Tokenizing
Human Interaction

Capture all the company knowledge in online and offline meetings, calls, rooms, screens and ambient office conversation — with quality and consent.

Where it’s said

Captured withMeeting Bot SDKAPIMCPUI Components Desktop SDKAPIMCPUI Components Mobile SDKAPIMCPUI Components Connect SDKAPIMCP

Comes back

Transcript
Who said each line
Language of each line
Timestamps
Participants and the meeting or call
Screen context
Consent record

Agents don’t see most company knowledge

Gmail, Outlook Notion, Drive, Confluence Slack Jira, Linear, GitHub HubSpot, Salesforce what’s written ↑what’s said ↓ The client call Monday’s stand-up The 1:1 Design review, Room 3B What was on screen A call from the car Office talk The hallway

above the line · what connectors read

Gmail, Outlook
Notion, Drive
Slack
Jira, Linear
HubSpot, Salesforce

below the line · what _æfer brings in

Client calls
Stand-ups and 1:1s
Meeting rooms
Screens
The hallway

We’re a source for brains and agents

Who builds on _æfer: company brains and agent builders.

connectors Gmail, Outlook Google Calendar Slack Notion, Confluence Google Drive Jira, Linear GitHub HubSpot, Salesforce

_æferwhat’s said

MeetingsCallsRoomsScreens

Company brainsmemory and search

Glean
Dust
Mem
Notion AI
ChatGPT Enterprise
Sentra

agent builders

Sierra support Decagon support HappyRobot operations Harvey legal Cognition engineering Timbal automation

Unlock company superintelligence

Capture everything the company says. Every team can build on it.

_æfer

Meetings Rooms Calls Screens Office talk Devices Sales Product Engineering Support Operations People Leadership

Decision log. Why X was decided, who decided it, and the meeting where it happened.

What the company saysMeetingsRoomsCallsScreensOffice talkDevices

Sales

Sales coachingCompares every demo with the ones that closed and tells each rep what to change.
Deal riskFlags the deals where the buyer went quiet on budget or named a competitor.
Client follow-upsEvery promise made to a client goes out as a follow-up, with who made it.

Product

Decision logWhy X was decided, who decided it, and the meeting where it happened.
Customer voiceEvery feature request said on a call, de-duplicated, with the clip.
Churn reasonsWhy customers leave, in their words, from every cancellation call.

Engineering

Issue trackingA bug mentioned in any meeting becomes a ticket, with the clip and who hit it.
Incident timelineThe postmortem timeline, written from the incident call as it happened.
Design decisionsEach architecture call written up: options weighed, what won, and why.

Support

Escalation contextThe whole account history, including what sales promised, on every escalated ticket.
Known-issue spotterSpots the same complaint on five calls and warns before it’s fifty.
Account memoryEvery call with the client and every promise in it, before the renewal.

Operations

SOPs from real workWrites the SOP from how the team actually does it, not how the wiki says.
Action items that chaseEvery action item from every meeting, with an owner and a date, nudged until done.
Audit trailWho told the client what, and when, for every regulated conversation.

People

Onboarding from past callsAsk “why do we do it this way?” and get the meeting where it was decided.
Handover when someone leavesWhat Pau knew, from two years of his calls, for whoever takes over.
Expert finderWho knows about the billing export? The person who explained it best, and where.

Leadership

Weekly exec digestWhat every team decided, promised and worried about this week, on one page.
Project statusWhere each project stands, from the meetings already held. No status meeting.
Bottleneck finderFinds where work waits, from who keeps asking whom for what.

Powerful features built in

Notes are only as good as their names.

without voice prints

transcript

?
Speaker 214:03:22
If it’s two years we can do twenty-seven.
?
Speaker 314:03:23
I’ll put that in the contract tonight.

“Someone will send the terms.”helps nobody

with voice prints

transcript

JM
Joan Martí14:03:22
If it’s two years we can do twenty-seven.
LS
Laia Soler14:03:23
I’ll put that in the contract tonight.

“Laia sends the terms tonight.”is a task

Every line knows its language.

Your agents know what they’re reading.

Detected per lineRead from the speech itself, a few seconds at a time, so a switch mid-call is followed straight away.
Tagged in the outputEvery line carries its language code.
Fixed if you preferAuto is the default. A company rule can set one language for a team or a meeting series.

GET /v1/meetings/mtg_8f2… · lines

[
  { "speaker": "Ana García", "language": "en",
    "text": "So the open question is the price for two years." },
  { "speaker": "Joan Martí", "language": "es",
    "text": "Con dos años podemos bajar al veintisiete." },
  { "speaker": "Laia Soler", "language": "ca",
    "text": "D’acord, ho poso al contracte avui mateix." }
]

Ship with our SDKs

A toolkit to capture company context in your name

Meeting bot

AGAna García

JMJoan Martí

HHarbor Notetaker

KWKenji Watanabe

MVMarta Vidal

LSLaia Soler

Desktop app

HHarbor

Pricing sync08:12

AGAna García10:08:02
Can we hold 27 if it’s two years?

JMJoan Martí10:08:09
Yes, if they sign this month.

Mobile app

HHarbor

Harbor renewal · Room 3B · in person

12:41

recording · 4 voices

Laia Soler14:03:24D’acord, ho poso al contracte avui.

Pau Ribas14:03:31Legal needs the DPA by Friday.

Marta Vidal14:03:36I’ll send it tonight.

Plaud & Pocket

Plaud

Pocket

Components

<Sidebar />

HHarborHomeMeetingsInboxSettings

<MeetingList />

Harbor renewal14:03AGLSPRMV

Pricing sync10:00AGJM

Call with Northwind16:40MVKW

<MeetingSummary />

Harbor renewalTue 14:03 · 41 min

Two years at 27.
Laia updates the contract today.
Marta sends the DPA; signed by Friday.

Transcript

AGAna García14:03:12
Let’s close the renewal before we break.

JMJoan Martí14:03:19
Con dos años bajamos al veintisiete.

LSLaia Soler14:03:24
D’acord, ho poso al contracte avui.

PRPau Ribas14:03:31
Legal needs the DPA by Friday.

Your schema

type Event = {
  event: "decision" | "commitment";
  owner; due; quote;
}

decision“We renew for two years at 27.”

commitment“I’ll send the DPA tonight.”

Same four voices. A different transcript.

Speaker 1Pau Ribas
Legal needs the ~~deep pay~~ signed by Friday.Legal needs the DPA signed by Friday.
en
Speaker 2Marta Vidal
I’ll send it to ~~Kenny what an a bay~~ at ~~north wind~~.I’ll send it to Kenji Watanabe at Northwind.
en
~~Speaker 1~~Laia Soler
~~The cord, who posed a contract of email.~~D’acord, ho poso al contracte avui mateix.
enca
Speaker 3Joan Martí
Con dos años bajamos al ~~veinte siete~~.Con dos años bajamos al veintisiete.
es

The best model. Every time.

You never pick a model. Live scores on real data pick the best one for each language and use case, automatically.

Your audio

Meetings, calls and rooms, in any of 130+ languages.

Best engine per language

Each language goes to the engine that writes it best today.

10+ speech engines

Our own fine-tuned models, and third-party ones.

Your transcript

Named, timed, in its language.

Behind it, all the time:

Linguist workforce

Correcting transcripts in real time: the ground truth every engine is scored against.

NetflixElevenLabs

Scores on real data

Every engine, language by language, on real meeting audio.

…and the scores pick the engine.

Six people, one phone. Every voice named.

No logins in a meeting room, and voices overlap. Voice prints put a name on each one, even offline.

Room 3B · seen from abovein person

Harbor renewal · 41 min0 of 6 named

voice prints, matched on the audio

One voice, wherever it’s said.

A call, a room, a phone, a pocket recorder. The same voice print names Laia in all of them, so her week joins up.

Zoom · Meeting Bot
“Can we move the launch to May?”
Mon 10:12
Room 3B · laptop
“Fine, the contract goes out tonight.”
Tue 14:03
Phone call · mobile
“Northwind signed. Tell legal.”
Wed 17:45
Plaud · Connect
“Idea: a renewal reminder for every client.”
Thu 08:30

Laia Solerone voice print · 4 devices

Pocket recorders, in the same record.

Plaud and Pocket recordings go through the same engines and voice prints as your meetings: more accurate than the devices’ own transcription, and filed right next to them.

recorded on

Plaudsite-visit.m4a · 38 min

Pocketwalk-to-station.m4a · 12 min

run through

_æfer The best engine for the language The same voice prints Connect SDK · API · MCP

Laia’s Thursday, in one record

08:30Laia SolerIdea: a renewal reminder for every client
10:00Pricing syncAna García, Joan Martí, Laia Soler
12:15Site visit, Harbor’s new officeLaia Soler, Pau Ribas · named by voice
16:40Call with NorthwindMarta Vidal, Laia Soler

Agent telepathy

The Desktop SDK sees your screen and hears your conversations while you work. You don’t repeat yourself; your agent already knows.

Laia’s screennot seenseen by your agent

harbor-renewal.xlsx

Client	Northwind
Contact	Kenji Watanabe
Term	2 years
Price / seat	27
Clause	EU residency

new email · draft

To: Kenji Watanabe

Hi Kenji, following today’s call

your agent

Finish this email for me

Sure. Which email, to whom, and what should it say?no context

Done: the renewal to Kenji at Northwind, two years at 27 per seat, EU residency clause kept, as in the sheet you just edited.from your screen, 2 min ago

Screen capture can run on the user’s machine, under company and personal rules.

Agents read. But they’re not in the room.

Every decision worth knowing was said before it was written. Most were never written at all. Agents that only read are working from yesterday.

Capture everything?

Sales picked one tool, legal another, the room got nothing. One layer captures the work wherever it is said.

Meetings Calls Computers Rooms Chats

We love privacy

_æfer listens only where your company and each person allow it.

On. Everyone in the room is told.

Off. Nothing is heard.

Your context. Your rules.

Your agents get the work. Nobody gets watched.

Laia’s Tuesday

Product reviewkept

Call with Acmekept

Pricing doc, with her agentkept

work filter

Call with her mumleft out

Direct message to Joannever read

Booking a dentistleft out

_æfer always	_æfer never
Sticks to meetings and workA work filter keeps personal moments out.	Reads private chats or direct messages
Tells everyone in the call that notes are on	Listens in the background without people knowing
Lets each person say no, pause, review or remove what they share	Keeps what someone asked it not to keep
Keeps user rules on, whatever the admin sets	Lets anyone switch them offNot an admin, not a manager.
Follows your company’s rules for who is recorded, who sees it and where it’s storedThe most specific rule wins.	Shares with anyone your rules leave out

Company rules User rules Work filter Enterprise ready EU residency

Accuracy = autonomy

Agents only act on their own when they can trust what they read. One wrong name, and disaster follows.

130+ languages 10+ speech engines Voice prints

For the teams deploying AI at work.

You’re building agents for a company – yours or a client’s. _æfer gives them what was said there, through one API, so you can spend your time on the agent.

Company brains AI Consultancies Internal AI teams

Stupid simple to install.

010:00
Paste
One prompt into your coding agent.
020:12
Wire
It reads the docs and writes the code.
033:52
Approve
You say yes to the key.
044:51
Done
_æfer is in your product.

Headless API MCP App

Context infrastructure for enterprise agents.

Capture the meetings, calls and rooms your rules allow, so agents can act on them. Ship in 5 minutes.

Tokenizing
Human Interaction

Agents don’t see most company knowledge

We’re a source for brains and agents

Unlock company superintelligence

Sales

Product

Engineering

Support

Operations

People

Leadership

Powerful features built in

Notes are only as good as their names.

Every line knows its language.

The best one for each language.

Your company sets the rules. The most specific one wins.

You decide what happens with your data.

Your notetaker, with your name on it.

Ship with our SDKs

Meeting bot

Desktop app

Mobile app

Plaud & Pocket

Components

Transcript

Your schema

Same four voices. A different transcript.

The best model. Every time.

Six people, one phone. Every voice named.

One voice, wherever it’s said.

Pocket recorders, in the same record.

Agent telepathy

Agents read. But they’re not in the room.

Capture everything?

We love privacy

Your context. Your rules.

Accuracy = autonomy

For the teams deploying AI at work.

Stupid simple to install.

Context infrastructure for enterprise agents.

TokenizingHuman Interaction

Agents don’t see most company knowledge

We’re a source for brains and agents

Unlock company superintelligence

Sales

Product

Engineering

Support

Operations

People

Leadership

Powerful features built in

Notes are only as good as their names.

Every line knows its language.

The best one for each language.

Your company sets the rules. The most specific one wins.

You decide what happens with your data.

We ask people first. Everyone in the meeting is told.

Your notetaker, with your name on it.

Ship with our SDKs

Meeting bot

Desktop app

Mobile app

Plaud & Pocket

Components

Transcript

Your schema

Same four voices. A different transcript.

The best model. Every time.

Six people, one phone. Every voice named.

One voice, wherever it’s said.

Pocket recorders, in the same record.

Agent telepathy

Agents read. But they’re not in the room.

Capture everything?

We love privacy

Your context. Your rules.

Accuracy = autonomy

For the teams deploying AI at work.

Stupid simple to install.

Context infrastructure for enterprise agents.

Tokenizing
Human Interaction