Chat & Ask (for hosts)
On this page
Ask is your interactive deep-dive into a project. You type a question in plain language and dembrane answers from the conversations you’ve collected, pointing back to where each part came from. It doesn’t replace reading transcripts - it helps you find what’s worth reading. The answers come from your participants; the model’s job is to find and organise what they said, with receipts.
The full mechanics live in the canonical Chat & Ask reference.
Run a good deep-dive#
The pattern that works: start broad, then zoom in, then ask for evidence.
- Click Ask question (or New chat) in your project.
- Start broad: “What are the main themes?”
- Zoom in: “What concerns came up about the bus route?”
- Ask for evidence: “Show me the quotes.”
Each chat is a thread - read the answer, then follow up: “say more about the second point”, “who said that?”, “now just the under-30s”. Old chats stay in your history. This is the right tool for comparing viewpoints, finding quotes, or testing a hunch.
Choose a mode#
When you start an Ask you pick a mode, and the mode decides how dembrane reads your conversations.
- Overview (beta) - reads across all the conversations in your project for themes and patterns. Fast, and the right default for “what are the broad themes”. It paraphrases, so it isn’t where you go for an exact quote.
- Specific Details - you choose the conversations (one, a few, or all of them) and dembrane finds exact quotes with citations from the full transcripts. Reach for this when wording matters, or when every answer should come from the same set (say, while drafting a report). If you’re already viewing one conversation when you start, it’s selected for you.
Tip
Map the territory in Overview, then switch to Specific Details (and narrow to the right conversations) once you know which thread to pull. For a verbatim quote, always use Specific Details - Overview paraphrases.
Check the sources#
Every answer links back to the conversations it drew on. Glance at them: they let you check the answer against what people actually said, jump to the transcript for full context, and quote a participant accurately. If an answer feels too neat, open the sources. The transcripts are the truth; the chat is a way in.
Templates and the prompt library#
You don’t have to write every question from scratch. Templates are pre-written prompts for common jobs - pulling out themes, listing concerns, summarising one topic. Built-in ones ship in the chat; you can save your own when you reuse a prompt across projects. There’s also a prompt library with more to copy. Pick one, adjust the wording to your project, send. They’re a starting point, not a cage.
Tips for good questions#
- Ask one thing at a time. “What were the top three concerns?” beats a five-part paragraph.
- Name the scope when it matters: “in the Tuesday sessions, …”.
- Give the project good context - the model uses it as background, so honest, specific context sharpens every answer.
- Check the sources before you act on an answer.
Agentic mode#
Note
Agentic mode is dembrane next only - it’s a preview feature, not in production yet. Most hosts won’t see it as a third mode option.
Where Overview and Specific Details answer from the conversations you chose, agentic mode works in steps - searching across conversations, pulling keyword matches, and fetching specific transcripts, then chaining those to answer a harder question (“find every conversation where someone disagreed with the proposal and tell me why”). It runs through a separate service, so it takes longer. For everyday “what did people say about X”, Overview or Specific Details is faster and plenty.
What your plan gives you#
| You’re on | Chat & Ask gives you |
|---|---|
| Free | Chat is gated under free-tier limits. |
| Innovator | No built-in analysis; the chat screen becomes a bring-your-own-LLM + MCP integration (coming soon). |
| Changemaker | Built-in analysis on EU-hosted Gemini - the usual home for hosts doing analysis. |
| Guardian | As Changemaker, on an EU-sovereign stack (coming soon). |
If you hit a wall, that’s a tier limit, not a bug. See tiers, billing & usage for how to upgrade.
Related#
- Chat & Ask - feature reference - the canonical how-it-works page.
- Conversations & transcripts - what chat reads, and where sources point.
- Library & analysis - the other way to make sense of a large set of conversations.
- Reports - turn good answers into something you can share.
- Tiers, billing & usage - what each plan unlocks.
- MCP & bring-your-own-LLM - connect your own model on Innovator (coming soon).
- dembrane next - preview features (like agentic mode) that aren’t in production yet.
Comments