Skip to main content

Episode 3 — Knowledge

Put a fact in and get it back cited — a knowledge entry created on camera, the Indexed badge explained, a record looked up, the crawler's boundary read, and a stale-knowledge trap shown live.

2 min read

The grounded answers of episode 2 all came from one place; this episode works in it. You add a real fact as a knowledge entry, learn what the Indexed badge actually means (and why indexing is not training), look a price up in a typed record, read the crawler's scan interval, open the control that limits a document to one team — and then meet the failure you'll actually hit: not a missing fact, an outdated one. At the end, a fresh chat cites the entry you created minutes earlier.

Episode 3 — Knowledge (5:50, captions available)

What the episode shows

AtScene
0:27The map: Documents, entries, websites, products — one tab row
0:54Entry vs document vs record — picking the right shape
1:18A knowledge entry created live: topic, content, save
1:44What Indexed means — retrieval at answer time, not training
2:11A real lookup in a typed record
2:37The crawler: a domain, a scan interval, an honest boundary
3:09Who reads what: a document assigned to a team
3:41The stale-knowledge trap, asked live
4:35The proof: a fresh chat cites the entry you just created

Where to go next

The knowledge overview maps the whole library; documents covers the indexing pipeline, knowledge entries the curated facts, structured data the typed records, and crawling the websites. For the scope switches, read agent knowledge.

© 2026 Tale by Ruler GmbH — ISO 27001 & SOC 2 certified.

Tale is MIT licensed — free to use, modify, and distribute.