agentforce
  
• What Is HubSpot Breeze, and How Does It Work?
  comprehensive AI toolkit first introduced at INBOUND 2024.