Run agents
Agents acquire data, reason across sources, and deliver decisions. They close the loop between a Middesk report surfacing a signal and that signal being resolved.
A standard Middesk report might surface an unknown tax ID number (TIN) or a potential watchlist hit. Upon review, you are tasked to investigate each signal: pulling documents, cross-referencing sources, determining the validity or accuracy of a match. Working with an agent, you can delegate the work of reading the report, extracting the signals, and gathering the information necessary to move forward. An agent can manage a team of agents to take the steps necessary to resolve each signal, so that your work shifts from investigation to reviewing the outcome and making a decision.
Understanding agents
Agents have a defined capability to plan, research, and reason, all with the goal to advance operational workflows.
Agents can delegate work to other agents, and on the Middesk platform are classified as two types:
- Orchestrators handle planning, coordination, and synthesis. They determine what work is needed, dispatch agents, and aggregate results to drive action.
- Specialists perform research, analysis, and tool calls within a specific domain.
Which agents are fit to run depends on the use case and nature of the operation.
Executing agents
You interact with agents through the following primitives:
- Agent is a defined set of capabilities. You can list available agents for your account via the API.
- Thread is a container to hold context and history for agent work. Threads commonly are associated with a specific context, e.g. a
business_id. - Run is an individual execution of an agent within a thread.
The above example demonstrates an end-to-end workflow:
The business verification process is initiated and advanced through the Business Lifecycle.
Run an Agent
Next, when the business verification order completes, a Business may need review depending on its review insights. From here, an agent can be dispatched to develop a plan and perform the review.
Viewing agent activity
As an agent performs a run, it maintains a full record of what has been performed and what was found, captured through steps and artifacts. This provides a complete audit trail of the agentâs work.
Steps represent the trail of work the agent performed. Each step captures an individual action, such as researching a data source, analyzing a result, or requesting your input. Steps can be nested, reflecting how an orchestrator delegates to specialists.
Artifacts represent what the agent found. Each artifact is a structured result that includes a confidence score and source references, tracing the finding back to the specific data that informed it.
Together, steps and artifacts give you the context to understand how the agent reached its conclusion and the evidence behind it. For the full response structure, see the Run object reference.
