SlackWren AI for Slack
Answers in the thread where the question was asked.
Mention @Wren AI in a channel or send it a message, in any language. It answers in the thread from live data, through the same definitions your data team maintains, with a chart and its reasoning one reply away.
- Channels mapped to projects
- Follow-ups keep context
- Any language
#sales-ops, Wren AIWren AI, in thread
Two regions missed target in Q3. APAC closed at 91% of target and LATAM at 96%. North America and EMEA beat it.
Illustrative answer on a sample dataset.
Trusted by data teams worldwide, with 17,841 GitHub stars
Why it matters
Stop answering the same question by hand.
Most data questions are asked in Slack and answered by someone on the data team, a little differently each time. Wren AI answers them in the thread, from the definitions that team already agreed on.
| Dimension | Asking the data team in Slack | Asking Wren AI in Slack |
|---|---|---|
| Time to answer | Hours or days, depending on the queue | In the thread, from live data |
| Definitions | Depend on who picks up the question | Resolved from your context layer, versioned in git |
| Follow-ups | A new request for every "and by month?" | Asked in the same thread, with the context kept |
| Which data | Whatever the person answering can reach | Each channel mapped to the project meant for it |
| Showing the work | A screenshot of a chart | A chart on request and the reasoning behind the answer |
| Language | Whatever the analyst speaks | Ask in any language |
Your data team still owns the definitions. Wren AI applies them every time, so they can stop re-answering and spend the time on the model.
How it works
From workspace to answer in three steps.
An admin connects Slack once. Everyone else just asks.
1. Connect
Add Wren AI to your workspace
In Wren AI, open Settings, then Integrations, and click Add to Slack. Approve the permissions, and your Slack workspace shows up on the integration page.
cloud.getwren.ai/settings/integrationsSettings
Organization
Members
Integrations
MCP
Integrations
Answer questions where your team already works.
- Connected
Slack
Workspace: acme
Add to Microsoft TeamsMicrosoft Teams
Answer in Teams channels and chats
Default project for Slacksales-analytics ▾2. Map
Point each channel at the right data
The default project answers in any channel. Map a channel to its own project, such as #finance to finance data, so each team asks about the data meant for them.
cloud.getwren.ai/settings/integrationsSettings
Organization
Members
Integrations
MCP
Slack
Channel to project mapping
ChannelProjectsales-opssales-analytics ▾financefinance-core ▾marketingmarketing-data ▾+ Add mappingUnmapped channels use the default project3. Ask
Mention @Wren AI and keep the thread going
Ask in plain language, in any language. Wren AI answers in a thread, keeps the context for follow-ups, posts a chart when you ask for one, and shows its reasoning.
# sales-opsMaya Chen10:02 AM
@Wren AI how is net revenue trending by quarter this year?
1 reply
Wren AIApp10:02 AM
Net revenue is up 18% year to date: $3.4M in Q1, $3.9M in Q2 and $4.4M in Q3. Growth came mostly from North America.
See reasoningReply in thread, for example "Generate chart"
One context layer
Every place your team asks, one definition of revenue.
Slack is one of several places Wren AI answers. Each one asks the same context layer, so a number in a Slack thread matches the one in ChatGPT, Claude or Teams.
Slack app
Answer the question in the thread where it was asked.
Teams app
Answers in Teams channels, group chats and DMs.
Wren AI in Teams →ChatGPTChatGPT app directory
Ask in ChatGPT and get the SQL and a chart back.
Wren AI in ChatGPT →ClaudeClaude connector, MCP
Turn one prompt into a dashboard where every number links to its SQL.
Claude dashboards →Your own agentMCP server
Give your product or internal agent the same context layer.
MCP server →FAQ
Wren AI in Slack, answered.
In Wren AI, open Settings, then Integrations, and click Add to Slack. Approve the permissions and your workspace appears on the integration page. Then choose a default project so Wren AI knows which data to answer from. The Slack setup guide walks through each step.
Mention @Wren AI in a channel, or send it a direct message without a mention. Questions can be in any language. Wren AI answers in a thread, and follow-up questions in that thread keep the context of the conversation.
Questions in a channel use the default project unless you map that channel to a specific project. Mapping a channel such as #finance to a finance project keeps each team's questions on the data meant for them, and limits which data sources that channel can reach.
Yes. Reply with "Generate chart" in the thread to post a chart of the result, and open See reasoning to check how Wren AI read the question, including its assumptions and steps.
Not yet. Row-level security for Slack is on the roadmap. Today, control what a channel can reach by mapping it to a project that only contains the data that channel should see. For per-user row- and column-level security, use Wren AI directly or through the MCP server.
Slack asks the same context layer as every other Wren AI surface: metrics, joins and business rules defined once in MDL and versioned in git. Change a definition in a pull request and the next question in Slack uses it.
Slack is available on the Essential Cloud plan with up to 3 mapped channels, and on Enterprise Cloud and above with unlimited channels. Each question and chart uses API credits like any other request. See pricing for details.
Try it
Put your data team's definitions in every channel.
Connect Slack in Wren AI settings, or see it on your own data with our team.