# How to configure a Digital Worker

### Overview

Configuring a Digital Worker involves defining its instructions, attaching the tools and skills it needs, setting up the triggers that initiate its activity, and adjusting runtime settings that control how it reasons and behaves. All configuration happens in the test environment against the draft version of the worker. Changes accumulate in the draft until the worker is ready to be evaluated and promoted to production.

### Instructions

Instructions are the foundational configuration layer of a Digital Worker. They define the worker's purpose, persona, constraints, and approach, including what it is for, how it should respond, and what it should not do. Everything else the worker does operates within the boundaries set by its instructions.

Instructions can be used to define the worker's role and tone, provide context about its purpose, establish guardrails that limit what it discusses or acts on, guide how and when it uses specific tools, define the structure or format of its outputs, and provide examples of expected responses to improve consistency for complex tasks.

Instructions are entered and edited in the Compose area of the Digital Worker workspace.

### Tools

Tools give the Digital Worker the ability to act, retrieving information, executing operations, and interacting with external systems. After instructions are defined, tools are attached to extend what the worker can do beyond language reasoning alone.

Tools are added from the Tools section of the Digital Worker workspace. Users can browse available tools by category, search across all tools, or reference examples of tools already in use by other Digital Workers in the same workspace. For more detail on tools and how they work, see the Tools article.

### Skills

Skills extend the Digital Worker's reasoning by providing reusable, domain-specific capabilities, including prompt templates, reasoning frameworks, and structured task patterns that improve the consistency and quality of the worker's outputs for complex tasks. For more detail on skills and how they work, see the Skills article.

### Triggers

Triggers define when the Digital Worker activates. A worker can be initiated by a user interaction, an incoming event, an API call, or a scheduled condition. Triggers connect the worker to the operational context it needs to act in and are configured in the Compose area alongside instructions, tools, and skills.

### Connectors

Connectors provide the authenticated access to external systems that integration tools rely on. If a tool requires access to an external platform, the relevant connector must be configured before the tool can operate. For more detail on connectors, see the Connectors article.

### Runtime Settings

Runtime settings control how the Digital Worker processes requests and manages its behavior during execution. The following settings are available.

**Agent type:** Sets the reasoning capability of the worker, ranging from chat through to advanced reasoning. The appropriate type depends on the complexity of the tasks the worker needs to handle.

**Reasoning effort:** Controls the depth of reasoning the worker applies before producing a response. Low effort favors speed and is suited to straightforward tasks. Medium is the default and appropriate for most use cases. High effort encourages deeper reasoning for complex, multi-step tasks and increases latency and cost accordingly.

**Verbosity:** Controls how detailed or concise the worker's responses are. Low produces short, minimal answers. Medium is the default and suited to general use. High produces detailed, thorough replies.

**Human-in-the-loop (HITL):** Defines when and how a human is brought into the worker's workflow. This setting configures which channel human review or approval messages are sent through, and whether messages are sent always or only when approval is required.

**Reflection:** When enabled, the worker evaluates its own outputs at each stage of plan execution before proceeding. This can improve output quality for complex tasks but may increase response time. Disabled by default.

**Concurrent processing:** When enabled, the worker can process multiple tasks simultaneously rather than sequentially.

**API access:** When enabled, exposes an API endpoint that allows the Digital Worker to be called directly from external systems.

<br>


---

# Agent Instructions: Querying This Documentation

If you need additional information that is not directly available in this page, you can query the documentation dynamically by asking a question.

Perform an HTTP GET request on the current page URL with the `ask` query parameter:

```
GET https://kb.theloops.io/agenticstudio/resource-library/hidden-managing-digital-workers/how-to-configure-a-digital-worker.md?ask=<question>
```

The question should be specific, self-contained, and written in natural language.
The response will contain a direct answer to the question and relevant excerpts and sources from the documentation.

Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.