Answer in 30 seconds
Operations teams can extract Slack documents with AI in Dynamite Docs. Review fields and request CSV, JSON, Excel, or source exports from channel messages.
/api/integrations/slack/*
Slack already holds the documents that teams pass around during reviews. DynamiteDocs imports supported files from one enabled channel and responds to export commands where the connected Slack user writes them. Each customer authorizes their own workspace. Tokens stay encrypted, and channels must invite the app.
Keep Slack handoffs attached to the document workflow
- Downloading a file from Slack, finding the upload screen, and returning with a spreadsheet creates avoidable handoffs.
- A bot should not read every channel in a workspace. Teams need to invite it only where the workflow belongs.
- A posted table should come from a reviewed extraction, not an unchecked first pass.
- Workspace administrators need to see the exact permissions before approving the connection.
Connect Slack in five steps using Dynamite Docs
Dynamite Docs- 01Open Slack from Apps
- 02Authorize your workspace
- 03Invite the app to a channel
- 04Choose intake or delivery
- 05Run a small test
Open Slack from Apps
Sign in to DynamiteDocs, open Apps, and choose Slack. The integration is available on Starter, Pro, and Scale plans. You can connect without selecting an extraction first.
Authorize your workspace
Choose Connect Slack, select the workspace you want, and review the permissions. Slack may send the request to a workspace administrator. After approval, you return to the same DynamiteDocs dialog with the workspace name shown as connected.
Invite the app to a channel
Open the destination channel in Slack and send /invite @DynamiteDocs. Do this for private channels too. The channel picker only lists channels where the app is already a member, so this invitation keeps access narrow and deliberate.
Choose intake or delivery using Dynamite Docs
In the Import view, choose one intake channel for supported files shared by the connected Slack user. In the Export view, select a saved extraction and copy its export command.
Run a small test using Dynamite Docs
Share a supported document or image in the intake channel and confirm that it reaches the Library. Then paste an export command into a joined channel and open the attachment Slack receives.
What the Slack connection can do
Dynamite Docs- Workspace OAuth
- each customer connects and approves their own workspace
- Channel discovery
- public and private channels joined by the app
- Reviewed delivery
- CSV, JSON, or Excel data posted from a channel command
The connection uses Slack OAuth and stores a separate encrypted installation for each DynamiteDocs account:
A realistic example
A practical accounts-payable channel can use both directions:
| Action | Where it happens | Result |
|---|---|---|
| A controller shares vendor-invoice.pdf | #invoice-review in Slack | The file is imported and queued for extraction |
| An analyst corrects a low-confidence total | DynamiteDocs review workspace | The saved extraction becomes the approved version |
| The analyst writes an export command | #invoice-review in Slack | The channel receives a file attachment with the reviewed rows |
What the Slack connection does and does not do
Does
- Lists channels that have invited the app and lets the user choose one intake channel.
- Posts reviewed CSV, JSON, or Excel data and stored source files after an explicit Slack command.
- Imports supported files from one enabled channel when the connected Slack user shares them.
- Verifies signed Slack events before accepting imports or commands.
Does not
- Does not read message history or scan every channel in the workspace.
- Does not import files shared by every channel member. Intake is tied to the Slack user who connected the account.
- Does not post an unreviewed extraction automatically.
- Does not keep Slack tokens in browser storage or plaintext database fields.
Why the channel boundary matters
Slack works best as a handoff point, not a hidden document store. Requiring a channel invitation makes the boundary visible to the people already working there.
A user enables intake for one channel and writes each export request in its destination channel.
Signed events, encrypted workspace tokens, and per-account routing keep a convenient workflow from turning into broad workspace access.
Setup and delivery questions
Yes. Each customer starts OAuth from DynamiteDocs, chooses their workspace, and approves the requested permissions. Workspace administrators can require approval before installation.
Invite @DynamiteDocs to the channel, then reopen the integration dialog. Private channels also require an invitation from a channel member.
Only supported files shared in the enabled channel by the Slack user who connected the DynamiteDocs account. Other channel members' files are ignored.
A CSV, JSON, or Excel attachment with the reviewed extraction, or a stored source file when the connected user requests original. DynamiteDocs does not export an unchecked extraction result.
One DynamiteDocs account can hold one Slack workspace connection at a time. Reconnecting replaces that account's previous Slack connection.
Extraction guides
Related integrations
Send AI extraction completion events through signed webhooks
Receive signed AI extraction completion events from Dynamite Docs. Verify HMAC signatures on raw bodies and handle retries before acting on delivered data.
POST /api/webhooks, POST /api/webhooks/:id/test
Read the integrationExport reviewed AI extraction results to CSV, JSON, and Excel
Export reviewed AI data from Dynamite Docs to CSV, JSON, and Excel. Choose table downloads or Word and PDF exports from the reviewed document state.
Export API (?format=csv|json|xlsx)
Read the integrationExtract document data using LLMs through a REST API
Extract document data using LLMs through the Dynamite Docs REST API. Submit files, retrieve structured rows, and manage scoped keys within plan limits.
/api/v1/extractions, /api/v1/infer, /api/tokens
Read the integrationDocument workflows it feeds
Prepare invoice data with AI for accounts payable teams
Prepare supplier invoice data with AI in Dynamite Docs for accounts payable. Review fields, line items, and tax before sending checked rows to your system.
Extract invoice line items with AI for accountants using Dynamite Docs
Accountants can extract invoice line items with AI in Dynamite Docs. Review descriptions, quantities, prices, and tax against the source before entry.
From the blog
Turn one Slack channel into a controlled document handoff.
Connect your workspace, invite DynamiteDocs to a channel, test one document import, and send a reviewed export command in Slack.