Cortex AI Cookbook¶

A workshop method for turning a broad agent idea into personas, a question taxonomy, a registered evaluation dataset, and a phased delivery plan.

Decide how people reach a Cortex Agent, with identity and policies in each lane, then best practices for managed MCP servers and the Agents REST API.

A Cortex Agent profiles messy CSV files, proposes column mappings with AI_COMPLETE, resolves free-text values, and loads approved mappings through allowlisted SQL.

Give an agent embedded in a Streamlit dashboard the page, filters, and persona the user is looking at, by prepending an app-context block to the user message.

Let users attach PDFs, Office files, images, and CSVs to a custom agent frontend with a caller's-rights document tool, per-user stage folders, and authenticated middleware.

One Snowflake CoWork profile routes to specialist agents with the agent_router tool, so Snowflake grants decide which specialist each user reaches.

Redact PII in free text with AI_REDACT, cover domain identifiers with AI_COMPLETE structured extraction, and serve redactions from a stream-maintained cache.

A Cortex Agent whose every number comes from a persisted causal estimator, and which declines to answer for cohorts where no honest estimate exists.

An agent double-counts a table that holds daily and monthly rows. Diagnose it from wrong answers, fix the semantic view with a GRAIN enum, rules, and verified queries, re-test.

Split one long MCP tool call into a fast submit and a bounded fetch over background agent runs, so no call nears a client's timeout and caller's rights still apply.

Relay each signed-in user's Entra ID token to a Cortex Agent so the agent runs as that person, with per-user results from a row access policy on CURRENT_USER().

Serve many tenants from one Cortex Agent: the app server names the end user in an immutable session attribute, and policies derive the tenant from an entitlement.

Grade semantic view descriptions on preciseness, conciseness, non-circularity, and correctness, lint them in SQL, and apply fixes with CREATE OR ALTER or the YAML procedure.

Run Cortex Agent evaluations with pinned metric versions and a custom judge, compare two committed versions, and promote the winner by alias.

Mine Cortex Agent traces for guessed, exploratory, and no-data answers, get the right answer from a subject matter expert, ship it into the semantic view, and re-test.

Mine thumbs-down feedback and user rephrases from agent traces, confirm each with one LLM call, and write a deduplicated eval dataset.

Commit, alias, promote, A/B route, and roll back Cortex Agent versions with runnable SQL and the behaviors observed along the way.

One reconciled view of Cortex AI credits by surface, user, agent, model, and cost center, plus budgets and per-user quotas.

A caller's-rights procedure that reads one agent request's trace, computes a time breakdown by span, and returns an LLM explanation.

Tiered per-user CoCo quotas, daily limits, and alert-only team budgets, starting from conservative defaults and sized from your own ACCOUNT_USAGE.

External LangChain agents reason through Cortex AI Gateway, act through a Snowflake MCP server, and are analyzed from gateway traces and per-user cost.

Route an app through Cortex AI Gateway with its own identity: both API formats, a model allowlist, traces, per-user cost, and a blocking quota.

dbt builds the tables and semantic view, the agent ships as a versioned spec from a stage, and an evaluation gate in GitHub Actions blocks promotion.