Last updated: 2026-08-31 · 2 min read

What is Agent Studio?

Agent Studio is where you design, check, and operate an AI Agent for recurring work without writing code. Describe what you want to achieve in plain language, and Terasu turns it into a proposal for the flow, Room materials, and checks the Agent needs.

A four-step flow from describing a goal to checking and improving an Agent

Create → Evaluate → Deploy → Improve is the safe order. You do not need to enable Room updates, external delivery, or automatic triggers at the start. Begin with an Agent that reads information and makes a proposal, then check the quality.

How this differs from the Room AI Agent

What you want to doWhere to go
Ask about the Room currently openThe AI Agent on the right side of the Room
Build, evaluate, and deploy a reusable AgentAgent Studio

The Room AI Agent is for a conversation in the moment. Agent Studio is for designing, evaluating, and deploying an Agent that can handle a defined job repeatedly.

What each sidebar screen is for

ScreenWhat you decide there
ジャーニー (Journey)Goal, boundaries, and materials to reference
設定と連携 (Connections)Review the built-in capabilities available in the Room and their boundaries
シミュレーション (Simulation)Evaluate results before production use
配備と実行 (Deploy & Run)Choose the Room and how an approved Agent runs
実行レビュー (Run Review)Read and assess one individual run
インサイト (Insights)Check Room-level quality and execution trends
改善キュー (Improvement Queue)Turn system-detected improvement suggestions into a draft

Run Review is where people inspect individual runs. Improvement Queue is where the system proposes changes from repeated patterns. Neither screen publishes a change automatically.

Start with a read-only job, such as turning meeting notes into decisions, open items, and discussion points for the next meeting.

Related articles

What is Agent Studio? | Help center