Frontline Studio · Agent Builder · Real product recording

Create an AI agent

Create and configure an operational AI agent from Studio Agent Builder: role, model/provider, instructions, channels, workflows, CRM context, and launch readiness.

Real product recording3 min

Agent Builder visual contextNew agent creation dialog
Use this state to verify the agent role, configuration entry point, and whether the agent is ready to connect to tools or workflows.

Real Studio screen

Follow the real configuration that turns an operation into a system.

These captures favor full, readable product states: agents, workflows, channels, logs, analytics, and publishing controls without floating labels or artificial step boxes.

CloseupAgent name field
Use this state to verify the agent role, configuration entry point, and whether the agent is ready to connect to tools or workflows.

Summary

Create and configure an operational AI agent from Studio Agent Builder: role, model/provider, instructions, channels, workflows, CRM context, and launch readiness.

ProductFrontline Studio

ModuleAgent Builder

CategoryAgent Builder

Concepts covered

Agent BuilderFrontline StudioAI Agents

Step breakdown

Open Agent BuilderStart in Studio and open Agent Builder so you can see the current Sales, HR, Support, and Marketing agents.
Review the agent inventoryCheck each agent's role, live status, owner, creation date, and selected model/provider.
Open Create AgentUse the Create Agent action to start a new AI teammate.
Name the agentChoose a clear operational role name such as Sales Qualification Agent, Support Triage Agent, HR Recruiter, or Marketing Assistant.
Choose model/providerSelect the provider and model for the job. Frontline is model-agnostic, so teams can use supported providers such as Claude, GPT, Gemini, DeepSeek, and others.
Add instructionsWrite the role, operating rules, tone, escalation boundaries, and response format the agent must follow.
Connect channelsDecide where the agent can communicate: WhatsApp, Instagram, Messenger, live chat, Slack, or another connected surface.
Connect workflows and CRM contextAttach the flows, tables, resources, tools, and CRM records the agent needs before publishing it.

About this walkthrough

This Agent Builder lesson uses the live Studio /agents page. It starts from the real Sales, HR, Support, and Marketing agents, then explains how a new agent becomes operational: name, model/provider, instructions, tools, resources, channels, workflows, CRM context, testing, and publishing readiness.

Implementation path

1. Open Studio, then Agent Builder.

2. Review the existing Sales, HR, Support, and Marketing agents so you understand what a production agent looks like.

3. Click Create Agent and name the new role by job, not technology.

4. Choose the model/provider for the job. Frontline is model-agnostic: Claude, GPT, Gemini, DeepSeek, and other supported providers can be selected as they are configured.

5. Add instructions that define role, tone, allowed actions, escalation rules, and output format.

6. Attach knowledge bases, tools, playbooks, tables, and resources.

7. Connect channels only where the agent should communicate.

8. Connect flows and CRM context before publishing.

9. Test with realistic conversations and review Analytics before expanding scope.

How real agents connect to operations

Sales Agent qualifies leads, uses CRM context, triggers lead capture flows, and hands qualified opportunities to Sales.

Support Agent reads customer messages, checks ticket context, drafts safe replies, and escalates risky cases.

HR Agent reviews candidate or employee context against approved criteria and prepares People-team next steps.

Marketing Agent turns campaign or social signals into captured leads, segments, enrichment, and follow-up workflows.

What to validate before launch

Validate selected model/provider, instructions, temperature, reasoning iterations, connected knowledge, tools, playbooks, flows, channels, and CRM permissions.

Then review Conversations and Analytics. If the agent cannot explain or repeat the expected operating behavior, it is not ready for customer-facing work.

Transcript

Open searchable transcript

Agent Builder is the starting point in Frontline Studio. This is where teams create and manage the AI agents that handle operational work. The agent list shows the agents already available in the workspace, including each agent role, live status, owner, selected model or provider, and when it was created. Open a real agent before creating a new one. The overview shows identity, live status, selected model or provider, owner, temperature, and a chat preview. The model shown here is the selected configuration for this agent, not a Frontline limitation. Teams can choose supported providers such as Claude, GPT, Gemini, DeepSeek, and others as they configure the agent. Settings is where the agent becomes operational: instructions, model/provider choice, knowledge bases, tools, playbooks, deployment, and chat customization. Flows connect the agent to real operating paths such as Start and Lead Capture, with triggers, intents, variables, and draft or live status. After reviewing an existing operational agent, return to the inventory and create the next role intentionally. To add another AI teammate, use Create Agent. Studio opens a focused creation dialog without leaving the agent inventory. The first required decision is the agent name. Give it a clear operational role, such as Sales Qualification Agent or Support Triage Agent. This creates the shell of the agent. From there, the next step is configuring its behavior, tools, channels, and workflows.

FAQs

What is an AI agent in Frontline Studio?

An AI agent is a configured teammate with a defined operational role, instructions, selected model/provider, tools, resources, channels, workflow responsibilities, CRM context, and review surfaces.

Is the agent limited to GPT?

No. A screenshot may show GPT-5.4 as the selected model in this workspace, but Frontline is model-agnostic and can support Claude, GPT, Gemini, DeepSeek, and other configured providers.

What is a Frontline agent?

A Frontline agent is an operational AI teammate with identity, behavior, prompts, connected context, channels, flows, conversations, analytics, and permissions.

When should I create a new agent instead of reusing an existing one?

Create a new agent when the operational role, tool access, escalation rules, or expected output is meaningfully different. Reuse an agent when the same job simply needs another workflow entry point.

How should prompts connect to workflows?

Prompts should describe the agent's job and output in a way the next workflow node can use. If a workflow branches on the result, ask the agent for structured values or a clear decision.

What memory should an agent have?

Give the agent the minimum useful memory: approved resources, relevant CRM context, table data, and current workflow state. Too much memory makes behavior harder to test and audit.

How do I test an agent before production?

Test the agent with realistic conversations, missing context, edge cases, escalation scenarios, and expected workflow outputs. Review tone, accuracy, tool use, and handoff behavior.

What permissions should an agent receive?

Give agents only the integrations and actions required for their role. If the agent only drafts or classifies, it may not need write access to external systems.

How do agents connect to channels?

Channels define where an agent can communicate. Use WhatsApp, Instagram, Messenger, or other channels with explicit routing, approved templates, and handoff rules.

How should teams monitor an agent after launch?

Review conversations, analytics, workflow logs, escalation quality, and Max Activity. Monitoring should show both AI quality and the operational outcome the agent supports.