skip to content
mentat

you hired 40 engineers.
why aren't you shipping faster?

Your senior engineer's knowledge is trapped in their head. New hires can't access it. Mentat makes it available for the rest of the team via 20-minute async interviews.

one question, four people paying for it

who
what happens
cost
new hire
Asks "how does auth work?" and gets sent to a stale wiki. Follows it, breaks their setup, spends 3 hours reverting. Never asks again.
Ramp time doubles. Nobody knows they're stuck.
senior eng
Said "check the wiki" mid-flow because they couldn't stop. Rational, but the wiki is stale and they know it.
23 min to recover focus after each interruption.
eng manager
Velocity dipped after adding 3 engineers and can't explain why.
Headcount ROI questioned by CTO.
cto
"We hired 40 people. Why did Q2 launch deadline slip?" Knows the answer but has no data to frame it.
Absorbs the blame at the board meeting.
42% of institutional knowledge exists only in someone's head Panopto/YouGov
3-6mo average engineer onboarding ramp
$47M/yr avg productivity loss from knowledge gaps per large company Panopto/YouGov

capture once. stop repeating.

01 connect

map knowledge

Slack + GitHub + docs. See where expertise lives and where gaps exist. Connect in minutes.

02 capture

interview, don't document

20-min async text chats. Experts share reasoning on their schedule. No prep, no meetings, no writing.

03 answer

team self-serves

New hires ask Mentat, not the expert. Answers include the why, with attribution. Senior's DM load drops.

the why behind the decision, not the what

live elicitation — ~2 minutes of a 20-minute async session
mentat the analytics backfill in november — why dual-write before cutover instead of cutting over cold?
marcus · staff eng · ~120-eng scaleup pipeline was 6h behind on writes. cold cutover loses a day of attribution data. dual-write lets us reconcile.
mentat what made you accept the dual-write cost over a pause-and-batch approach? walk me through the SLA tradeoff you negotiated with marketing.
marcus · staff eng · ~120-eng scaleup marketing accepts a 2h delay on attribution dashboards — we got that in writing during quarterly planning, in exchange for clean reconciliation. pause-and-batch would have kept the data clean but blown the daily SLA.
The why behind a decision rarely makes it into a design doc. Mentat asks the follow-up questions that surface the organizational tradeoffs — the part the next engineer needs and can't search for.
Representative example of the follow-ups Mentat asks during a 20-min interview. Speaker name and company size are illustrative.

what makes mentat different

wikis fail because engineers don't write

Mentat captures knowledge through conversation. Experts talk for 20 minutes instead of writing docs they'll never finish.

search can't find what was never written

Mentat creates what doesn't exist yet. The tradeoffs, failed alternatives, and reasoning behind decisions.

opt-in, not surveillance

Experts choose what to share and review the output. Recognition for their knowledge, not monitoring of their behavior.

find out which departure would hurt most. 15 minutes.

book a call →