Recently Updated Pages
Ungoverned-agent policy
On Policy → Ungoverned AI agents you choose what happens when an autonomous AI agent Sentilai doe...
Welcome
Sentilai is the control plane for the AI coding assistants your team already uses. Every request ...
Log retention
How long Sentilai keeps your audit events, findings and any captured prompt content. Where it is ...
Admins, developers and seats
Sentilai has two kinds of people, and they use the product completely differently. Admins Admins ...
The Overview screen
Overview answers one question — is everything all right? — before it offers you anything to do. T...
Your first hour
This is the shortest path from a new organization to a governed request you can see in the consol...
Authenticating to the API
Sentilai's API uses OAuth 2.0 client credentials. You create a credential in the console, exchang...
Blocked conversations
When the classifier stops a conversation, it appears at the bottom of the Policy screen — and thi...
Local MCP decision cache
Policy → Local MCP decision cache (seconds), from 0 to 3600. What it controls When an AI tool cal...
Device sessions
How long a developer's machine may keep working without signing in again. The two settings Policy...
Connection modes
Per tool, whether requests run on the developer's own AI subscription or on your organization's p...
Prompt capture
Off by default, and the setting that deserves the most thought before you turn it on. What it doe...
The prompt-injection classifier
A model, rather than a pattern, judging whether a request is being manipulated. How it runs The c...
Lethal-trifecta enforcement
The one detector that is about a combination rather than a thing. Default: warn. The idea An AI a...
Personal data (PII)
Flags personal data appearing in prompts. Default: report. What it detects Email addresses Intern...
Credential-store reads
Flags an AI agent reading a file that holds credentials into its context — a .env, ~/.aws/creden...
Project configuration that runs code
Flags repositories whose configuration executes code when an AI agent opens them — a core.fsmonit...
Credentials in context
Catches credentials that do not match a known vendor format — internal tokens, database passwords...
Secret scanning
Stops credentials from leaving your organization inside a prompt. Default: warn. This is the dete...
How a policy decision is made
Several things can have an opinion about a single request. This is the order they are consulted, ...