Agents

AI assistants that use prompts, models, context, and tools to answer questions and take action.

An agent is an LLM with a system prompt, a model, generation parameters, declared input variables, and a set of allowed tools. Unlike a workflow, an agent does not follow a predetermined graph. The model decides which tools to call and in what order based on the conversation.

Agents live at /automation/agents. Each agent has a list view, a configuration/detail page, and a built-in test chat.

Use agents when the main challenge is understanding what the user wants, choosing the right tool, and explaining the result.

User asks

The user sends a message, or another system invokes the agent with context.

Agent chooses

The prompt, model, inputs, and chat history help the agent decide what to do next.

Tools run

The agent calls core tools or workflow tools to search, research, navigate, report, or perform a controlled action.

Answer returns

The agent explains what it found, what it changed, or what the user should do next.

An agent is the interpretation layer. Tools do the actual data access, navigation, research, reporting, or workflow execution.

Agent Anatomy

An agent's configuration covers the pieces that shape how it behaves:

Behavior

System prompt

The agent's operating instructions: what it is responsible for, how it should communicate, when it should use tools, and what it should avoid.

Reasoning engine

Model

The provider and model id. Deprecated models stay runnable until admins explicitly migrate stored agent configurations.

Generation controls

Temperature and max steps

Temperature controls variation. Max steps limits how many tool-call turns an agent can take before stopping.

Context contract

Input variables

Values callers pass in, such as account_id, user_id, or page context. Inputs keep the prompt reusable across records and pages.

Capabilities

Tools

The actions the agent is allowed to take. Tools can be core tools, like search or product help, or workflow tools you expose from your org.

Verification

Test chat

A built-in chat interface runs the agent against real org data and shows tool calls so you can confirm it behaves as expected.

Agent Types

Custom — built in your org for your use case.
Suggested — recommended starting points.
Customized System — a copy of a system agent you've modified.

Agents support tags and folder tags in the unified Automation Library, matching workflow organization.

Choosing Tools

The most important agent design choice is the tool set. Give the agent the smallest set of tools that can solve its job.

Built in

Core tools

Use core tools for product help, record search, report search, web research, navigation, dashboard/report assistance, and other built-in capabilities.

Good for broad assistance
Managed by GTM Engine
Available across many agent surfaces

Your process

Workflow tools

Use workflow tools when the agent should run a repeatable, controlled operation you built in the workflow builder.

Good for real actions
Versioned and inspectable
Uses workflow inputs and outputs

Tool selection rules of thumb:

If the agent needs to answer or look something up, start with core tools.
If the agent needs to perform an operation, expose a workflow as a tool.
If the operation has required business rules, keep those rules in the workflow, not only in the prompt.
If the agent keeps calling the wrong tool, remove tools until only the useful choices remain.

Good Agent Jobs

Page-aware

Forecast assistant

Answer questions about forecast movement, look up risky deals, and route the user to the right records or reports.

Synthesis

Account research assistant

Combine CRM context, recent activity, web research, and saved reports to prepare a rep for a meeting.

Action

Workflow launcher

Ask clarifying questions, identify the right record, then call a workflow tool to run a controlled operation.

Conversational access

Slack or Teams bot

Let users ask GTM questions where they already work, while the agent reaches back into approved GTM Engine tools.

Creation support

Builder assistant

Help users draft prompts, configure workflow tasks, debug variables, and understand tool behavior.

Interactive UI

Guided form helper

Use page context and tools to fill form fields, explain options, and guide the user through a workflow.

Poor Agent Jobs

An agent is not the right primitive when the process should be identical every time.

Use a workflow instead when you need to:

Apply the same transformation to every record in a batch.
Enforce required field mappings or schema validation.
Retry failed records with precise step-level history.
Run from a trigger without a user conversation.
Keep a process stable while you draft future changes.

Where Agents Run

Agents can be invoked from several places:

Inside a workflow as an Agent task.
From the test chat on the agent's configuration page.
From Slack or Microsoft Teams via per-agent chat configuration in integration settings.
From Genie surfaces in the app — the page-context Genie sidebar uses the same agent infrastructure under the hood.

Genie

Genie is the in-app AI assistant that appears as a floating button on authenticated pages. It is not literally one agent. It is a family of page-context agents that share the same core tool catalog. Each page can register its own Genie variant with a tailored system prompt, tool set, and structured page context, such as which account, report, or forecast slice the user is viewing.

The most common Genie surfaces include:

Home Day Planner — generates a strictly prioritized plan for the user's day, drawing on profile, calendar, records, reports, and recent activity.
Page Genies — forecast_page, account_page, outreach_page, generate_accounts_page, etc. Each one knows about its page's data and can call set_form_field to fill UI controls.
Workflow Builder Genie — code-defined agent embedded in the workflow builder. Lives in the codebase rather than the agents table.

Agent vs. Genie vs. Custom Agent

These three terms can blur together. The mental model:

Genie is a label for the in-app, page-context AI experience. Under the hood it is implemented as a set of agents.
Agents is the general term for any LLM + tools + prompt entity, whether it powers Genie, runs in Slack, or is a workflow step.
Custom agent is what you call an agent you build at /automation/agents for your own use case.

Testing

The agent configuration page includes a chat interface that runs the agent against real org data and exposes per-message tool calls. Use it to verify:

The agent understands the kinds of questions users will ask.
It reaches for the tools you expect.
It avoids tools it should not need.
It asks for missing inputs instead of guessing.
It explains actions clearly after a workflow tool runs.

Next Steps

Workflows vs. agents — when to use which.
Workflows — how to build controlled actions agents can call.
Build your first agent — guided walkthrough.
Build a multi-tool agent — combine core tools, workflow tools, and trace inspection.
Use a workflow as an agent tool — compose a conversational agent with a workflow action.