Use case · Research
Turn twelve interview transcripts into what customers actually said
To synthesise customer interviews with AI agents, give Brainwrite bots the transcripts from Fireflies, Google Meet, or files in a working folder. One bot pulls each customer's problem, current workaround, and trigger to switch. Another groups them into themes, each backed by quotes and the call they came from. You decide what the themes mean for the product.
Read the 12 onboarding interviews from Fireflies tagged October research. For each call, note the problem, what they used before, and why they switched, with exact quotes. Then group the themes, count how many calls mention each, and save the synthesis to Notion.
Your Chief of Staff put a team on it
Nova· Chief of Staff
Atlas· Interview analyst
Sage· Theme researcher
- 12 transcripts read; 5 themes found, ranked by how many calls raised them
- Theme 1 (8 of 12 calls): setup took longer than promised; quote from Maya at Bramble Co
- Theme 4 (2 of 12 calls): wants a Windows version; treated as a minority view, not a pattern
- Contradiction: 3 customers call pricing simple, 2 call it confusing; both sets of quotes included
DoneWhat the themes mean for the roadmap or positioning waits for you. Nothing was sent.
Customer interview synthesis: done. Nothing sent.
- 112 transcripts read; 5 themes found, ranked by how many calls raised them
- 2Theme 1 (8 of 12 calls): setup took longer than promised; quote from Maya at Bramble Co
- 3Theme 4 (2 of 12 calls): wants a Windows version; treated as a minority view, not a pattern
3 bots on this jobThe job
Doing it yourself, and handing it off.
Doing it yourself
After a round of customer interviews you have hours of recordings and a few pages of rushed notes. The calls you remember best are the most recent or the most dramatic, not the most typical. Rewatching every recording to pull quotes takes days, so the synthesis becomes a summary of impressions. When someone asks how many customers mentioned a problem, nobody can say without going back through every call.
What the team does
- Read every transcript, not just the memorable ones
- Record each customer's problem, workaround, and switching trigger with exact quotes
- Count how many calls raised each theme
- List contradictions and questions for the next round of interviews
What waits for you
- What the themes mean for the roadmap or positioning
- Which quotes can be shared outside the team
- Who to interview next
The team
Who's on it.
Your Chief of Staff picks the specialists the job needs. Each has its own role, instructions, model, and app access.
- NovaIllustrated example
Chief of Staff
Splits the transcripts across specialists and writes the final synthesis.
AtlasIllustrated exampleInterview analyst
Reads each transcript and records the customer's problem, workaround, trigger, and exact quotes, with the call and timestamp where the transcript has one.
SageIllustrated exampleTheme researcher
Groups findings across calls, counts how many customers raised each theme, and separates strong patterns from single mentions.
How it runs
A run, step by step.
- 01
Gather the transcripts
Connect Fireflies or Google Meet, or drop transcript files into the bot's working folder.
- 02
Say what you are deciding
Tell the Chief the question behind the interviews, such as why customers switch or what blocks setup.
- 03
Per-call notes
The analyst writes one short record per interview, with quotes copied word for word.
- 04
Read the synthesis
You get themes ranked by how many calls raised them, with quotes and call names, plus questions the interviews did not answer.
Start faster
Ready-made teams for this job.
Add a team from the library in one click. You see a preview first; routines arrive paused and connected apps stay off until you approve them.
What you'll connect
Apps this job uses.
Fireflies
Bots read Fireflies transcripts, ask AskFred about calls, and turn what was said into follow-ups and CRM notes.
Google Meet
Bots create Meet spaces, list past meetings and attendees, and read transcripts to write recaps.
Zoom
Bots schedule Zoom meetings, list recordings and attendees, and turn meeting summaries into follow-ups.
Notion
Bots search Notion, read and write pages, query databases, and add or update rows and comments.
FAQ
Questions about Customer interview synthesis
Which transcript sources does it work with?
Fireflies and Google Meet connectors can list transcripts and read their entries. The Zoom connector lists cloud recordings and can fetch a meeting summary on paid Zoom accounts. You can also drop transcript files, such as text or document exports, into the bot's working folder and point it there.
How do I know the quotes are real?
Tell the analyst to copy quotes word for word and name the call they came from, and save that rule in its memory. Each theme then lists its supporting quotes and call names, so you can open the original transcript and check any of them in a minute.
Will interview data leave my Mac?
Brainwrite keeps chats, files, and memory on your Mac. Transcript text the bots read is sent to the AI provider you chose for each bot, and connected apps such as Fireflies are reached through Composio. Pick a provider you are comfortable sharing customer conversations with, or a local model.
Built on
Features this job relies on.
Chief of Staff
One bot takes your request, hands focused tasks to specialists, and returns a single summary.
Threads and groups
Up to three independent threads per bot, plus group chats where several bots share one brief.
Memory
Plain-text memory per bot that you can read, fix and delete. No hidden profile.
Connected apps
Gmail, GitHub, Slack, Notion and hundreds more via OAuth, with per-bot tool grants.
Give your first job to Brainwrite.
Download the app, connect the AI you already pay for, and tell your Chief of Staff what needs doing.
macOS today. Windows and Linux are coming soon.