SecondStack is self‑hosted today: it runs on your own servers, and every chat, file and agent run stays in your own database. What goes out to an AI provider is checked first, with personal data and secrets masked by the rules you set.
SecondGuard, the guardrails inside the gateway, swaps personal data and secrets for placeholders before a request leaves. The real values come back in the answer, on your side.
Approve invoice 4471 from Meridian Legal, paid by card [CARD_1], contact [EMAIL_1], amount $12,300.
Approve invoice 4471 from Meridian Legal, paid by card •••• 4455, contact j.ortiz@meridian.example, amount $12,300.
Each agent reaches only what it was given, and none of them ever holds a password. Its owner or an admin can pause it, any time.
Credentials stay in a separate egress proxy, which adds them to each call: the agent gets the result, never the password.
Who may call, train or manage an agent is set per person, team or the whole organization, and a deny beats any allow.
Each run of each agent writes the same eight lines: what started it, what it could reach, what left and what it cost. Administrators can read the record but not edit it. It holds what ran; the chat itself stays in your own database.
Example run. Names and numbers are illustrative; the lines are the ones the platform records.
Where it runs, where data lives, who signs in and what is recorded.
The same platform, seen from another team
On the demo call we show how it would run as a named agent and what its record in ControlTower would show. You decide whether that is enough.
or email hello@secondstack.ai
