Chat & search experience

In one line. The two ways an end-user asks questions over their documents — conversational Chat (with cited answers) and query-driven Search (ranked results) — and how a builder turns them on. You’ll be able to. Walk a user through asking a grounded, cited question; read every control on the Chat and Search surfaces; and know which builder setting shapes each. Where this lives. Consumer app: the Chat tab and the Search tab. Builder config is in Studio ▸ Experience ▸ Chat and Studio ▸ Experience ▸ Search — see Shaping the experience.

Why it matters

The document pages (Document workspace, Document detail) were about processing documents — extracting fields, moving them through review. This is the other half of the platform: letting people ask questions of a body of documents and get answers back. That is what a Knowledge collection exists for. There are exactly two surfaces for it, and they answer different needs:

	Chat	Search
Shape	A conversation — you ask, it answers, you follow up	A query box — you ask once, you get a ranked list
Answer	A written answer, grounded with citations back to source documents	A list of matching documents/passages, with the best answer highlighted
Best for	“Explain it to me”, “compare these two policies”, multi-step reasoning	“Find me the document that says X”, scanning many hits
Memory	Multi-turn — it remembers the conversation	Stateless per query (but keeps a search history)

Same underlying retrieval; different end-user experience. Teach a user Chat when they want an answer in words, Search when they want to find and open the right document.

Chat

One engine, four places. The platform has one chat engine that surfaces in several containers: the full-page Chat tab, a Project Co-pilot modal launched from the nav, an embedded doc-chat pane on a single document, and a floating agent widget. They share the same controls — learn it once here and you know all four. Piper is the platform-wide assistant and is a separate thing again: it answers across the platform rather than inside one project’s chat.

Layout

CHAT  (Chat tab)
+---------------+----------------------------------------------------------+
| CONVERSATION  |  +- You ---------------------------------------------+   |
| RAIL          |  | Which of our policies cover remote work?          |   |
|  + New chat   |  +---------------------------------------------------+   |
|  Search chats |  +- Assistant ---------------------------------------+   |
|  -----------  |  | Three policies address remote work ... [1][2]     |   |
|  Today        |  |  References:  [1] Remote-Work.pdf p.3             |   |
|   . Remote... |  |               [2] Travel-Policy.pdf p.1           |   |
|   . Leave...  |  |  up / down    copy    speak                       |   |
|  Yesterday    |  +---------------------------------------------------+   |
|   . Expenses  |   Follow-ups:  [ Does it cover contractors? ]            |
|  -----------  |   thinking... 62%   Building... (live steps)             |
|  profile      |  +---------------------------------------------------+   |
|               |  | Ask a question...                          [Send] |   |
+---------------+--+---------------------------------------------------+---+

Conversation rail (left) — + New chat, Search chats, and the history of past conversations grouped by day. A user profile link sits at the foot.
Message thread (centre) — alternating you bubbles and assistant bubbles.
Composer (bottom) — the question box, with Send. On an empty chat it shows suggested/default questions to get the user started.

What every control does

Control	What it does	Notes
Ask a question box	Type a question, press Send	On an empty chat, suggested questions (the project’s default questions) appear above/in the box as one-click starters
Assistant answer	A written, streaming answer	Renders rich content: markdown, tables (with CSV export), charts, code blocks
References chips	Numbered citations — `[1] [2] …` — one per source document	Clicking a chip deep-links into the document at the cited page. This is how chat proves its answer.
Thumbs up / down feedback	Rate an answer	Plus copy and speak (read aloud) on each answer. The builder reads this feedback back in Studio — see below.
Follow-up chips	Suggested next questions	One click asks them — this is what makes Chat conversational.
Regenerate	Re-runs the last question	Use when an answer was weak.
thinking… footer	A sticky status while the agent works	Animated dots plus a progress %/heading. When the agent is running steps, a Building… list replaces the dots and streams each step as it happens, so you can watch the work rather than a spinner.
+ New chat	Starts a fresh conversation	Clears context so a new topic doesn’t inherit the old one.
Search chats	Finds an earlier conversation in the history	History persists per user.
Output / Query toggle	Shows the answer or the underlying query the agent ran	Only when the project enables answer transparency.

Walkthrough — ask a grounded question

Open the Chat tab.
The empty chat shows suggested questions. Either click one, or type your own in the Ask a question box — e.g. “Which of our policies cover remote work?” — and press Send.
Watch the thinking… footer while the agent finds matching passages and composes an answer. If the agent is working through steps, the Building… list shows each one as it completes.
Read the streamed answer. Note the [1] [2] markers and the References block beneath it.
Click a reference chip — the source document opens at the exact cited page so you can verify the claim. This round-trip back to the source is the whole point of grounded chat.
Click a follow-up chip (or type your own) to continue the thread — the assistant remembers what you already discussed.
Give the answer a thumbs up or down. That feedback is recorded for the builder to review.

Behaviours to know

Connection / streaming states. Answers stream token-by-token. If the connection drops you’ll see “Reconnecting…” or “Connection lost — Reconnect”; an unanswered question offers “Try again”. None of this loses your conversation.
Human-in-the-loop. If the agent is set up to pause for a person before it acts, chat shows an approval card with three choices — Approve & Execute, Review (send it back with written feedback), or Reject. You can edit the step’s details before you approve. The conversation resumes once you decide. You only see this on agents that have an approval step; most read-only knowledge agents never do — see Your first agent.
The four containers. The same controls appear in the Co-pilot modal, the per-document doc-chat pane, and the floating agent widget (the only place a user picks which agent to talk to at runtime). If you learned the Chat tab, you’ve learned them all.
It only knows what it was given. A chat agent answers over the Knowledge collections attached on its Knowledge tab — nothing else. No attachment, no answer (see the builder section below).

Search

Layout

Search has two states on the one tab:

Search home — a hero prompt (“Hi there, What Can I Help With?”) with the query box, a Select meta fields picker, a Select a view picker, the Search button, and three prompt-hint cards.
Search results — after you search: the query bar with a Clear control, a “Showing: N of M Results” count, a Search history toggle, the ranked results list (matching passage highlighted, thumbs up/down per result), Refine search, and Load more.

What every control does

Control	What it does	Notes
Search hero	The “Hi there, What Can I Help With?” prompt box	The landing state of the Search tab.
Select meta fields	Choose which extracted fields to search/return	Has Select-All / Unselect-All.
Select a view	Scope the search to a saved View	The same Views a builder defines at `Studio ▸ Data ▸ Views` (Shaping the experience).
Prompt-hint cards	Three example queries	One click runs them — onboarding for new users.
Search button	Runs the query	Switches the page into the results state.
Results list	Ranked matching documents/passages, with the answer-key passage highlighted	Each result deep-links to its document.
Thumbs up / down per result	Vote a result up or down	Tunes relevance / records feedback.
Load more	Pages in the next batch of results	Counts up toward the total “Showing: N of M Results”.
Refine search	Narrow by annotations, keywords, or labels	Layer constraints without retyping the query.
Search history	Re-open a past search	Toggled from the results header.
Clear	Empties the query	Returns you to the hero.

Walkthrough — find the right document

Open the Search tab.
(Optional) narrow the scope: pick a View in Select a view, and/or pick meta fields.
Type a query — e.g. “remote work policy” — and press Search (or click a hint card).
Scan the results list: the matching passage is highlighted in each hit, ranked best-first.
Thumbs-up or down the results to record relevance feedback.
Load more to page further, or Refine search to add a keyword/label constraint.
Click a result to open the source document; reopen earlier queries from Search history.

Behaviours to know

Search reuses Views. “Select a view” is the same View a builder saves at Studio ▸ Data ▸ Views — a Search scope is just a saved slice. (Views sits under Data, not under Search.)
It’s feedback-driven. Per-result voting is first-class here; encourage users to thumb results so relevance improves.

Why the citations are worth clicking. An answer is composed only from passages found in the Knowledge collections attached to the agent, and each citation points back at the passage it came from. A collection that isn’t attached is never read. Nothing is invented in between.

How a builder turns these on

You don’t write code for any of this — you configure it. The essentials, with their home pages:

To do this…	Go to…	Page
Let an agent answer over a corpus	Attach a Knowledge collection on the agent’s Knowledge tab	Your first agent — required, or it has nothing to read
Create the Knowledge collection	`Studio ▸ Data ▸ Collections` — create the collection and choose the Knowledge purpose. It gains an Index Health tab.	Collections & schema
Set default / suggested questions, transparency, feedback	`Studio ▸ Experience ▸ Chat`	Shaping the experience
Configure how Search behaves	`Studio ▸ Experience ▸ Search`	Shaping the experience
Define the Views that scope Search	`Studio ▸ Data ▸ Views` — Views sit under Data, not under Search	Shaping the experience
Show or hide the Chat / Search tabs entirely	A project can turn either tab off. If a colleague has a tab you don’t, ask your administrator.	Shaping the experience

A document becomes answerable once it has been indexed — the Index Health tab on the Knowledge collection shows where each document has got to.

Where the feedback lands. The thumbs-up/down this page keeps collecting is read on the Audit and Feedback tabs of Studio ▸ Experience ▸ Search and Studio ▸ Experience ▸ Chat. Those two tabs are search- and chat-specific. The project-wide record of who did what is a different page: Studio ▸ Governance ▸ Audit & Usage.

Watch out. The single most common “why won’t it answer?” mistake: the Knowledge collection was never attached to the agent’s Knowledge tab. No attachment = no retrieval = a vague, source-less answer. Always check the Knowledge tab first (Your first agent).

Try it yourself

Using a project that already has a Knowledge collection attached (the Policy assistant use case builds one end-to-end):

Open the Chat tab, click a suggested question, and watch it stream.
Click a References chip — confirm it opens the cited document at the right page.
Ask a follow-up chip, then a fresh question after + New chat — notice the second one has no memory of the first.
Give one answer a thumbs down.
Now open the Search tab, run the same question, scope it with Select a view, thumbs-up the best hit, and Load more.
Compare the two experiences: which felt better for “explain it to me”, which for “find the doc”?

Recap

Two surfaces ask questions over documents: Chat (conversational, multi-turn, cited answers) and Search (query → ranked results). Same retrieval, different experience.
Chat gives written answers grounded with citation chips that deep-link back to the source page; it has conversation history, suggested/follow-up questions, thumbs up/down feedback, a thinking footer, streaming/reconnect states, and — on agents that pause for a person — an approval card.
One chat engine surfaces in four containers (Chat tab, Co-pilot, doc-chat, floating widget). Piper is the platform-wide assistant, separate from a project’s chat.
Search offers a hero prompt, View-scoped results, per-result voting, Load more, Refine search, and Search history.
An answer is composed only from passages in the Knowledge collections attached to the agent, and every citation points back at its passage — which is why the citations are worth clicking.
A builder must attach a Knowledge collection on the agent’s Knowledge tab (Your first agent), create that collection at Studio ▸ Data ▸ Collections, define scoping Views at Studio ▸ Data ▸ Views, and tune Chat/Search at Studio ▸ Experience ▸ Chat / Studio ▸ Experience ▸ Search — no code required.

Where to go next

Collections & schema — build the Knowledge collection these surfaces answer over.
Shaping the experience — turn Chat/Search on, set default questions, and define the Views that scope Search.
Your first agent — the Knowledge tab where a corpus gets attached to an agent.
Policy assistant — build chat-over-a-corpus end to end.