A Company Assistant That Lives Inside Slack

The problem

Your team asks the same questions every week. Where is the runbook. Who owns this project. What did we decide in that meeting.

The answers already exist somewhere in your systems. The real problem is finding them again, keeping the right people from seeing the wrong things, and getting the answer in front of someone without asking them to open a new app.

What we are building

An assistant that lives inside Slack and knows what your company knows. An employee tags Claude in any channel and asks a question. Claude searches your company’s data, finds the answer, and posts it back with links to the sources. The whole thing respects Slack permissions, so nobody sees anything they should not.

Nothing gets installed on anyone’s computer. It requires a one time setup in Slack. That is it.

How it works, in plain terms

We build three things, and we borrow one.

We build the pipes. Our software plugs into Slack and pulls information from Microsoft, Google Workspace, and your other existing sources so the answers surface without anyone leaving the channel. Every time a Slack thread is updated or a doc changes, we pull it in and store it in a searchable format. This is boring plumbing, and it needs to run all the time without breaking.

We build the brain. When someone asks a question, we run four different search methods at the same time (keyword, meaning, rare-word, and freshness), combine the results, and use a smaller AI model to rank the best ten. Then we send those to Claude to write the answer. The Cerebras engineering team wrote up this exact recipe after building their own version, which now handles 15,000 employee questions a day.

We build the permissions layer. Every piece of information we store carries a list of who is allowed to see it. When someone asks a question, we only search across the pieces that person’s channel has access to. The rules refresh every ten minutes, and any big changes (someone leaves a channel, a doc gets unshared) update right away.

We borrow the interface. Anthropic already ships an official Slack integration called Claude Tag. It handles the chat, the threading, the mobile app, the notifications, and the mentions. We plug our brain into it. This saves months of work and gives your team an interface they already know how to use. It runs on your company’s existing Claude subscription.

The design decision worth calling out

Claude Tag currently does not pass individual user identity to our servers. It operates as a shared bot identity inside each channel. That may be worth raising with the Claude team, since a per-user identity option would open up finer-grained personal access.

Until then, the cleanest solution is to turn channel membership itself into the access boundary. Ask a question in #eng-platform and you draw from the data #eng-platform can see. Ask the same question in #sales-us and you draw from a different set. Employees already understand how Slack channels work, so this reuses a rule they already know. For questions that need per-person access, like private DMs or personal calendars, the same brain serves through Claude Desktop or Claude Code with a personal login.

Timeline

Two to four weeks for the initial build. The core loop could land closer to two weeks; four weeks gives room to ship it polished and documented, with the first connector, the permissions layer, and Claude Tag all wired end to end.

Additional sources, a web dashboard, and admin analytics come after the core loop is working with real users.

Open question

The one thing worth confirming before kickoff is the billing rate and which Claude model Claude Tag uses on your subscription. Anthropic charges consumption-based on API tokens with per-channel spend caps (support page), and the specific model routing affects both cost per query and answer quality. Worth a short conversation with the Claude team.

References