Skip to main content
A research monitor is a long-running, natural-language research loop. You describe what you want watched (e.g. “semiconductor sanctions affecting Taiwan markets”) and SimpleFunctions runs the research on a cadence, posts results to your delivery channels, and stores history. This is different from a watch + alert rule, which fires on a structured condition (price threshold, econ release, …). Research monitors are open-ended LLM runs over a topic.

CLI

sf monitor create returns the new monitor and the first run result inline.

API

All routes require Authorization: Bearer sf_live_... or browser session.

POST /api/research-monitors

Body Response 201

PATCH /api/research-monitors/

All fields are optional. Pass only the fields you want to change.

POST /api/research-monitors//run

Returns { ok: <bool>, result: <runResult>, meta: { fetchedAt } }. Failures bubble up as 500 with ok: false so a webhook receiver can retry on transient errors.

Errors

Patterns

Watch a topic, post to Telegram

Programmatic create with webhook

Run on demand from a CI job

See also

Watchlist + alerts

Structured price / econ / gov alerts.

Webhooks

Signed delivery and replay.

Telegram bot

Bridge the CLI to a chat surface.

Direct API access

Auth, base URLs, language examples.