What is agent chat? Direct AI agents through conversation
Agent chat is the conversational control surface for real work. Ask a question, attach context, choose an agent and skills, then review the evidence, tool activity, and proposed changes in the same thread.
The concept
A plain-language definition before the product implementation.
Chat is an interface, not the whole agent
A chat message is one way to give an agent a goal. The agent can retrieve approved knowledge, use connected tools, create structured drafts, and operate workflows. The thread preserves the conversation around that work without reducing every output to prose.
How AI Agent uses it
Turn a request into inspectable work
AI Agent chat renders tool traces and structured result cards alongside the conversation. Agents can draft tickets, tables, fields, workflows, and investigations, while actions that change external systems remain reviewable.
Choose the right agent
Direct a specialist or team instead of sending every request to one generic assistant.
Attach live context
Include files, knowledge sources, skills, and connected tools when the request needs them.
Review structured outputs
Inspect drafts and tool results as product objects, not pasted blobs of text.
From idea to a working system.
- 01
Ask
Describe the outcome and attach the relevant context.
- 02
Observe
Follow the agent's tool activity and grounded findings.
- 03
Apply
Review the structured draft or gated action before it changes work.
Keep a person in the loop while the request takes shape
Best for
Interactive investigation, drafting, and planning where a person wants to add context and review structured results as the work develops.
Choose another pattern when
Scheduled or unattended execution. Move stable work into a workflow or autopilot once the conversational path is understood.
Included in AI Agent
The product capabilities behind the idea.
- Agent and skill selection
- File and knowledge attachments
- Streaming tool traces
- Structured drafts and result cards
Frequently asked questions
Keep exploring
Related product guides
Agents
An agent is the reasoning layer: it understands a goal, decides which approved tools to use, and works toward an outcome. AI Agent gives that reasoning a clear operating contract instead of relying on one giant prompt.
Knowledge
Knowledge gives an agent a trusted source set beyond its model training. AI Agent turns approved documents and websites into retrievable context, then records what the run actually used.
Human approval
Human approval puts a deliberate checkpoint between agent reasoning and a consequential action. The agent can prepare the work, while a person decides whether it should be applied.
Build the smallest useful version first.
Start with the agent and one real task. Add workflow control, context, and approvals when the work shows you where they matter.