Integrations
/
Snowflake

Snowflake

Query warehouses from agents with query cost limits.

Data
Official
v1.3.2
Install
View docs
Install
~/infra
$
lattis tools add snowflake
✓ tool registered snowflake_wh
✓ credit limit set 2 per query
● first query ran 5 s ago
Pixel Bloom lattice with a cobalt band running across cream pixels
Lattis · production
Last 24 h ·
Snowflake
tool.snowflake.queries
Warehouse queries per hour
320 / h
tool.snowflake.credits
Credits used per day
4.6 / day
tool.snowflake.cache
Results served from run cache
41%

Overview

Let agents answer questions from your warehouse. Every query is checked against a credit limit before it runs, and results are cached per run, so a curious agent cannot run up the bill.

What agents get

snowflake.query
tool
Read-only SQL on one warehouse
snowflake.schema
tool
Databases, schemas and tables in scope
snowflake.sample
tool
First 100 rows of a table for context
tool.snowflake.credits
gauge
Credits used per query and per agent
tool.snowflake.cache
count
Results served from the run cache

Setup

01

Create a Lattis user

Give it a dedicated warehouse and a read-only role.

02

Add the tool

Run the install command and sign in with key pair auth.

03

Set credit limits

Cap credits per query and per agent in the console.

Works well with

All integrations

Postgres

Data

Give agents read access to your database with row-level scopes.

Grafana

Observability

Pre-built dashboards for quality, cost and latency.

Slack

Messaging

Approvals and run alerts in your channels.

Run your first agent in five minutes.

1M free tokens a month. No card, no sales call, production keys in two minutes.

Get API key
Read the docs
~/my-app
zsh
$ npm install @lattis/sdk
$ export LATTIS_API_KEY=lt_••••••••
$ npx lattis run hello-agent
✓ plan · ✓ search_docs · ✓ answer
● run completed · 3 steps · 0.9 s