Skip to main content
Find dialogue lines where a specific person or company is named in podcast transcripts. Use this for the “every line about X” workflow. For dialogue that discusses a topic (paraphrase-tolerant or BM25), use particle_podcast_search_transcripts instead — that one ranks segments by relevance to a free-text query, not by who’s named.

​
Two response modes

format="summary" (default — wide scan). Returns up to limit episodes (reverse-chronological), each with metadata plus the first 10 mention-only lines (just the lines naming the entity, no surrounding dialogue). Use this to see what’s been said across episodes and decide which episodes are worth reading in full. Paginate older episodes with cursor. format="detail" (narrow drill-in). Requires episode_slug. Returns the full mention windows with context_lines of surrounding dialogue around each mention. Pass one slug for a single episode, or up to 10 comma-separated slugs (e.g. episode_slug="all-in-200,all-in-201,all-in-202") to multi-get several episodes in one call. limit/cursor don’t apply.

​
Workflow

  • No specific episode in mind: call format="summary" first to scan, then call format="detail" with the slug(s) of the episodes worth reading in full. For most questions (sentiment, recurring themes, who said what when), summary alone has enough signal and the second call isn’t needed.
  • Already have the episode slug (e.g. user mentioned the episode by name, or you got it from particle_podcast_get_episode / particle_podcast_search_transcripts): skip summary entirely and call format="detail" with episode_slug directly.

​
Inputs

One of person_slug or company_slug is required. Resolve a name to a slug first with particle_person_resolve, particle_entity_resolve, or particle_company_resolve.
FieldTypeRequiredDefaultDescription
format"summary" | "detail"no"summary"Response shape. See “Two response modes” above.
person_slugstringone of—Person slug from particle_person_resolve or particle_entity_resolve (e.g. "sam-altman"). Also accepts a bare entity slug for non-person entities like places.
company_slugstringone of—Company slug, domain, or canonical ID (e.g. "nvidia" or "nvidia.com"). Resolves to the company’s linked entity.
episode_slugstringyes for detail—One slug for single drill-in, or up to 10 comma-separated slugs for a multi-episode drill-in in one call. In summary mode, optional filter to one episode.
podcast_slugstringno—Restrict mentions to a single podcast by slug, ID, or numeric iTunes ID.
roleenumno—Constrain how the entity participates. One of: guest, host, panelist, correspondent, mention.
sincestringno—Only episodes published on or after this ISO 8601 date (e.g. 2025-01-01).
untilstringno—Only episodes published on or before this ISO 8601 date.
context_linesinteger (1–20)no2Surrounding dialogue lines around each mention. Detail mode only — ignored in summary.
limitinteger (1–50)no10Episodes per page. Summary mode only.
cursorstringno—Opaque pagination cursor. Summary mode only.

​
Output

A markdown document with ## Mentions of <Name> (N episodes, format=<summary|detail>) and one ### Episode title section per episode. Each section carries bulleted KV rows: - **Podcast:**, - **Podcast slug:**, - **Published:**, - **Episode slug:**, - **Mentions:**. In summary mode, each episode is followed by a flat bullet list — one bullet per mention, formatted @ <seconds>s **Speaker:** text. When more pages exist, a horizontal rule and a **Cursor:** <value> line are appended; pass that value back as cursor to fetch the next page. In detail mode, each episode is followed by one bullet per mention window (Segment title (TYPE) @ start–end), then indented dialogue lines underneath. The line that actually names the entity has the entire Speaker: text wrapped in bold; surrounding context lines render as **Speaker:** text (speaker label bold, text plain). Sample (summary, person_slug="marc-andreessen", limit=2): 
## Mentions of Marc Andreessen (2 episodes, format=summary)

### The Sunday Interview: Governing Without Accountability …

- **Podcast:** Straight White American Jesus
- **Published:** 2026-05-03T13:15:00Z
- **Episode slug:** the-sunday-interview-governing-without-accountability-silicon-valleys-ideology
- **Mentions:** 5
- @ 719s **Annika Brockschmidt:** And one of the people who really likes to claim that, … Marc Andreessen-
- @ 1098s **Annika Brockschmidt:** I f- I especially find the stuff that Marc Andreessen says out loud into microphones …

### Why Most of What You're Hearing About AI Is Wrong

- **Podcast:** DarrenDaily On-Demand
- **Published:** 2026-05-01T10:00:00Z
- **Episode slug:** why-most-of-what-youre-hearing-about-ai-is-wrong
- **Mentions:** 1
- @ 155s **Darren Hardy:** Marc Andreessen calls it the silver bullet excuse for layoffs driven by pandemic over-hiring.
---

**Cursor:** s.1hwwoMp2yqmPExv6N5kGy5OYdb8kKihxYYWJ
Sample (detail, drilling into one of those episodes): 
## Mentions of Marc Andreessen (1 episodes, format=detail)

### Why Most of What You're Hearing About AI Is Wrong

- **Podcast:** DarrenDaily On-Demand
- **Published:** 2026-05-01T10:00:00Z
- **Episode slug:** why-most-of-what-youre-hearing-about-ai-is-wrong
- **Mentions:** 1
- AI as layoff scapegoat and market incentives (TOPIC_DISCUSSION) @ 140s–183s
    **Darren Hardy:** When Elon Musk bought it, he gutted 80% of the staff …
    **Darren Hardy: Marc Andreessen calls it the silver bullet excuse for layoffs driven by pandemic over-hiring.**
    **Darren Hardy:** So let me be clear about this, okay? AI is not what's killing the job market, yet at least.

​
Example

# Wide scan, then drill in.
Agent calls: particle_podcast_find_mentions {
  "company_slug": "openai", "podcast_slug": "all-in",
  "since": "2025-11-01", "limit": 20
}
            → reads "- **Episode slug:**" rows for episodes worth reading in full
            → e.g. "all-in-200", "all-in-201"

Agent calls: particle_podcast_find_mentions {
  "format": "detail",
  "company_slug": "openai",
  "episode_slug": "all-in-200,all-in-201"
}
            → returns full mention windows with context for both episodes in one call