Admin Console Reference
How this section writes things, and the list of values settled in the admin console. Item names follow the screen. How to choose among them is covered in each guide.
Notation
This service has two screens for administration. In the DevPortal, they are written as below.
| Written as | Which screen |
|---|---|
| admin console | The screen each tenant has, where administrators manage the tenant's users, agents, records and security. Its title on screen is “AGENTIC STAR ADMIN”. This section (Admin) covers it |
| Console | The screen that manages API clients and LLM Gateway keys (Console Guide) |
Sign-in
| Item | Value | Default |
|---|---|---|
| Signing in to the admin console | With a password, an authentication code by email every time. Not asked when signing in with a passkey or SSO | — |
| Self sign-up | Default (current behavior), Enabled, Disabled | Default (behaves as enabled) |
| Password reset | Default (current behavior), Enabled, Disabled | Default (behaves as enabled) |
| Time until login expires without activity | 15 minutes to 24 hours. No longer than the maximum time. Also applies to signing in to the admin console itself | — |
| Maximum time a login can last | 1 to 30 days. Also applies to signing in to the admin console itself | — |
External Auth
| Item | Value | Default |
|---|---|---|
| Enable External Authentication | On, Off | Off |
| Entry ID | Starts with a lowercase letter; 2–64 lowercase letters, digits, hyphens and underscores. Cannot be changed later | — |
| Icon | PNG, JPEG. Up to 512KB | — |
| IdP type | OIDC / OAuth2, SAML 2.0. Cannot be changed later | — |
| Scopes (OIDC) | Separated by spaces or commas | openid profile email |
| Link By | Email, Subject (sub) | |
| Auto Create User | On, Off | On |
| Auto-approval | Don't auto-approve (an administrator approves), Auto-approve only specified domains, Auto-approve everyone | — |
| IdP Claim Value Rules | The source value applies only on an exact match | — |
Network
| Item | Value | Default |
|---|---|---|
| How allowed IPs are written | IPv4, IPv6, CIDR. 0.0.0.0/0 and ::/0 cannot be registered | — |
| Services for an allowed IP | ADMIN, WEB (at least one) | — |
| External API Allowed IPs restriction | On, Off | Off |
| Where Country Restrictions apply | Sign-in, the chat and the admin console. They do not apply to the external integration API or the LLM Gateway. Cannot be split by service | — |
| Country Restrictions rule name | Starts with a letter; letters and digits only, up to 128 characters | — |
| Countries in Country Restrictions | 1 to 10 per rule | — |
| Priority in Country Restrictions | An integer from 100 to 199. Smaller numbers take effect first. Cannot be shared between rules | — |
| Country Restrictions action | Block, Detect only | — |
| Time for Country Restrictions to take effect | About an hour | — |
| Detections in Country Restrictions | Last 30 days | — |
| Ports an agent can connect out on | 443, 80, 8080, 8443, 8000, 3000, 5000, 9000. HTTP and HTTPS only | — |
| Destinations agents can go out to | Destinations matching a banned URL are stopped | All |
Guardrails
| Item | Value | Default |
|---|---|---|
| Prompt attack detection | On, Off | On |
| Harmful content detection sensitivity | Recommended, Lenient, Most Lenient, Disabled | Recommended |
| Personal information masking | On, Off | On |
| Execution time limit | 5, 15, 30, 60, 90 or 120 minutes, or “No limit” | No limit |
| Sensitive terms and exclusions | Up to 200 each | — |
| Length of a sensitive term | Words up to 100 characters, regular expressions (RE2) up to 500 | — |
| Display name of a sensitive term | Up to 50 characters. [, ] and control characters cannot be used | — |
| Length of an exclusion | Up to 100 characters | — |
| Test regular expression | Sample text up to 2,000 characters. Up to 50 matches are shown | — |
| Merge order in Common AI Agent Instructions | 1, 2, 3 | — |
| Organization in Common AI Agent Instructions | Global (all organizations), each organization | Global (all organizations) |
| Reasons for a banned URL | Security, Compliance, Internal Policy, Other | — |
| What Widget Connection Restrictions can register | Deny only (a host name; subdomains are blocked too). Takes effect within about 60 seconds | — |
| Time for Guardrails Settings to take effect | Within a few minutes, from the next request | — |
| Time for Prohibition Instructions (Common AI Agent Instructions) to take effect | Up to 30 minutes | — |
Records
| Item | Value | Default |
|---|---|---|
| Retention | 24 months (Audit Logs, Operation audit logs, AI Agent LLM Usage, Outbound Communication Records, LLM Gateway records) | — |
| CSV export | Audit Logs: no limit. Outbound Communication Records and User action audit: up to 5,000. AI Agent LLM Usage and LLM Gateway records: up to 1,000 | — |
| Conversation Export | JSON, up to 1,000 per export | Without a period, the last 30 days |
| User action audit screen | — | Without a period, the last 30 days |
| SIEM destinations | HTTP push (generic), Microsoft Sentinel, Splunk, AWS CloudWatch Logs | — |
| External SIEM destinations | https only | — |
| Interval for sending to a SIEM | Every minute (records usually arrive in about 1–2 minutes) | — |
| Records you can send to a SIEM | Nine kinds | “User action audit” and “Outbound Communication Records” are not sent; the others are |
| Token header name for SIEM HTTP push | — | Authorization |
| Log stream for SIEM CloudWatch Logs | — | The identifier of the kind of record (such as audit_logs) |
Keeping and sharing conversations
| Item | Value | Default |
|---|---|---|
| Stop shared links (Feature permissions) | On, Off. When on, links already created can no longer be opened (they can still be listed and deleted). Takes effect within 60 seconds of saving. Where the deployment settings turn shared links off, they cannot be turned on from this screen | Off |
| Days before archiving | 30–3650 days. Takes effect from the next archiving run | Blank (the deployment setting) |
| Retention after archiving | 30–3650 days. Once it passes, the conversation and its attachments are deleted and cannot be restored. Anything under legal hold is not deleted | Blank (no limit) |
| Legal hold ID | A project ID is a UUID; a conversation ID is up to 128 characters | — |
Error codes
Errors the external API returns because of admin console settings.
| HTTP status | error.code | When | Setting that decides it |
|---|---|---|---|
403 | ip_not_allowed | External API Allowed IPs is on and the call comes from an address that is not allowed | External API Allowed IPs |
403 | sso_required | In the project external API, a user who did not sign in with SSO performs an operation reserved for SSO users | Letting people in through SSO only |
Administrator types and the screens they can use
| Screen | System administrator | Organization administrator | Auditor |
|---|---|---|---|
| Dashboard | ○ | ○ | — |
| Cross-project KPI and Execution history under Project Management | ○ | ○ (the organizations in their charge) | ○ (view only) |
| Execution rules under Project Management | ○ | View only | — |
| Review requests and Organization projects under Project Management | Only when also an organization administrator | ○ (the organizations in their charge) | — |
| Agent inventory under AI Agents | ○ | ○ (the organizations in their charge) | ○ (view only) |
| Share requests under AI Agents | ○ | ○ (the organizations in their charge; the tenant-wide setting for whether sharing needs approval is for system administrators only) | — |
| MCP Connections under Connections and Usage Scope (for system administrators, “MCP Servers” > the “MCP Connections” tab) | ○ | ○ (only the connections of users and projects in their own organization) | — |
| Audit Logs, Operation audit logs, User action audit, AI Agent LLM Usage and Outbound Communication Records under Records and Audit (among auditors, Outbound Communication Records is for tenant auditors only; Guardrail Alerts and User Evaluations are not shown to auditors) | ○ | — | ○ (view only) |
| “Change Password” in the user menu | ○ | ○ | ○ |
| All other screens (including the settings in these guides) | ○ | — | — |
Organization administrators are set under Users and Organizations, in “Admin Roles” (Roles Reference).