FAQ
Questions, answered.
Ownership, security, timelines, what happens if you leave. The straight answers, before you book anything.
You do. The prompts, the schemas, the retrieval setup, the integration code. You can keep us running it, or take the keys and run it in-house. We document either way.
A working version in your sandbox at week three is the norm. Live with real users between week three and four for a first build. Bigger systems take longer; we tell you that in the assess call.
Your data stays in systems you control. We use providers with zero-data-retention modes (OpenAI, Anthropic) and host on infrastructure you approve: your AWS / GCP / Azure, or our managed setup. Nothing is used to train anything. SSO, audit logs and role-based access are standard on the software around the agent.
Whatever you already run. Calendars (Google, Microsoft), CRMs (HubSpot, Salesforce, Pipedrive), comms (Twilio, WhatsApp, Slack, email), data (Postgres, Snowflake, BigQuery), and your own APIs. If it has a public API or a webhook, we wire it in. If it does not, we usually find a path.
Every build comes with a written handover doc, a runbook and access to all the underlying accounts. The codebase lives on your GitHub from week one. You can take it in-house any month. No exit fee, no hostage code.
Yes. Some clients come for the agent and stay for the software around it. Some come for software outright: internal tools, dashboards, web apps, integrations. Same studio, same team, same engagement model.