The product · shipping Q1 2027
Four things ship in V1. Here is exactly what each one will do.
A brief in 90 seconds. A link anyone can open. A search across every call you have run. And an API your AI agents can read. None of it is live yet — V1 lands Q1 2027.
01 / interview brief generator
Upload. 90 seconds. Ship a roadmap on it.
Value-risk synthesis · the headline output
She will choose this if bulk payments land under a 1.5% effective fee. Confidence: high. Evidence: Says[03:12], Says[19:47].
Says · diarised
"Four days end-to-end and three ops people on it."
Thinks · extracted
"No contract unless treasury can approve without exception."
Does · observed
"Demonstrated the current workaround twice."
Feels · flagged
"Suspicion on the pricing reveal at 27:03."
- Built to accept exports from Zoom, Meet, Loom, Granola, Otter and Fireflies at launch. Or raw audio. Or manual entry. These are file formats we intend to support, not partnerships or integrations we have in place.
- Four-dimensional tagging pass. Says diarised. Thinks extracted. Does observed. Feels flagged.
- Value-risk synthesis as three evidence-linked bullets. That is the headline output.
Target at launch: under 90 seconds from upload to rendered brief, 95% of the time, on a 10 Mbps Lagos upload. Nothing is measured yet — this is the bar we are building to.
02 / shareable brief URL
Every brief is a link. Every link travels.
- Designed to be public by default, with auth-optional viewing and workspace, team and private toggles.
- One-click Slack, WhatsApp, LinkedIn, X, email share.
- Open-Graph and Twitter-Card unfurls with the Value-risk synthesis as preview.
Target at launch: under 5 minutes from sign-up to a brief shared in Slack, 95% of the time.
Bulk payments discovery · 38 min
She will choose this if bulk payments land under a 1.5% effective fee.
Slack unfurl preview
RICS Brief · Bulk payments discovery
Value-risk: chooses under 1.5% effective fee. 3 evidence-linked bullets.
03 / brief corpus query
Built so every insight you capture stays one query away.
Cross-brief synthesis · 3 briefs matched
Segment leads converge on a fee ceiling between 1.2% and 1.5% effective. Two of three flagged treasury approval as the blocking step above ₦5M. Willingness-to-pay sits in Thinks, not Says, in all three briefs.
brief #7 · Segment Lead A · Mar 12
Says[19:47] "anything above one and a half points is a hard no" · Thinks[19:52] threshold is effective rate, not sticker
brief #4 · Segment Lead B · Feb 28
Says[22:10] "we benchmark against our current 1.2%" · Thinks[22:31] anchor is the incumbent, not value
brief #2 · Segment Lead C · Feb 14
Says[33:18] "legal reviews anything over $15 a seat" · Thinks[33:29] procurement threshold is the real ceiling
- Natural-language queries against the entire brief corpus.
- Cross-brief synthesis when a query matches more than one brief.
- Faceted filters: date range, participant, segment, risk tag, empathy dimension.
Target at launch: first result in under 3 seconds, 95% of the time.
04 / MCP server (Model Context Protocol)
Every AI agent in your team's stack, reading the same substrate.
- Read tools day one: list_briefs, get_brief, query_briefs, get_empathy_field, get_risk_tags.
- Write tools V1.5: emit_brief, update_empathy_field, set_risk_tag.
- Workspace-scoped API keys, with rotation and revocation in-console. Both land with the V1 server.
Target at launch: MCP tool calls returning in under 5 seconds, 95% of the time.
Free · no signup
How much of what you learned last quarter can you still find?
Ten questions. Two minutes. No signup. A scored result across the 4x4.
Take the audit →