Dagctl offers AI‑driven agents that automate the operation of dbt‑core and SQLMesh data pipelines, handling failure remediation, schema drift fixes, cost monitoring, and query optimization by generating pull requests with version‑controlled code changes. The platform integrates with GitHub, Airflow, and Dagster, delivering all improvements through a flat‑rate subscription without per‑seat or usage fees.
Funding
Funding not disclosed
Founders
Product
Problem
Data teams using dbt-core or SQLMesh often face manual, time‑consuming pipeline failures, schema drift, and hidden warehouse costs, requiring engineers to constantly monitor logs, diagnose lineage issues, and write fixes by hand. This reactive approach leads to delayed deployments, unpredictable spend, and fragmented workflows that rely on alerts rather than code‑based changes.
Solution
Dagctl provides AI‑driven agents that operate across the entire dbt and SQLMesh data pipeline. When a job fails, the agents parse logs, trace lineage, generate corrective code, and open a pull request for review, turning incidents into version‑controlled fixes. Continuous cost monitoring attributes query spend to models and schedules, surfacing runaway usage and recommending optimizations. The platform also profiles slow or expensive queries, automatically creates PRs with SQL improvements, and offers model‑building and operational intelligence—all delivered through a GitHub‑native workflow that requires no per‑seat or consumption fees.
Target Audience
Dagctl targets data engineering teams that manage dbt-core or SQLMesh pipelines, including organizations that rely on Airflow or Dagster for orchestration and need automated, code‑first pipeline operations.
Features
- Autonomous failure remediation: reads logs, traces lineage, writes fixes, and opens PRs for dbt and SQLMesh pipelines
- Schema drift detection and automatic correction via code changes
- Warehouse cost monitoring by model, job, and schedule with actionable spend recommendations
- Query profiling and optimization that generates PRs with concrete SQL improvements
- Model building and ops intelligence agents that enhance pipeline robustness
- GitHub‑centric workflow: all changes are delivered as pull requests with full diffs and optional auto‑merge
- Integration with Airflow and Dagster for dbt-core orchestration
- Flat‑rate pricing model without per‑seat, per‑model, or usage charges