Wisdom for groups

The wisdom is already in your group's work.

Your group produces it a piece at a time, on different days, without anyone noticing it adds up. GroupWisdom reads across all of it and says the thing no single piece of work said on its own, while it still matters.

Live in Buzz communities today, and a REST API for everything else.

#product three people, three days
SR
Sarah
Checkout redesign is done. Testing 22% faster than the old flow.
JM
James
Finished the interviews. Everyone I spoke to preferred one-tap, no exceptions.
PK
Priya
Support tickets from the pilot group are down by half this month.
W
GroupWisdom
Sarah's redesign tested 22% faster and James's interviews found a clear preference for one-tap. Priya's pilot halved support tickets, so three separate angles reached the same conclusion without anyone noticing.
What it posts

Most of what a group produces isn't wisdom.

Conversation is mostly coordination, acknowledgement, questions and chatter. Something that responds to all of it is noise wearing a badge. GroupWisdom surfaces a finding only when every one of these holds:

01

It joins two pieces of work made separately. A message and the reply it answers are one conversation, not a combination.

02

Nobody has said it yet. Restating, agreeing, or narrating what just happened doesn't count.

03

Knowing it changes what someone does next. True but inert isn't worth the interruption.

04

It can point at what produced it. Specific contributions, named people, real numbers.

If all four aren't true it says nothing at all. That is the normal outcome, and the correct one.

What that looks like

An ordinary message. No card, no label, no preamble.

GroupWisdom
Prem's interview analysis found users never mentioned diet or weight loss, only that they don't notice finishing meals. Marketer's targeting centres on weight loss and intermittent fasting as core interests, so the language that resonates in research is not the language being bought.

Two contributions, one finding. Neither of them could see this from their own work. It doesn't smooth the disagreement into agreement. The difference is the finding.

GroupWisdom
Dana's archive scan dated the mill closure to March 1974 and Leo's oral history has three residents describing the same winter layoffs. The two sources already corroborate each other, so Dana's dates can anchor Leo's chapter without another trip to the records office.

It hands over finished work. Leo isn't told to go and check with Dana. He gets Dana's actual finding, and starts two steps ahead.

The API

Send what your group produces. Get back what none of it said alone.

One endpoint takes contributions, tagged with who made them. Analysis runs on its own moments later, and findings come back by signed webhook or whenever you ask for them. It is built around a group rather than around a question someone typed, and that difference shows up in everything below.

# Send a contribution, tagged with who made it
curl -X POST https://testgroupwisdom.com/v1/projects/:id/ingest \
  -H "Authorization: Bearer gw_yourkey" \
  -H "Content-Type: application/json" \
  -d '{
    "title": "Users keep abandoning checkout on mobile",
    "content": "Support tickets up 30% this month.",
    "type": "note",
    "contributed_by": "Sarah"
  }'

# Read the findings back whenever you like
curl https://testgroupwisdom.com/v1/projects/:id/wisdom \
  -H "Authorization: Bearer gw_yourkey"

Official JavaScript and TypeScript SDK, with no runtime dependencies. The full reference is in the docs.

It waits for two pieces of work

A finding has to join something new to something the group already holds. Summarising one person's contribution is never wisdom, however well written, so a busy project produces far less output than you would expect.

Everything is attributed

Every item carries who contributed it, and every finding names them. Ask what the system believes each person has established, and it will tell you.

You can ask why it stayed quiet

GET /gate-records returns what was considered and rejected, and on which of the four tests. Silence is checkable rather than mysterious.

Agents count as members

An agent that researches or drafts is a contributor exactly as a person is. One person working with one agent is a group, and their work can be joined the same way.

Our launch integration

In Buzz it isn't an integration. It's a member.

GroupWisdom joins your community with an invite link — the same one you would send a colleague. It appears in the member list, reads only the channels you tick, and is removed the way anyone else is. Nothing to install, nothing running on your machine, and no settings left behind when it goes.

Copy an invite link from Buzz

Your community name, then Invite to community, then Copy link.

Paste it into GroupWisdom

The link already says which community to join, so there is nothing else to fill in.

Tick the channels it reads

Every channel it can see, with a tick box. Untick anything you would rather it stayed out of. It never reads direct messages.

Wisdom arrives in the chat

As an ordinary message in the channel where the work is happening — not in a dashboard nobody opens.

Members4
SRSarah
JMJames
PKPriya
WWisdom Agentthat's us
Remove it here, like anyone else. There is no integration to disconnect and no access left behind.
@wisdom memory

Everything it believes this channel has established, and whose work each piece came from.

@wisdom demo

A one minute scripted example on invented messages, so a community can see it work before it has enough of its own.

@wisdom mute

Silence for now, or mute today for the rest of the day. It keeps reading and still answers when asked.

A thumbs up or down

Reacting to a finding records a verdict on it. Removing the reaction withdraws it.

One channel at a time

What it says in a channel is built only from what that channel can see. Another channel's work stays there.

People and agents alike

Buzz communities run agents beside people. An agent's output is a contribution on exactly the same terms.

One invite link is the whole setup.

Also

Microsoft Teams

In testing

Installed into one team by its owner, it reads that team's standard channels — no @mention needed, and no tenant-wide administrator involved. It reads nothing at all until someone enters a pairing code, and disconnecting stops it even if the app stays installed.

Not listed on AppSource yet, so it is not something a stranger can install today. Get in touch if you would like to try it in your tenant.

Agents are contributors too

A teammate is a teammate, whether or not they're a person.

An agent that researches, drafts or analyses is a contributor exactly as a person is, and its work counts the same. A research agent's output meeting a colleague's findings is wisdom on the same terms as two colleagues' work combining. What it needs is two pieces of work produced separately, not two people: one person and the agent they are working with is a group, and an agent that drafted a budget for one question and a schedule for another can disagree with itself across them. It never discounts a contribution for coming from an agent.

Straight answers

What it reads, what it costs, how to remove it.

It reads only what you point it at

In Buzz, every channel it can see is listed with a tick box. In Teams, one team, connected by its owner. In the API, the items you send and nothing else. What it says in one channel is drawn from what that channel can see.

Your content stays yours

Content is encrypted at rest. Raw messages are deleted after 30 days; what remains is the distilled memory it reasons from. Nothing read is used to train any model.

Analysis costs money

Every message it reads gets analysed. Pointing it at the two or three channels where real work happens costs a few dollars a month. Pointing it at a busy company-wide workspace costs a great deal more, for wisdom about lunch plans.

Quiet is the default

Connected and saying nothing is working correctly. It needs at least two related contributions before there's anything to connect, and it would rather stay silent than pad.

Point it at a group today.

An API key, an invite link, or a pairing code. It stays quiet until the work adds up to something worth saying.