CHATBOTS

PII Lookup Bot for Postgres Columns

Lets staff ask in Slack whether a Postgres column holds sensitive data; classifies it against the governance registry and replies with the PII tier, masking policy, and approval…

CategoryChatbots
Enginepaperclip
Difficultyintermediate
Triggerchat
Steps5
Setup~15 min

How it runs

The automated pipeline, trigger to output.

  • TriggerSlack question about a columnSlack
  • ActionInspect live column type + comments in PostgresPostgreSQLPostgres
  • ActionLook up PII classification in Coda registryCodaCoda
  • LogicBranch: classified vs unclassified column
  • OutputReply with PII tier, masking policy, approval pathSlack

What it does

Gives engineers and support agents a fast way to check whether a database column contains regulated data before they query, export, or log it. Ask about `users.ssn_last4` and the bot returns its PII tier, retention rule, and whether it must be masked.

When to use it

When teams are unsure which columns are safe to expose in dashboards, support tools, or third-party exports, and you need a consistent, auditable answer instead of guesswork.

How it works

  1. 1A Slack message triggers the bot with a table.column reference.
  2. 2The flow inspects the live column type and comments from the Postgres operational database.
  3. 3It looks up the governance classification (PII tier, masking policy, lawful basis) stored in Coda.
  4. 4A decision step branches: if the column is unclassified, it routes the question to the data-governance channel for triage; if classified, it formats the policy answer.
  5. 5The bot replies with the tier, required masking, and who to ask for export approval.

Set it up

What you configure once, before turning it on.

  1. 1
    Connect SlackChannels, DMs, threads, mentions.
  2. 2
    Connect PostgresAny Postgres URL — query, write, migrate.
  3. 3
    Connect CodaDocs, packs, automations.
  4. 4
    Set each agent's modelWe leave models unset so you pick the tier — fast + cheap, or top-quality.
  5. 5
    Tune it to your dataEdit the prompts, filters, and field mappings so it matches how your team works.
  6. 6
    Test, then turn it onRun once against a sample, confirm the output, then enable the trigger.

Run this workflow in your colony.

14-day trial. No DevOps. No Sales call. Provisioned in under a minute.