CHATBOTS
Slack column-meaning concierge grounded in the warehouse catalog
An analyst asks 'what does this column mean?' in Slack and gets an answer pulled live from the warehouse table comments, column descriptions, and tags.
How it runs
The automated pipeline, trigger to output.
- TriggerSlack mention or slash command with a column/table nameSlack
- LogicParse message to extract table and column identifiers
- ActionQuery Snowflake INFORMATION_SCHEMA + object commentsSnowflake
- ActionCompose grounded plain-English definitionOpenAI
- OutputReply in Slack thread with definition, type, and table linkSlack
What it does
Turns the data-dictionary lookup into a Slack conversation. A teammate mentions the bot with a column or table name, and it answers from the warehouse's own metadata — table and column comments, data types, and governance tags — instead of a stale wiki.
When to use it
When analysts and PMs keep DMing the data team to ask what `orders.net_revenue` or `dim_user.is_activated` actually means. Point them at the bot instead. Best when your catalog descriptions live in Snowflake `COMMENT` metadata and you want answers that can never drift from the schema.
How it works
- 1A Slack mention or slash command arrives with a column or table reference.
- 2The text is parsed to extract the candidate table and column identifiers.
- 3The bot queries Snowflake `INFORMATION_SCHEMA.COLUMNS` plus object comments for matching definitions and types.
- 4An OpenAI step composes a plain-English explanation grounded only in the retrieved metadata, refusing to guess when nothing matches.
- 5The answer, with data type and a deep link to the table, is posted back in the Slack thread.
Set it up
What you configure once, before turning it on.
- 1Connect SlackChannels, DMs, threads, mentions.
- 2Connect SnowflakeWarehouses, queries, shares.
- 3Connect OpenAIModels, embeddings, files.
- 4Set each agent's modelWe leave models unset so you pick the tier — fast + cheap, or top-quality.
- 5Tune it to your dataEdit the prompts, filters, and field mappings so it matches how your team works.
- 6Test, then turn it onRun once against a sample, confirm the output, then enable the trigger.
More Chatbots workflows
Discord Onboarding Completion to CRM Sync
The moment a member finishes Discord onboarding, captures their submitted profile answers, creates or updates a contact in HubSpot.
Discord FAQ-Gated Role Concierge
Greets each new Discord member in a private onboarding thread, walks them through required FAQ steps one at a time.
Discord FAQ Free-Text Answer Grader
When a member submits a free-text answer in their onboarding thread, an agent grades it against the canonical FAQ knowledge base, replies with targeted feedback.
Discord verify-button onboarding via web form webhook
Receives a completed external verification form by webhook, matches it to the Discord account, grants the verified role, and confirms back to the member in Discord.
Discord intro-gated role granting concierge
Watches your #introductions channel, uses AI to confirm a new member's intro is genuine and complete, then auto-assigns the verified Member role and welcomes them.
Daily Discord Digest of Repeated WAF False-Positive Reports
Each morning, scans logged Discord WAF reports in Postgres, groups them by the Cloudflare rule that keeps firing.
Run it inside a business
This workflow drops into a full company template. Import the org, and this is one of the playbooks its agents run.
Run this workflow in your colony.
14-day trial. No DevOps. No Sales call. Provisioned in under a minute.