Spotter Is Now Available in Slack and Microsoft Teams

Ask Your AI Analyst Complex Data Questions, Without Leaving Your Thread

The Thursday Problem

Let’s say a regional sales director posts a soft renewal number in the channel. A teammate asks the question that decides the plan: trend, or seasonal blip? Nobody in the thread can answer, so the thread does what threads do. It moves on, and the plan gets anchored to the most confident opinion in the room.

The maddening part: the data existed. It was modeled, governed, correct, sitting in the warehouse the whole time.

It's not a data problem; the answer was there. And it's not a tooling problem; the BI platform could have produced that exact cut. It's a timing problem. The question was live on Tuesday. The analyst returns answers on Wednesday.

The Thursday problem charges you twice: teams commit plans without the reliable number, and analysts spend their time on one-off cuts that get thrown away after a single meeting. The answers are right and late.

Spotter is in Your Channels: Where the Decisions Happen

Spotter now runs as an app inside Slack and Microsoft Teams. Add it to a channel, a group chat, or a direct message, and mention it the way you'd mention a colleague. It answers from your governed data models, directly in your message threads.

Every answer names the model it came from, so anyone can check the number instead of taking it on faith.

And it's an analyst, not a lookup. “What were EMEA renewals last month?” is retrieval.

“Why did they fall, and is it the same accounts as last quarter?” is what teams actually ask.

And Spotter handles it: trends, comparisons, contributing factors, and forecasts, at whatever cut the decision turns on, no view built first. It removes the work around work rather than relocating it.

Nobody needs to pick a data model; Spotter selects the most relevant one, and users can scope a chat to a single model for tighter control. And nobody needs to re-explain the thread.

Mention Spotter twenty messages in, and it reads what came before, though every number still comes from your governed models (on Teams, thread context takes administrator permission).

Answers arrive as native charts and tables, and when one needs to travel, ask for a PDF to circulate or a CSV to pull into the forecast model.

On Teams, Spotter is also an agent inside Microsoft 365 Copilot, the surface people at Microsoft shops already open by habit, and it doesn’t consume Copilot licenses or credits, because it brings its own reasoning and its own connection to your models.

Whose Data is Everyone Using?

Here’s an example: An analyst in a shared channel raises the obvious question. Spotter answers under the permissions of the person who asked: your metric definitions and row-level rules, defined once in ThoughtSpot, applied per person on every group discussion.

Spotter inherits the permissions of the user.

An answer posted in a channel is visible to everyone in it - the same exposure as pasting a screenshot. If a colleague wants to dig deeper, they start their own conversation with Spotter, and it answers under their permissions, never the original asker's.

That per-person model is the line between Spotter and assistants wired through one shared service account, which are stuck choosing between over-sharing every answer and hiding in private chats.

How You Can Get Started Now

Spotter in Slack and Microsoft Teams is now available to all customers by default in your ThoughtSpot instance. You can install the app from the Slack or Teams directory, and each person connects their account once from their ThoughtSpot profile. Then add Spotter to a channel and ask away.

What this launch removes is the distance between a live question and a governed answer, and it makes the models you already built more valuable, because the whole company now queries them.

Start your personalized demo to see it in action on your own data stack.

Subscribe to our blog