Introduction
In Pencil, Custom Agents allow you to scale creative work without losing your brand voice or strategic focus. You might think of them as smart teammates - each with a specialised role, memory and context - ready to be pulled into your workflow whenever needed.
What is a Custom Agent?
A Custom Agent in Pencil is a configurable AI assistant designed to support a specific creative or strategic task. All Custom Agents are defined by:
Instructions: Its core behaviour and tone
Knowledge: Brand-specific or topic-specific context
Capabilities: Tools like web search or file reading
Model: The underlying AI model powering its responses
Agents can work independently or as part of a team or chain in a creative pipeline - depending on your use case.
How do I build a Custom Agent?
Option 1: Duplicate a pre-built agent and adapt it
This is likely to be the fastest way to get started. Choose one of the pre-built Agents and, hovering over it, click the three dots and choose 'Duplicate':
The copied agent will appear at the bottom and hovering will reveal a menu that includes 'Edit':
This is a good way to see how high-performing Agents are configured and adapt them to your needs.
Option 2: Import an agent using an Agent ID
If someone has shared an Agent ID with you (from another workspace or team member), you can import it directly:
Click 'Import Agent' in the top right of the Agents homepage.
Paste the Agent ID into the field.
Click 'Import Agent'.
The Agent will be added to your workspace with all its configuration intact - instructions, knowledge, capabilities, and model settings.
To find and share an Agent ID: Click the three-dot menu (⋯) on any Agent card (on the Agents page or within the Agent's settings) to view and copy its ID.
This is useful for:
Sharing proven Agents across workspaces
Distributing team-wide best practices
Quickly onboarding new workspaces with pre-configured setups
Option 3: Create a New Agent from Scratch
Click 'New Agent' in the top right of the Agents homepage.
Configuring your Agent
Once inside the setup screen, you'll configure:
Name and Description
Choose a clear title that reflects the Agent's purpose
Use the description to help your teammates understand when and why to use it
Model
Select from the available AI models which model will underpin your agent:
Instructions
Define the Agent's behaviour clearly
Example: "Always suggest emotionally resonant headlines that follow this format: [benefit] + [emotional hook]. Reference tone given in Brand Library”
Knowledge & Capabilities
Upload files in the following formats for your Agent to reference, or write/paste plain text.
.pdf
.docx
.pptx
.txt
.csv
various image formats
Web Search: choose whether you want your Agent to be able to access and reference data from the web
URL Access: choose whether you want your Agent to be able to scrape and reference information URLs from any of the source data you have provided
To get the best outcome:
Be clear about the Agent's role (e.g. “concept testing for B2B SaaS landing pages”)
Specify the input context it will need
Mention tone or brand considerations
Clarify output format (e.g. “short headline list with variants”)
How can Custom Agents Access my Brand Library?
Brand library access is not configured in the agent setup. Instead, the Reference brand library settings toggle is available in the Settings panel within any chat, and can be turned on or off at the point of submitting a prompt. This means the same agent can be used with or without brand library influence depending on your needs — useful if, for example, you want to explore more neutral outputs without creating a separate agent for the purpose.
Multiple Agents and Modular Workflows
Multiple Custom Agents can be used powerfully in sequence. For example:
Audience Research Agent ->
Messaging Strategy Agent ->
Headline Generator Agent ->
Scriptwriter Agent
Each Agent builds on the work of the last, bringing its own customised specialism and focus while preserving context across the creative pipeline.
Deployed into the right context, creating a Custom Agent can take minutes, and can save hours.
Start small, test the results, and refine your Agent(s) over time. The more context you give, the better the results.