In this article, we answer the most common questions about Botmaker 3.0, the agentic version of the platform. They are grouped by topic so you can quickly find what you are looking for.
It is the entry point of your project and the coordinator of the entire team of AI Agents. It receives the messages from the channels, converses with the user, and decides which agent should resolve each query. It is the one that holds the voice and the tone, and the only one that talks to the user.
The orchestrator performs a function similar to the Masterbot, but expanded: in addition to routing, it converses, maintains the tone, can combine several agents in a single response, and jump between them as the conversation develops.
Instead of building rigid decision trees, you define goals in natural language and the agent interprets them. The main association shifts from “bot + channel” to “channel + orchestrator,” and you reuse agents and languages without duplicating bots.
No. The agents resolve tasks and return the result to the orchestrator; the one that responds to the user is always the orchestrator.
No. The boxes are the states (steps) that a single agent follows to accomplish its goal. An agent is an agent; its internal steps are not separate agents.
Yes. It can consult more than one agent and synthesize a single response with what each one contributes.
Yes. The orchestrator can jump between agents depending on how the conversation evolves; it does not follow a fixed linear path.
It reads the description (activation) of each agent: a brief natural-language phrase that indicates when it should be used. There is no need to program the routing logic.
No. The relationship is 1:1: a channel is associated with a single orchestrator, so that conversations don't get mixed up. A single orchestrator can indeed have several channels connected.
The email linking is done through Mailbot; then you return to AI Agents to continue with the configuration.
That is determined from the “Tone and style” section of the orchestrator. You can request that it speak a specific language or that it adapt to the language the user writes in: if they write to it in English it responds that way, if they write to it in Spanish it responds in Spanish, and so on. It is not guided by the number's prefix, but by how the user talks to it.
Yes. A single orchestrator can handle different languages, without needing to build one bot per language.
Yes. Agents can be reused across several orchestrators without duplicating them, which avoids redoing processes.
There is no maximum number: an orchestrator can have several agents depending on what you need.
When you want the same team of agents with different behaviors depending on the channel (for example, one orchestrator for Instagram with a relaxed tone and another for email that is more formal), or to separate large areas of your operation.
Not at the moment; it is a planned improvement. In the meantime, configuration is done manually.
By entering the orchestrator and using the pencil that appears next to the title, at the top.
The orchestrator is deleted from the option at the end of its configuration (“delete orchestrator”). An agent is deleted from its profile, next to the workflow view.
Three: instruction (indicate a task in natural language), conditional (open paths based on a condition), and loop (repeat steps over a set of items until a condition is met).
By adding required data in the corresponding state of the workflow. The agent will ask for it in order to continue.
Yes. If you prefer that it ask for them one at a time, conversationally, indicate this in the tone and style of the orchestrator.
You can test a workflow logic in isolation. To test the complete behavior, it is done from the orchestrator.
Documents such as PDF, DOC, XLSX, or TXT, or the URL of a web page.
The upload is processed asynchronously (indexing). The base becomes available to the agent only when its status changes to “ready.”
By re-uploading the source material when it changes, so that the agent always responds with current information.
Integrating is linking the account of an external service to the project (done once). Connecting is enabling that integration within an agent, choosing its actions and describing when to use them.
The agent can report that it cannot complete the action temporarily, because integrations depend on the external service.
An external server from the project's catalog that exposes additional tools for the agents to use.
Not for conversational purposes: the bot has memory and remembers the context automatically. Variables are reserved for integrations and code actions.
Not on its own: memory is per channel. To recognize a person across channels you need an external system (CRM or spreadsheet) that uses a piece of data as an identifier.
No. The ticket is unique and moves along throughout the processes, regardless of which agent participates.
By adding a “route to a human” step in the agent's workflow. It is not automatic: it is configured, and it can be assigned to a user or to a team.
At this stage they participate as a validator or approver within the process; the conversation with the user is still handled from the AI Agent. The functionality is evolving.
They arrive as cards in the tickets section, along with the tickets from previous versions (legacy tickets).
From the Test button in the orchestrator. Testing the orchestrator is equivalent to testing the complete bot. You cannot test an agent separately; you can test a workflow logic in isolation.
In the tester (with “View details” you see which agent it routed to) and in the Executions section. That reasoning is not shown in the conversation the end user sees.
The authorized profiles of the project (for example, those responsible for designing the agents).
By typing the command @reset, which clears the context and lets you start from scratch.
No, they are saved automatically. In addition, several people can edit at the same time in real time.
Not at the moment: the generative model comes preconfigured.
By tokens, the unit with which the model's processing is measured. You can review your consumption in the Products and consumption section, in the generative consumption view, with detail by project, by model, and by function.
With concise designs: a brief tone and style and clear instructions make the model process less information.
Remember to visit our Help Center for further information.