So before you jump in, here's a quick summary: Elements.cloud is the platform of choice for implementing Agents on Salesforce's Agentforce and other agentic platforms.

Elements allow you to:

This approach ensures transparency, reduces risks, and accelerates implementation, particularly for organizations with complex processes or strict compliance requirements.

Before implementing Agentforce with Elements.cloud:

The first step is to create Agent Interaction Map (AIM) for the agent you are designing. The map has 2 levels:

This top-level diagram shows the user interaction and on the right side of the diagram, the boxes represent the Topics. How the Atlas Reasoning Engine decides is based on the Topic Classification Description and Scope. You can see the Topic Classification description is the text on the line going into the JTBD / Topic box, and the Topic Scope is the text in the box.

You can copy the AIM template from the Elements Public Templates workspace to use as a starting point. It has the necessary structure.

The next step is to create a Level 2 diagram, called an Agent Instruction Diagram (AID). It is a drill down from a box in the Level 1 diagram. This is the Jobs To Be Done (JTBD) diagram that describes the Topic.

Whether you are using templates or starting from a blank screen, you should review this short video which explains the fundamentals of creating the most effective and reliable Agent Instruction Diagrams.

This covers mapping the triggers, activities, the actions with the resources used and guardrails.

Capturing precise logic is important when deciding how you want to educate Agentforce with the deterministic paths. These are what you would like it to base its reasoning and planning. Even though an agent is inherently probabilistic, you can still direct it, (in the same way you would with a human employee), by being very specific about when to follow certain paths and what to do. e.g. "IF" certain things happen or conditions are met. In this context, there is a simple but effective way to build AND/OR logic into these diagrams.

Your Level 2 AID will be a single Topic in Salesforce Agent Builder. This Topic could be added to a new or an existing Agent

All of this work is required before you add the Topic instructions.

In your process diagram:

Go to the Agent Builder and the Topic. Paste instructions into ONE instruction field. There is no need to paste each instruction into a separate instruction fields.

Every time you start to edit the Level 2 AID, it takes a snapshot of the diagram. Also when you generate instructions it takes a snapshot of the diagram and a copy of the instructions. You can access snapshots in the right panel of the diagram. You can filter for just these snapshots

Testing involves running each test case systematically to confirm whether the agent behaves as designed. If the agent responds as expected, the test passes. However, if something fails, (i.e. if the agent does not behave as intended), it is critical to address the root cause.

Review the Level 2 AID and look at the different paths and create test scenarios. You wll use these to evaluate the agent. This is all about evaluating the logic and probable outcomes from the multiple conversation permutations that can take place in different scenarios. We are developing significant capabilities to enhance the evaluation of Agents in this context. This document (and users) will be updated as we release this critical capability in the near future.

We also generate test utterances for each path to use alongside your analysis of the Level 2 AID.

In your process diagram:

Inside Agent Builder, firstly take your agent through the 'Happy Path'. Keep your questions and statements clear within the bounds of the instructions you have given it, don't try and 'push it'. Take the agent through its activities one at a time, tracking its progress through the process as you go.

Then take the agent through some of the fault paths to evaluate the results.

You need to work out why the agent failed and then how to resolve it. That is made far easier because you have the Level 2 AID:

This iterative process ensures that agent behavior aligns precisely with the designed logic, maintaining clarity and consistency across all steps. And it also helps you keep your design documentation up to date.

Once the topic passes all evaluations, you can deploy your Agent using your chosen Salesforce DevOps tool. You may need to get sign-off from stakeholders and the Level 2 AID makes this easier to explain what the Topic does.

You will need to deploy

And finally activate the Agent in your Production Org.

On top of metadata deployment, use Elements diagram versioning and governance to publish your AIM map. This creates a locked-down version and you can keep working on the "Draft" version of the diagram. (see "Diagram Versions and Publishing new Diagrams" article)

We recommend that the version management is treated as a core deliverable for building Agents. To benefit from it, the AIM content will need to be identified as ongoing operational content that will be handed over to and managed by the end-customer. At the start it may be project or POC stakeholders who are allocated. But even there, "who approved these directions and instructions for the Agent" will be very valuable.

Once in operation, this becomes an operational benefit as the auditable design documentation which is the equivalent of a "Quality Management System" (QMS) for human labor - but applicable to your Digital Labor. The more complex and critical your Agent use cases get, the more valuable this will prove to be for you.

By implementing Agentforce with Elements.cloud, you gain a structured, iterative approach to designing, building, testing, and deploying AI agents. This methodology ensures clear logic, stakeholder approval, and measurable business value while enabling continuous improvement.