Skip to main content

Documentation Index

Fetch the complete documentation index at: https://docs.dovetail.com/llms.txt

Use this file to discover all available pages before exploring further.

Chat GA Pn

How Chat works

Chat auto-applies context from wherever you are in Dovetail, so you’re always asking the right question at the right scope.
  • Focused analysis: Ask about a specific transcript — including OCR’d documents like academic papers — or a single feedback note.
  • Project synthesis: At project level, ask broader questions across all the data in that project: a meta-study, a round of interviews, a collection of sales calls.
  • Workspace overview: Zoom out further and synthesize across projects — different product areas, research themes, or feedback sources.
Chat responds in the same language you write in, and infers sensible search language from your project and document names, so multilingual teams can work naturally. Here are a few ways to put it to work:
Use caseExample question
Get answers, not summaries”How many enterprise customers mentioned onboarding friction this quarter, and what did they say?”
Segment by what matters”What are churned accounts saying about pricing compared to customers who expanded?”
Validate before you build”What have customers actually said about [feature]? Show me the quotes.”
Uncover what you’re missing”What topics keep coming up across support and sales calls that we haven’t explored in research?”
Brief leadership fast”What are the top three themes across all customer feedback this quarter, with evidence?”

Start a new chat

Open Chat from the sidebar, or press ⌘ J (Mac) / Ctrl J (Windows) from anywhere in your workspace. You can switch to full-page Chat for a larger workspace when you want more room for deeper analysis, then toggle back to the corner view whenever you need. Ask anything — from “How might I improve this conversation next time?” on a single customer interaction to “What are the main VoC themes this month?” at workspace level. The real power is conversational: ask follow-ups, push for nuance, challenge a point, or change direction entirely. Treat it like a dialogue with your research, not a search box. Customer signals don’t exist in isolation. Sometimes you need external context alongside your internal data — what competitors are shipping, how the market is shifting, or which trends explain a pattern you’re seeing. Web search lets you pull in external sources within a single Chat conversation, without leaving Dovetail. Ask Chat to look up a competitor’s latest product announcement, find industry benchmarks, or surface recent coverage tied to a trend in your data. How teams use this:
  • Competitor context — compare what your customers are saying with what competitors are shipping, in one place.
  • External validation — support emerging themes with third-party sources and published benchmarks.
  • Market signals — layer in industry or macro trends to strengthen your interpretation of internal data.
Blog Image Chat

Rich media in Chat

Customer feedback isn’t just text — it’s video. Real moments, real expressions, real frustration and excitement. When Chat surfaces a relevant snippet from customer feedback, it renders the video directly in the conversation. You can watch it inline, right alongside the analysis. When multiple moments are relevant, they appear in a scrollable carousel so you can move through the evidence without losing your place. Each highlight is also downloadable, so you can bring customer moments into presentations or share them with stakeholders in one click. You’re not reading a summary of what a customer said. You’re watching them say it, without leaving the conversation.
Blog Image Chat 736x492

Multi-context: ask one question across multiple sources

You can now @mention multiple sources in a single query — a project, a channel, a specific document, or any combination — and Chat will synthesize insights across all of them in one response, with citations linked back to each source. You can also narrow your scope within a project. Instead of querying an entire project, select specific calls or documents and ask targeted questions about just those inputs. How teams use this:
  • Cross-functional synthesis — combine perspectives from research, support, and sales to understand what’s changing and where to focus next.
  • Focused analysis — isolate a handful of interviews or documents without noise from the rest of the project.
  • Strategic context — pair internal research data with specific strategy documents for more informed answers.
Blog Image Chat 736x492 (1)

View citations

Every answer is grounded in your data. Citations are interactive, with expandable source previews so you can verify exactly where information came from without leaving the conversation.

Transparent thinking

Expand the Show thinking panel to see exactly how Chat arrived at an answer — which sources were scanned, how many interviews were read, what highlights and documents were generated, broken down step by step. Dynamic thinking states show real-time progress as Chat works through your question, so you always know what’s happening. You can also stop a response mid-stream once you have what you need, and Chat will always tell you if citations are still loading or thinking is still in progress.

Create an Agent from Chat

If a conversation surfaces something worth repeating, you can turn it into an agent in one click. Create agent appears at the bottom of a Chat response. Clicking it opens the agent dialog with a prompt already written — so you’re not starting from scratch. How the prompt is generated depends on the conversation:
  • Single question — the prompt is taken directly from your question, as written.
  • Multi-turn conversation — Chat rewrites the prompt to capture the full context of the thread, so the agent understands the intent behind the whole conversation, not just the last message.
From there, you can refine the prompt, configure the agent, and save it — ready to run against your workspace whenever you need it.

Create a doc from Chat

Create a doc directly from Chat by clicking Create doc on any response. The doc lands in your workspace ready to refine — citations link back to their source data, and any video or highlight reels referenced in the response are embedded automatically. Where the doc is created depends on where you opened Chat:
Chat locationDoc is created in
ProjectThat project
FolderThat folder
WorkspaceRoot
Multi-select (first context is a project or folder)That project or folder
Multi-select (first context is anything else)Root

View Chat history

Open Chat, then select Show chat history to see past threads. Conversations are named from what they were about, so you can scan the list quickly. You can view all chat history in the sidebar of full page chat too.
Full Page Chat Figma

How Chat uses metadata

Chat reads metadata across your data. The better structured your workspace — fields filled in, contacts assigned, segments used consistently — the richer the answers.

Who can see what

Chat only searches and cites content your account can already access in Dovetail. It doesn’t bypass permissions.

Share your feedback

Use thumbs up and thumbs down on replies. Feedback goes directly to the Dovetail team to improve Chat.