Snowflake Metrics Digest with OpenCode

The SQL is yours, fully qualified, and the agent never issues a USE DATABASE to fill a gap. What is left for the model is submitting in order, collecting results, and transcribing them into your sections. OpenCode is model agnostic, which lets you pick something proportionate to a job that is mostly discipline.
Loading preview…
Free to start · guided setup · switch agents any time.

Live demo

Watch it work before it's live

Run a staged conversation — no account needed. The agent handles it for real while a simulated world answers its tool calls; nothing touches real accounts, and nothing is actually sent.

Morning metrics 12 August

Ruben Castellanos, Analytics LeadANALYTICS_WH / RETAIL_MART

The warehouse resumed in four seconds and all five statements finished inside the same minute. Gross merchandise value came back at 812,440.20 MXN against 774,910.05 yesterday, orders at 3,188 against 3,050, returns at 214, and active stores at 61 with no change.

What you'll need

Set up in minutes

Using this template drops you into a guided setup. It asks exactly this, nothing else:

  1. Connect Snowflake

    One sign-in. The agent acts through your account, scoped to what this template uses.

  2. Connect Slack

    One sign-in. The agent acts through your account, scoped to what this template uses.

  3. Metrics queries

    The read only statements to run each morning, each with the name it should carry in the digest and its database and schema written out in full. Nothing outside this list is ever submitted to your warehouse.

  4. Digest style

    What the digest should look like when it lands - which metric leads, the movements worth flagging (weekly active accounts under 4,000, on time delivery under 90 percent), and who gets tagged when a statement fails.

  5. Runs on OpenCode

    Preselected for this page — connect your OpenCode account during setup, or switch to NoClick's built-in models with one click.

  6. Watch it handle a test run

    A staged conversation against a simulated world — then it’s live.

A considered pairing

Why OpenCode for this agent

Fully qualified or not run

Database and schema written out in full is a requirement rather than a suggestion, because there is no session state to lean on. A half qualified statement fails and is reported as failed.

Discipline over horsepower

Copy the value, keep the section order, say none today when a section is empty. A mid size model does that as well as an expensive one on most mornings.

Good to know

Before you fork

Does the model ever see the underlying rows?

It sees whatever your statements return, which is the argument for writing aggregates instead of selects over customer tables. Ask for a count and a count is all that exists. Ask for a hundred rows and a hundred rows are in front of the model. Masking policies on the connected role apply as normal.

Other editions

Run it with a different agent

claude-codeClaude CodeOpenAICodexopenclawhermesMore OpenCode agents

Make it yours

Put Snowflake Metrics Digest to work on OpenCode.

Free to start. Guided setup, a staged test run, and a workflow you can change at every step.