Demo post

BigQuery locally for agent-written pipelines

Agents are good at writing SQL quickly. LocalCloud helps them test that SQL quickly, too: create local datasets, load small fixtures, run representative queries, and surface unsupported BigQuery features before a real-cloud run.

Read docs Check compatibility SDK examples

Agent prompt CTAs

BigQuery local test

Ask an agent to validate BigQuery code against the local emulator.

Use LocalCloud to test BigQuery code locally. Read https://local.cloud/ai/agents.md and the BigQuery docs, set BIGQUERY_EMULATOR_HOST for localhost, create a local dataset/table, insert sample rows, run a representative query, and call out any unsupported SQL features instead of using real BigQuery.

Configure this repo

Have an agent wire an existing project to LocalCloud safely.

Set up this repository to use LocalCloud for local GCP development. First read https://local.cloud/ai/agents.md, then inspect this repo, identify the GCP services and SDK language, configure emulator environment variables, and run the narrowest integration test against localhost. Do not use real GCP credentials or production endpoints.

Fact

Use BIGQUERY_EMULATOR_HOST for local SDK routing.

Fact

Test representative query paths, not production scale.

Fact

Escalate unsupported SQL and managed features to real BigQuery validation.

Pipeline loop

Fixture, query, assert

Have the agent seed a tiny dataset, run the query or transformation it just wrote, and assert the result. This is faster and safer than using a shared dev project for every iteration.

Caveat

Local SQL coverage is not a production SLA

LocalCloud BigQuery is designed for development and testing coverage, not billing, IAM, slots, reservations, or complete GoogleSQL parity.

Copy-ready setup

Commands and prompts

Use these snippets as starting points, then keep the checks scoped to localhost until you intentionally validate against real Google Cloud.

BigQuery agent prompt

Use LocalCloud BigQuery to test this pipeline locally. Set BIGQUERY_EMULATOR_HOST=http://localhost:24087, seed a tiny dataset, run the representative query, assert the expected rows, and list any SQL features that need real BigQuery validation.

Limitations

Use the sandbox deliberately

LocalCloud BigQuery does not cover BQML, AEAD encryption functions, security policy enforcement, or full GEOGRAPHY parity.
Permitted workflows use local endpoint values and should stop rather than fall back to real Google Cloud or real credentials. The Public Preview License permits individuals and organizations, including for-profit companies, to use LocalCloud for non-production internal development, testing, CI, evaluation, and pilots.
LocalCloud emulates bounded local development workflows. Validate application behavior against real Google Cloud before production deployment.
Before production deployment, unset LocalCloud emulator environment variables and validate behavior against real Google Cloud.

Next routes

Keep the agent on the supported path

BigQuery agent testing — SDK/env quickstart and compatibility table.
BigQuery alternatives — Standalone and real BigQuery tradeoffs.
Compatibility matrix — Check current support boundaries before relying on a local-only test.
Service catalog — Review every LocalCloud service, endpoint, and limitation.
SDK examples — Use standard Google Cloud SDKs pointed at localhost.
Seed data — Load deterministic fixtures for repeatable agent and CI runs.

Sources and review

Claims are tied to current sources

BigQuery emulator features — LocalCloud tested coverage.
LocalCloud agentic facts reviewed 2026-08-26.