BuildFeed

Full-text search over BuildFeed's curated AI/startup/VC YouTube video library. Scores videos by keyword match across title, topics, TLDR summary, channel name, and key takeaways, ranked by relevance (then recency). Use this when the user asks about a specific topic, person, product, or company and you need to find relevant videos with summaries — not when you just want to browse everything (use list_videos for that instead).

{
  "type": "object",
  "properties": {
    "query": {
      "type": "string",
      "minLength": 1,
      "maxLength": 200,
      "description": "Search keywords, e.g. \"Claude agents\", \"seed fundraising\", \"Figma design systems\"."
    },
    "category": {
      "type": "string",
      "enum": [
        "AI",
        "VC",
        "Startup",
        "Product",
        "Design",
        "Tools"
      ],
      "description": "Restrict results to one category: AI, VC, Startup, Product, Design, or Tools."
    },
    "since": {
      "type": "string",
      "minLength": 8,
      "maxLength": 40,
      "description": "Only videos published on or after this ISO 8601 date (reads the archive index)."
    },
    "limit": {
      "type": "integer",
      "exclusiveMinimum": 0,
      "description": "Max results to return (default 20, hard cap 50)."
    }
  },
  "required": [
    "query"
  ],
  "additionalProperties": false,
  "$schema": "http://json-schema.org/draft-07/schema#"
}

Search inside transcript passages, returning the most relevant timestamped excerpts across multiple videos. Use this for evidence, quotations, implementation details, or questions whose answer may not appear in a title or summary.

{
  "type": "object",
  "properties": {
    "query": {
      "type": "string",
      "minLength": 2,
      "maxLength": 200
    },
    "category": {
      "type": "string",
      "enum": [
        "AI",
        "VC",
        "Startup",
        "Product",
        "Design",
        "Tools"
      ]
    },
    "topic": {
      "type": "string",
      "enum": [
        "ai-agents",
        "language-models",
        "rag-and-search",
        "model-training",
        "ai-coding",
        "developer-tools",
        "software-architecture",
        "no-code-and-automation",
        "product-strategy",
        "growth",
        "design-systems",
        "ux-and-research",
        "fundraising",
        "company-building",
        "go-to-market",
        "markets-and-investing",
        "enterprise-ai",
        "robotics",
        "hardware",
        "security-and-privacy"
      ]
    },
    "contentType": {
      "type": "string",
      "enum": [
        "Analysis",
        "Tutorial",
        "Interview",
        "Demo",
        "Review",
        "News",
        "Case Study"
      ]
    },
    "audience": {
      "type": "string",
      "enum": [
        "Investor",
        "Founder",
        "Builder",
        "Product",
        "Designer",
        "General"
      ]
    },
    "limit": {
      "type": "integer",
      "exclusiveMinimum": 0,
      "maximum": 20
    }
  },
  "required": [
    "query"
  ],
  "additionalProperties": false,
  "$schema": "http://json-schema.org/draft-07/schema#"
}

Get a bounded transcript window for one video. Prefer search_transcript_passages for discovery; use this tool to inspect surrounding context after selecting a video.

{
  "type": "object",
  "properties": {
    "videoId": {
      "type": "string",
      "pattern": "^[A-Za-z0-9_-]{11}$"
    },
    "startSeconds": {
      "type": "number",
      "minimum": 0
    },
    "endSeconds": {
      "type": "number",
      "exclusiveMinimum": 0
    },
    "maxChars": {
      "type": "integer",
      "minimum": 500,
      "maximum": 20000
    }
  },
  "required": [
    "videoId"
  ],
  "additionalProperties": false,
  "$schema": "http://json-schema.org/draft-07/schema#"
}

List curated BuildFeed videos, optionally filtered by category and sorted by recency, views, likes, or quality score. Returns compact video records (title, channel, categories, view/like counts, quality score) without transcript or description text. Use this to browse recent/top videos; use search_videos instead when looking for a specific topic.

{
  "type": "object",
  "properties": {
    "category": {
      "type": "string",
      "enum": [
        "AI",
        "VC",
        "Startup",
        "Product",
        "Design",
        "Tools"
      ],
      "description": "Restrict to one category: AI, VC, Startup, Product, Design, or Tools."
    },
    "sort": {
      "type": "string",
      "enum": [
        "recent",
        "views",
        "likes",
        "quality"
      ],
      "description": "Sort order: recent (default), views, likes, or quality."
    },
    "since": {
      "type": "string",
      "minLength": 8,
      "maxLength": 40,
      "description": "Only videos published on or after this ISO 8601 date. Searches the full archive; videos outside the rolling cache have qualityScore 0 and commentCount 0."
    },
    "limit": {
      "type": "integer",
      "exclusiveMinimum": 0,
      "description": "Max videos to return (default 20, hard cap 50)."
    }
  },
  "additionalProperties": false,
  "$schema": "http://json-schema.org/draft-07/schema#"
}

Get full detail for a single BuildFeed video — description, channel info, stats, categories, topics, TLDR, and key takeaways (the raw transcript text itself is excluded). Accepts either an 11-character YouTube video ID or a BuildFeed article slug. Use this after search_videos/list_videos to drill into one specific result.

{
  "type": "object",
  "properties": {
    "id": {
      "type": "string",
      "minLength": 1,
      "description": "YouTube video ID (11 chars, e.g. \"dQw4w9WgXcQ\") or a BuildFeed article slug."
    }
  },
  "required": [
    "id"
  ],
  "additionalProperties": false,
  "$schema": "http://json-schema.org/draft-07/schema#"
}

List YouTube channels tracked by BuildFeed, with per-channel video counts and categories, sorted by video count descending. Use this to discover which creators BuildFeed covers, optionally filtered to a category.

{
  "type": "object",
  "properties": {
    "category": {
      "type": "string",
      "enum": [
        "AI",
        "VC",
        "Startup",
        "Product",
        "Design",
        "Tools"
      ],
      "description": "Restrict to channels that have published in this category."
    },
    "limit": {
      "type": "integer",
      "exclusiveMinimum": 0,
      "description": "Max channels to return (default 20, hard cap 50)."
    }
  },
  "additionalProperties": false,
  "$schema": "http://json-schema.org/draft-07/schema#"
}

List all of BuildFeed's video categories (AI, VC, Startup, Product, Design, Tools) with the number of videos in each. Use this to understand the taxonomy before filtering search_videos/list_videos/list_channels by category.

{
  "type": "object",
  "properties": {},
  "$schema": "http://json-schema.org/draft-07/schema#"
}

List canonical topic clusters from the full BuildFeed archive, grouped into stable families such as AI & Models, Building, Product, Startups, and Industry. Returns video counts, aliases, content-type distribution, and audience labels.

{
  "type": "object",
  "properties": {
    "group": {
      "type": "string",
      "minLength": 1,
      "maxLength": 50,
      "description": "Optional exact topic family, e.g. \"Building\" or \"Startups\"."
    },
    "minVideos": {
      "type": "integer",
      "minimum": 0,
      "description": "Only return clusters with at least this many videos."
    },
    "limit": {
      "type": "integer",
      "exclusiveMinimum": 0
    }
  },
  "additionalProperties": false,
  "$schema": "http://json-schema.org/draft-07/schema#"
}

Get aggregate statistics for the entire BuildFeed corpus: total videos, channels, categories, topics, and views; the published-date range; and transcript/TLDR enrichment coverage. Use this for high-level "how much data / how fresh" questions rather than per-video detail.

{
  "type": "object",
  "properties": {},
  "$schema": "http://json-schema.org/draft-07/schema#"
}

Get BuildFeed's weekly roundup content. Without a date, returns the index of available weekly roundups (most recent first) — useful for discovering which weeks exist. With a date (YYYY-MM-DD week key), returns that week's full roundup detail. Use this for "what happened this week" or historical week-by-week summary questions.

{
  "type": "object",
  "properties": {
    "date": {
      "type": "string",
      "pattern": "^\\d{4}-\\d{2}-\\d{2}$",
      "description": "ISO date (YYYY-MM-DD) identifying a specific week. Omit to list available weeks."
    },
    "limit": {
      "type": "integer",
      "exclusiveMinimum": 0,
      "description": "When listing weeks (no \"date\" given), max entries to return (default 20, hard cap 50)."
    }
  },
  "additionalProperties": false,
  "$schema": "http://json-schema.org/draft-07/schema#"
}