Skip to main content

AI Agents

Learn how to use AI Agents inside Factors.

​Agents in Factors are purpose-built AI collaborators designed to automate the most grueling parts of your Go-To-Market (GTM) workflow. Instead of your team manually stitching together data from different silos, Agents handle the heavy lifting — surfacing actionable insights so your reps can focus on high-value engagement.

Today's manual process of account enrichment is fragmented. Teams often bounce between Slack, CRM, and LinkedIn to find context. Agents bridge this gap by delivering the right information to the right person at the exact moment they need it.
​

How to Build Your First Agent

Getting started is straightforward. Navigate to the automation hub to begin:

  1. Select Automations from the top navigation menu.

  2. Click on Agents and select Create Agent.

  3. Enter your specific Agent Instructions to define its goal.

  4. Click Create Agent. Note: you need to publish the agent to access it across the application and via the API.
    ​

Writing Effective Agent Instructions

Agents function by leveraging specific Tools. To trigger a tool within your instructions, use the @ symbol. You can further refine the data by applying filters inside each tool.

Note: When using the Web Research tool, include a clear and specific search query, and explicitly reference it using the @web_research tag.

Factors now supports 13 specialized tools across CRM, web, people, segments, and agent chaining:

Tool

Purpose & Data Provided

@account_profile

Firmographic data and account-level properties for the given domain.

@account_journey

All touchpoints (G2, LinkedIn, ads, website visits, form fills, etc.) for users on a specific domain. Configurable by event names and timerange (Last 7 / 15 / 30 days).

@top_identified_users

Recently active top contacts on your website from the given company, with their properties.

@web_research

Scouts the live web for recent news, funding, hiring, leadership changes, or any specific company update. Pass a clear search query and reference {company_domain} as a placeholder.

@hubspot_company

HubSpot Company properties (CRM-level company records, owner, lifecycle stage).

@hubspot_deal

HubSpot Deal properties (real-time deal stages, amounts, sales history).

@salesforce_account

Salesforce Account properties for the given domain.

@salesforce_opportunity

Salesforce Opportunity properties (stage, amount, close date, owner).

@people_search

Search LinkedIn-based people data for the given company domain — useful for finding decision-makers and building outreach lists.

@champion_finder

Find likely champions or stakeholders at the company by job title (e.g., VP of Marketing, Head of RevOps).

@segments

Returns the list of segments the given domain is currently part of.

@part_of_segment

Checks whether a domain is part of one or more specific segments — useful for conditional logic inside an agent prompt.

@agents

Runs one or more other linked agents for the given domain. Enables agent chaining and multi-agent workflows.

Example: Combine @web_research with @account_journey to build a Pre-call Brief agent that summarizes why an account is spiking and what their recent news is. Or chain a Champion Finder agent into a Pre-call Brief agent using @agents to layer enrichment in stages.
​



Agent Chaining (Multi-Agent Workflows)

The @agents tool lets you treat published agents as building blocks. A parent agent can call child agents and combine their outputs into a single response. This unlocks patterns like:

  • An ICP qualification agent that calls a firmographic agent, an intent agent, and a champion-finder agent, then returns a single GTM-ready summary.

  • A deal-risk agent that pulls @hubspot_deal data, runs a separate competitive-intel sub-agent via @agents, and stitches both into one Slack alert.

To chain agents, reference them by their callable name inside the @agents tool input.
​

Deploying Your Agents

Once published, your Agents become part of your data layer. You can deploy them across five surfaces:

  • Alerts: Get AI-summarized insights delivered directly to Slack or Email when an account shows intent.
    ​

  • Workflows: Use Agent output to trigger automated sequences or CRM updates.
    ​

  • Column Properties: Add Agent-generated data (like "Pain Point Summary" or "Champion Email") as a column in your account views.
    ​

  • Segments and Reports: Build sophisticated audiences and reports based on Agent findings (e.g., "Accounts with recent leadership changes" or "Accounts where a Director-level champion exists").

  • API: Access agent output via the Factors API to build automations outside Factors.

Sample API request:

curl 'https://api.factors.ai/afx/call/deal_won_story_slack_VISWz?domain=domain.com&response=json' \ 
--header 'Authorization: your_token'

Did this answer your question?