Retrieved Context Chunks
The RAG debugging surface: ranked passages with similarity as a meter, matched spans in real mark elements, and filter chips wired as a radiogroup so arrows move between them.
All blocksAI Interfaces
Retrieval & Context
9 blocks in this category, each rendered live below. Open any of them for the full source and a copy button.
A block is one finished section of a page — a pricing table, a hero, a footer.
Answer Source Citations
The published footnotes under an answer — ordered list, real cite and time elements, the claim each source supports, and a staleness warning written in words rather than shown as an amber dot.
Knowledge Source Picker
Choosing what the assistant may read, with indexing state told honestly — a half-indexed source says so rather than showing a green tick — and the footer stating the effect of the selection, not its cardinality.
Nothing Found, Answered Honestly
The refusal screen: says plainly that nothing was found, shows where it looked and the near-misses below threshold, and offers the two real ways out instead of inventing an answer.
Context Window Budget
What is in the context and what fell out of it — a stacked budget with the reply reserve drawn as a segment, and the dropped chunks named with the reason, which is the part nobody ships.
Index Freshness Panel
A green tick means the connector works, not that the answers are current. Freshness as an age in words per source, the headline taken from the stalest one, and a failed sync that still says what age it is answering from.
Retrieval Freshness List
Retrieved sources ranked by how stale they are, because a confident answer from a two-year-old document is the failure people do not catch.
Context Scope List
Which sources this answer may draw on, shown as a scope the user can read before asking rather than a citation list after.
Grounding Split
How an answer is tied to its sources, and what the system does when it cannot find any.