Glean Cost Tuning

Glean Cost Tuning

Overview

Glean pricing scales with indexed content volume and per-seat user count, making document indexing volume and search query frequency the primary cost drivers. Enterprise deployments typically connect dozens of datasources, each pushing thousands of documents into the index. Without active content governance, stale drafts, archived pages, and near-empty documents inflate the index by 30-50%, driving up costs with zero search value. Pruning irrelevant content and using incremental indexing are the highest-leverage optimizations.

Cost Breakdown

API Call Reduction

class GleanIndexFilter {
  private staleThreshold = 365 * 24 * 60 * 60 * 1000; // 12 months

  shouldIndex(doc: { status: string; updatedAt: number; title: string; content: string }): boolean {
    if (doc.status === 'draft' || doc.status === 'archived') return false;
    if (Date.now() - doc.updatedAt > this.staleThreshold) return false;
    if (doc.title.startsWith('[Template]')) return false;
    if (doc.content.length < 50) return false;
    return true;
  }

  async incrementalIndex(docs: any[], lastSyncTimestamp: number): Promise<any[]> {
    // Only process documents modified since last sync — reduces indexing calls by 80-90%
    const modified = docs.filter(d => d.updatedAt > lastSyncTimestamp);
    const eligible = modified.filter(d => this.shouldIndex(d));
    return eligible.map(d => ({
      ...d,
      content: d.content.slice(0, 50_000) // Truncate to 50KB
    }));
  }
}