Studio

Everything, glued together in one place.

Studio is where your team connects its systems, models the business once, and builds the agents and automations that run on it. Changes reach production only when you say so.

01·Connections

Connect each system once, for every environment.

A connection keeps its own settings for test, staging, and production, and Studio tests all three from one screen. A saved key is never shown again.

02·Business model

Model the business in its own terms.

A dataset is a saved query on a connection. Map it to a business object such as Case or Household, and every agent that reads it reads the same rows.

Studio · DatasetsProduct
A dataset in Studio: a query reads a cases table, and the inspector shows its connection, the UAT environment, and its mapping to the Case business object.A dataset in Studio: a query reads a cases table, and the inspector shows its connection, the UAT environment, and its mapping to the Case business object.
A saved query on a support database, mapped to the Case object in staging.

03·Lineage

Trace any agent back to the systems it reads.

When someone asks where an answer came from, open the map. It traces each agent back through every business object and saved query to the system the data came from, so the question takes a minute instead of a meeting.

04·Agents and tools

Build agents on your business, with the tools you allow.

Give each agent a role, the data it may read, and its tools, including routines published from Scan. Try it in a sandbox, then publish a version to one environment.

How Scan records a routine
Studio · Agents
Creating an agent in Studio: a name, a role, and the runtime it uses in production and in testing.Creating an agent in Studio: a name, a role, and the runtime it uses in production and in testing.
Name an agent, give it a role, and choose its runtime.
Studio · Tools
The Tools page in Studio: tools connect agents with other systems, and an agent run figure shows each tool next to the agent's skills.The Tools page in Studio: tools connect agents with other systems, and an agent run figure shows each tool next to the agent's skills.
Every agent run shows the tools it called. In preview, MCP lets outside AI assistants call your agents too.

05·Automations

Run queries and agents on a trigger.

Build a workflow on a canvas from webhooks, schedules, queries, agents, and conditions. Then test it. Each step lights up as it runs, and every version is kept.

06·Runs and production

Every run recorded. Production waits for you.

Each run keeps who started it, where it ran, every step with its timing, and its cost. A change in production asks you to type the environment's name first.

Security in detail
Studio · Production
A production confirmation: typing PROD confirms a change in the production environment. A production confirmation: typing PROD confirms a change in the production environment.
Studio · Run
A dataset run in Studio: it succeeded in UAT in 91 milliseconds, with five recorded steps, their timings, and an event log.A dataset run in Studio: it succeeded in UAT in 91 milliseconds, with five recorded steps, their timings, and an event log.
Every run keeps its steps, their timings, and an event log.

Start with one source and one agent.

We'll connect one source in staging and map it with you. The first agent you build on it is timed from its very first run.