Skip to main content
Your agent can explore your Snowflake databases and run read-only queries so you get insights, reports, and data checks without writing SQL. Ask in natural language and get answers. Authentication uses either a Snowflake Programmatic Access Token (PAT) or an RSA key pair — no password — and queries time out after 30 seconds.
Snowflake capability settings using a Programmatic Access Token stored as a workspace secret

​
How to enable

Go to Settings → Capabilities and enable Snowflake, pick an Authentication method, then link a workspace secret with your connection details. The same secret can be reused across agents and teams.

​
Example use cases

  • Revenue and rankings — “Query our Snowflake sales table and show top 10 customers by revenue this year”
  • Scheduled reports — “Every Friday, run a query for weekly signups and post a summary to Slack”
  • Data reconciliation — “Compare yesterday’s order count in Snowflake with the count in our CRM and flag any mismatch”
  • Schema discovery — “List the tables in our analytics schema and describe the columns in the events table”
  • Ad-hoc analysis — “What were our top-performing campaigns last month by spend and conversions? Use the marketing schema in Snowflake”
Dr Plotts answering a question using Snowflake data
Dr Plotts chart from Snowflake data
The agent supports read-only operations only (e.g. querying data, listing tables, describing schemas). No DDL or DML.

​
How to connect Snowflake

1

Get your account identifier and login name

In Snowflake, open Account Details. Note your Account Identifier (format: <org>-<account>) and Login Name (username).The login name doesn’t have to belong to a person — a dedicated Snowflake service user works, and is the usual choice for an integration.
2

Create a credential for that user

Pick whichever fits your Snowflake policy:
  • Programmatic Access Token (PAT) — generate one in Snowflake; see Snowflake’s PAT documentation.
  • RSA key pair — generate a key pair and assign the public key to the user with ALTER USER ... SET RSA_PUBLIC_KEY; see Snowflake’s key-pair documentation. Both PKCS#8 (BEGIN PRIVATE KEY) and PKCS#1 (BEGIN RSA PRIVATE KEY) PEM keys work, encrypted or not.
Either way, no password is used.
3

Configure in Abundly

Go to Settings → Capabilities, enable Snowflake, and set Authentication to match the credential you created.Then create a new workspace secret and paste in the Account Identifier, Login Name, and either the PAT (secret type Snowflake) or the private key (secret type Snowflake — Key pair (RSA), plus a passphrase if the key is encrypted).All the values live in a single workspace secret, so you only have to enter them once and can share the same secret across multiple agents.

​
Learn more

BigQuery

Query and explore your Google BigQuery data from the agent.

Steep

Query metrics from your Steep semantic layer without writing SQL.