iblai-api-agent-safetylisted

# iblai-api-agent-safety Configure an agent's moderation and safety systems via the API: the moderation and safety enable flags, system prompts, and responses (all saved through the single `settings/` endpoint), plus reviewing and deleting flagged-prompt moderation logs. Use when setting guardrails or auditing flagged content. ## Auth & conventions - **Base URL:** `https://api.iblai.app` - **Header:** `Authorization: Api-Token $IBLAI_API_KEY` on every request. - **Path vars:** `{org}` = `$IBLAI_ORG`, `{username}` = `$IBLAI_USERNAME`, `{mentor}` = the agent's unique id (e.g. `d17dc729-60fd-4363-81a0-f67d9318b03e`). - **Settings writes** go through one endpoint — **PUT** `…/users/{username}/mentors/{mentor}/settings/` with `multipart/form-data` — sending **only the changed field(s)**. - Not connected yet? Run **`/iblai-api-login`** first to populate `IBLAI_ORG`, `IBLAI_USERNAME`, and `IBLAI_API_KEY`. ## Reads - **GET** `https://api.iblai.app/dm/api/ai-mentor/orgs/{org}/users/{username}/mentors/{mentor}/settings/` — load moderation/safety prompts, responses, and enable flags. - **GET** `https://api.iblai.app/dm/api/ai-mentor/orgs/{org}/users/{username}/moderation-logs/?mentor={mentor}&page={n}&page_size={n}&search={q}&target_system={Moderation System|Safety System}&start_time={iso}&end_time={iso}` — list flagged prompts. ## Writes - **PUT** `…/users/{username}/mentors/{mentor}/settings/` — update moderation/safety fields (`multipart/form-data`, send only changed k