parent_slug, returns the top-level roots (Politics, Business, Technology, etc.). With parent_slug set, returns the direct children of that topic.
To find a topic by name instead of walking the tree, pass query (e.g. artificial intelligence). Exact names rank first, then names starting with it, then names containing it, each by story coverage. With parent_slug set, the search covers that topic’s descendants. The same name often sits under several parents, so read the ancestry before picking a slug. Name search covers topics with at least 5 story clusters; browse with parent_slug for the long tail.
Topic slugs use a parent/child convention (e.g. politics/elections) and let agents browse the hierarchy to find well-named categories. The slugs round-trip into the topic_slug filter on particle_podcast_resolve and particle_podcast_list_guests, and appear on episodes via particle_podcast_get_episode with include: ["topics"].
Inputs
Output
A markdown document with an## Topics (N) heading and a flat bullet list — one bullet per topic, formatted **Name** — slug: <slug> (with — <ancestry> appended when an ancestry path is available). When more pages exist, a horizontal rule and a **Cursor:** <value> line are appended; pass that cursor value back as the cursor input.
Sample (limit=5):
slug: is what you pass back as parent_slug to drill into a topic’s children.
Example
Related
- REST equivalent:
GET /v1/topics. - Feed a topic slug into
particle_podcast_resolve(topic_slug) orparticle_podcast_list_guests(topic_slug).