Copper Agent

Give an AI agent access to your Copper CRM data inside a workflow, so it can look up records, summarize account context, or make changes on your behalf. Reach for it when a step needs judgment instead of a fixed field mapping.

What It Does

Runs an AI agent with tool access to your connected Copper account. Based on the instructions you write, it can search companies, people, opportunities, leads, and projects; fetch specific records and pipelines; create or update records; add notes; and summarize what it found or did back into the conversation.

When To Use It

Use it whenever a workflow needs to read or write Copper data based on instructions rather than a fixed field-by-field mapping, such as "find the Copper opportunity tied to this deal and update its stage" or "summarize this company's Copper history before the call." Pair it with the Copper Trigger so a change in Copper can kick off a workflow that uses this agent to take the next action.

Configuration

Configure the node with these settings:

Field	What it controls
Related object type	`meeting`, `calendarEvent`, `person`, or `company`. Sets what kind of record the agent receives as background context. Defaults to `meeting`.
Related object	The specific record to use as context. All information tied to it is passed to the agent.
Agent prompt	Required. Tell the agent what to search for, summarize, or change in Copper.
Show user's message	Off by default. Turn on to show your prompt text in the conversation.
Show completion	On by default. Shows the agent's response in the conversation.
Model	Which LLM answers the prompt. Defaults to `claude-sonnet-4-5`. OpenAI models are not supported and are switched to an Anthropic model automatically.
Max steps	How many tool call steps the agent can take before it must respond. Defaults to 20, which is also the maximum.
Chat title	Optional. Name for the created conversation. A title is auto generated if left blank.

Outputs

The node passes these values downstream. Check the Outputs tab on the configured node to confirm exact paths.

Variable	Type	Description	Example
`conversation`	`object`	A reference to the conversation where the message was sent	`{{nodeId.conversation}}`
`conversation.id`	`string`		`{{nodeId.conversation.id}}`
`conversationLink`	`string`	A clickable link to the created conversation in AskElephant	`{{nodeId.conversationLink}}`
`aiCompletion`	`string`	The LLM completion that was sent to the conversation	`{{nodeId.aiCompletion}}`

Example Workflow

After a sales call, an agent reads the meeting context, looks up the matching Copper opportunity, adds a note summarizing the call, and posts the summary back to the conversation.

Copper Trigger
On HubSpot Object Event
Universal Agent

Need More Help?

Reach the AskElephant support team by:

clicking the Support tab on the right side of your screen,
emailing [email protected],
or using @askelephant support in your dedicated Slack channel.