In Peachdesk, what you see as an agent in the dashboard is called a workflow in the API. They are the same thing тАФ a workflow is the underlying definition, agent is the product name for it.
Anywhere the API says workflow, think тАЬagentтАЭ. Anywhere the API says workflow_definition, think тАЬthe conversation logic inside your agentтАЭ.

тАЛ
The graph model

A workflow is a directed graph тАФ a set of nodes connected by edges. Nodes are the steps in the conversation. Each node has a prompt that tells the LLM what to say and do at that point. Edges are the transitions between nodes. Each edge has a condition тАФ a natural language description of when to move on. The LLM evaluates whether the condition has been met based on the conversation so far.

тАЛ
Node types

тАЛ
Edges and transitions

An edge connects two nodes and fires when its condition is satisfied: Edge configuration transition_speech is optional тАФ if set, the agent speaks it before moving to the next node.

тАЛ
Versioning

Every time you update a workflowтАЩs workflow_definition, Peachdesk saves a new version while keeping the history. The current version is always what runs. Old versions are retained for auditing.

тАЛ
Creating workflows

There are two ways to create a workflow via the API:
  • From a definition тАФ provide the full node/edge graph yourself. Best for programmatic generation.
  • From a template тАФ describe the use case in natural language and Peachdesk generates the initial graph using an LLM. Best for getting started quickly.
See the Workflow Definition Schema for the full field reference.