Agent Builder overview
Understand Agent Builder as the Studio control center for operational agents: roles, instructions, model/provider choice, workflows, channels, CRM context, conversations, and analytics.
Configure the agent's instructions, model/provider, temperature, reasoning limit, knowledge, tools, playbooks, deployment, and chat behavior here.
How an agent is organized.
Read Overview, Settings, Flows, Conversations, Analytics, and Channels as one agent system: identity, behavior, orchestration, evidence, and publishing.
Use Overview to confirm identity, status, owner, model, temperature, and preview behavior before changing settings or channels.
Check which workflow responsibilities the agent owns: start flows, lead capture, intents, variables, and draft/live flow status.
Confirm where the agent can talk to customers or teammates before routing sample conversations through it.
Configure the agent's instructions, model/provider, temperature, reasoning limit, knowledge, tools, playbooks, deployment, and chat behavior here.
What this screen shows
Agent Builder is the roster of AI agents inside Studio. Each card shows the operational role, model, live status, owner, and creation date.
Use the roster to answer the first product question: do we already have an agent for this job, or do we need a new role?
How to read an agent
An agent is more than a prompt. It has identity, instructions, model settings, knowledge, tools, deployment state, flows, conversations, analytics, and channels.
Open Overview first to confirm you are editing the right agent. Then use Settings for behavior, Flows for conversation paths, Channels for exposure, Conversations for evidence, and Analytics for monitoring.
Useful role examples
Sales Agent can answer lead questions, check deal context, qualify interest, and hand off to a pipeline workflow.
Support Agent can triage customer messages, check ticket context, reply when safe, or escalate to a teammate.
Marketing Agent can turn campaign or social signals into lead capture, segmentation, and follow-up workflows.
HR Agent can screen candidate or employee context against approved criteria and prepare handoff tasks.
What to inspect before launch
Before an agent affects customer-facing work, inspect owner, status, model, instructions, allowed tools, knowledge bases, connected flows, channel exposure, and the expected handoff path.
Keep the first production scope narrow: one job, one flow, one channel, and a clear review path.
Recommended setup order
1. Create or choose the agent role.
2. Configure Settings: instructions, model, temperature, knowledge, tools, deployment, and chat customization.
3. Add or review Flows so the agent has structured paths for questions, variables, and handoff.
4. Connect Channels only after behavior and flows are testable.
5. Monitor Conversations and Analytics after launch.
Troubleshooting
If behavior is wrong, start from the evidence: the preview conversation, a real conversation, or the workflow run. Then check instructions, available context, tools, channel state, and routing.
Change one thing at a time. Re-test with the same prompt or event before expanding the agent's permissions.
FAQs
What is Agent Builder in Frontline Studio?
Agent Builder is the Studio control center for creating, configuring, testing, and operating AI agents that can participate in workflows, channels, CRM-backed work, and teammate handoff.
Is Frontline tied to GPT models only?
No. Frontline is model-agnostic. A workspace may show GPT-5.4 as the selected model for a specific agent, but the operational model choice can support Claude, GPT, Gemini, DeepSeek, and other providers as they are configured.
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.