> ## Documentation Index
> Fetch the complete documentation index at: https://docs.forge.shieldtp.com/llms.txt
> Use this file to discover all available pages before exploring further.

# Create a Custom Agent

> Define a narrow recurring workflow, owner, target, output, and success criteria.

The best first version of an agent is narrow enough to test and useful enough that someone will read its output.

## Design the workflow first

Write down:

* **Outcome:** What decision, report, or updated state should exist?
* **Owner:** Who reviews quality and responds to failures?
* **Target:** Organization-wide, selected accounts, or a dynamic group?
* **Inputs:** Which records, files, systems, or prior memory are required?
* **Output:** Narrative, structured fields, a table, or another defined result?
* **Cadence:** On demand or scheduled in the organization's timezone?
* **Boundary:** Which writes, if any, are allowed? When must the agent stop?
* **Success:** How will a reviewer know the run was useful and correct?

## Create the draft

<Steps>
  <Step title="Open Agent Library">
    Choose **New Agent** or the available create action.
  </Step>

  <Step title="Name the job">
    Use a verb and outcome, such as “Review backup exceptions” rather than a department name.
  </Step>

  <Step title="Write the instructions">
    State the workflow, evidence requirements, output format, stop conditions, and what not to infer.
  </Step>

  <Step title="Choose the model">
    Use Fast for routine, well-defined extraction and reporting. Use Smart for workflows with more ambiguity or cross-source reasoning.
  </Step>

  <Step title="Keep it inactive">
    Save the first version as inactive while you configure tools and test.
  </Step>
</Steps>

## A durable instruction structure

1. **Purpose and audience**
2. **Inputs and source precedence**
3. **Ordered workflow**
4. **Tool-use boundaries**
5. **Required output**
6. **Evidence and confidence**
7. **Stop and escalation conditions**

<Tip>
  If two outputs have different owners or failure behavior, they are often better as two agents. Smaller agents are easier to test, permission, and maintain.
</Tip>

Next, [configure the agent](/custom-agents/configure-agent).