iblai-api-agent-create

Create a brand-new agent from a template. This is the step before configuring an agent: it mints a new agent and returns its unique_id, which you then hand to the /iblai-api-agent-* skills (settings, llm, prompts, datasets, …) to configure further. To duplicate an existing agent instead of starting from a template, use /iblai-api-agent-setting (fork).

Auth & conventions

• Base URL: https://api.iblai.app
• Header: Authorization: Api-Token $IBLAIAPIKEY on every request.
• Path vars: {org} = $IBLAIORG, {username} = $IBLAIUSERNAME.
• Not connected yet? Run /iblai-api-login first to populate IBLAI_ORG,

IBLAIUSERNAME, and IBLAIAPI_KEY.

Reads

• GET https://api.iblai.app/dm/api/search/orgs/{org}/users/{username}/mentors/ — list existing agents in the org (useful to pick a fork source or confirm names are free).
• GET https://api.iblai.app/dm/api/ai-mentor/orgs/{org}/users/{username}/mentor/categories/ — category options (to assign after creation via /iblai-api-agent-setting).

Writes

• POST https://api.iblai.app/dm/api/ai-mentor/orgs/{org}/users/{username}/mentor-with-settings/ — create a new agent from a template (returns the created agent with its unique_id):

``json { "templatename": "string (required, e.g. ai-mentor)", "newmentorname": "string (required)", "displayname": "string", "description": "string", "systemprompt": "string", "llmprovider": "string" } ``

Example

Create a data-science agent from the default ai-mentor template, then capture its unique_id for follow-up configuration:

curl -X POST \
  "https://api.iblai.app/dm/api/ai-mentor/orgs/$IBLAI_ORG/users/$IBLAI_USERNAME/mentor-with-settings/" \
  -H "Authorization: Api-Token $IBLAI_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "template_name": "ai-mentor",
    "new_mentor_name": "Data Science Tutor",
    "description": "Helps users with statistics and Python."
  }'
# → response includes "unique_id"; use it as {mentor} in the other skills

Notes

• template_name defaults to ai-mentor on most orgs; the create call accepts

any template the org exposes.

• Creation is intentionally minimal — set only name + a couple of fields here,

then drive the rest with the focused skills: /iblai-api-agent-setting, /iblai-api-agent-llm, /iblai-api-agent-prompt, /iblai-api-agent-dataset, /iblai-api-agent-tool, etc., using the returned unique_id as {mentor}.

• To copy an existing agent rather than start from a template, use the fork

endpoint in /iblai-api-agent-setting.

• End-to-end example: the iblai/quickstarts

Python client wraps these calls — create an agent, open a session, and chat with it from a script (see also /iblai-api-agent-session for the chat transport).

Reference material

Doc-sourced material preserved from the developer docs:

• [references/quickstart.md](references/quickstart.md) — the iblai/quickstarts Python client outlined: env vars and the create-agent → open-session → chat-over-WebSocket flow, with the runnable client (quickstart.py + api.py) preserved in [assets/](assets/).
• [references/agent-file-format.md](references/agent-file-format.md) — the .iblai Markdown agent-file format (iblai/standard pointer).