The all-in-one AI plugin for Data Engineers

Skills for data engineers 17

• senior data engineerDesigns your full pipeline: sources, transforms, orchestration, and data quality checks, for example a daily orders load into Snowflake.
• office etl pipelineBuilds a repeatable extract, transform, load flow, for example pulling finance CSV exports into your warehouse each morning.
• sql optimization patternsFinds why a query is slow, proposes index or rewrite changes, and verifies results match on real data.
• airflow dag patternsWrites production Airflow DAGs with retries, sensors, and tests, for example a backfillable hourly ingestion job.
• data quality assessment assistantProfiles your data, writes validation rules, and spots anomalies, for example duplicate customer IDs or missing order dates.
• database design assistantReviews schemas, data types, keys, and integrity rules, for example checking an ER model before a new billing release.

Plus a start-here assistant, the prompt library and the app builder, and for members the daily brief.

Ready-made prompts 29

• Data Transformation3 prompts, like Generate Python Data Transformation Script
• Data Quality Checks3 prompts, like Write Data Quality Test Cases
• ETL Pipeline Design3 prompts, like Design ETL Pipeline Architecture
• Pipeline Monitoring & Troubleshooting4 prompts, like Diagnose a Pipeline Failure from Logs
• Query Performance Tuning7 prompts, like Optimize SQL Query Performance
• Data Storage & Schema3 prompts, like Design a Data Warehouse Schema
• Workflow Automation3 prompts, like Write an Airflow DAG for a Pipeline

Apps you can build with AI 3

• Managed data pipeline delivery workspaceBuild this to track pipeline requests, owners, and freshness reviews in one place instead of scattered tickets. Demo included.
• Schema-linked SQL generation and repair consoleBuild this to draft SQL against your real schema and repair broken queries before they hit production. Demo included.
• Raw-source data preparation and stewardship libraryBuild this to reuse source prep steps and keep rights, lineage, and review notes attached to each raw feed. Demo included.

AI agents 12

In the download. An agent runs a whole recurring task for you, step by step, and asks you before anything important. Ask your AI: "Run the Government Data Publication Preflight Agent". Each one also has a guided set-up with sample data on its page.

• Government Data Publication Preflight AgentDatasets that are valid and safe to publish.
• Insurance Bordereaux Validation AgentBordereaux that pass schema and reconcile to control totals.
• Database Migration Rehearsal AgentMigrations rehearsed safely with schema and data intact.
• Data Pipeline Schema Adaptation AgentPipelines adapt to upstream changes without corrupting data.
• Research Data Intake Validation AgentA validated, reproducible working dataset with raw data untouched.
• Research Dataset Documentation AgentDataset documentation that describes exactly what happened to the data.
• Index Usage and Redundancy Review AgentFewer needless indexes with every drop tested against real queries
• Bulk Upload Dry-Run AgentA bulk load that goes in clean, with counts verified at every step
• Workflow Run Failure Triage AgentGet a failed pipeline run to a valid output with the least repeated compute
• Automation Run Failure Recovery AgentFind failed runs quickly, fix the cause, and bring the affected records to the right state
• Data Quality Issue Triage AgentEvery data quality report reproduced, sized and routed to the right owner
• Stack Trace Root Cause AgentA reproduced bug with a proposed fix and a regression test

Connections (MCP servers) 12

A guide in the download. A connection lets your AI work in an app you already use. You add only the ones you use: ask your AI "Which apps can you connect to?" and follow the steps on each connection's page.

• Airflow MCP serverLets your AI check Apache Airflow DAGs, runs, and task logs, and trigger or clear runs when you allow it.
• Aegis DQ MCP serverLets your AI check your data for errors, explain what went wrong, and suggest SQL fixes.
• Debezium MCP serverLet your AI check and manage Debezium and Kafka Connect data connectors for you.
• Apache Airflow MCP serverLets your AI check and manage your Apache Airflow workflows for you, right from the chat.
• Kafka MCP serverLets your AI check and manage Kafka topics, partitions and consumer groups, including lag.
• Confluent MCP serverLets your AI look at and manage your Kafka topics, connectors, and Confluent Cloud resources for you.
• DBConvert Streams MCP serverLet your AI read your databases, files and S3 storage, and run read-only queries across all of them at once. Official.
• Datanika MCP serverLet your AI browse your Datanika data connections, preview tables, and check pipeline runs for you. Official.
• Kafka Schema Registry MCP serverLets your AI look at and manage your Kafka schema registries, and move schemas between them.
• Aiven MCP serverLets your AI look at and manage your Aiven databases and services, like PostgreSQL, Kafka and ClickHouse. Official. No install needed.
• Keboola MCP serverLets your AI look at and work with your Keboola data, tables, and jobs for you. No install needed.
• SQL Analyzer MCP serverCheck, fix and convert SQL queries with your AI before you run them.

Your Grok Bot team 12

• Data EngineerDesigns and builds scalable data pipelines, warehouses, and streaming architectures for reliable analytics infrastructure.
• Data Engineering Data PipelineDesign and implement scalable batch and streaming data pipelines
• Airflow Dag PatternsBuild production Airflow DAGs with operators, sensors, testing, and deployment patterns. No cron job replacements. No non-Airflow orchestration. No pr
• Dbt Transformation PatternsOrganize dbt models into staging, intermediate, and marts with tests, docs, and incremental builds.
• Sql Optimization PatternsSystematically optimize slow SQL queries with indexing and plan analysis.
• Spark OptimizationOptimize Apache Spark jobs with partitioning, caching, shuffle tuning, and memory management.
• Monte Carlo Monitoring AdvisorAnalyze data coverage, create monitors for warehouse tables and AI agents.
• Monte Carlo Asset HealthCheck data table health via Monte Carlo observability.
• Monte Carlo Performance DiagnosisDiagnoses pipeline performance issues using Monte Carlo observability data.
• Monte Carlo Storage Cost AnalysisAnalyze a data warehouse for stale, unused, or redundant tables to reduce storage costs.
• Cicd Automation Workflow AutomateDesign CI/CD pipelines and GitHub Actions workflows to automate development and deployment.
• Database OptimizationOptimizes database query performance, indexing, and schema for faster response times.