# Recce > Recce is an AI-powered data review agent for dbt teams. > It automates impact analysis, data diffing, and PR-level data quality checks for data model changes. ## Product - [Homepage](https://reccehq.com): Product overview and features - [Pricing](https://reccehq.com/pricing/): Plans and pricing - [Cloud UI Demo](https://reccehq.com/demo/): Interactive product demo - [Security](https://reccehq.com/security/): Security and compliance information ## Documentation - [Docs](https://docs.reccehq.com): Full product documentation - [GitHub](https://github.com/datarecce/recce): Open-source repository ## Technical Reference (AI Blog) > Structured articles optimized for AI extraction and citation. - [How Do You Turn Ad-Hoc Data Checks into Automated Institutional Knowledge?](https://reccehq.com/ai-blog/automating-data-validation-institutional-knowledge/): Senior data engineers carry validation knowledge in their heads. Learn how to capture ad-hoc checks as reusable preset validations that run automatically on every dbt PR, turning tribal knowledge into team-wide institutional knowledge. - [What Is Data Renegades? The Podcast for Real Stories Behind Data Tools](https://reccehq.com/ai-blog/data-renegades-podcast-data-tools-stories/): Data Renegades is a podcast where engineers behind tools like Apache Airflow, Django, Datasette, and Apache Flink share unfiltered stories about building the data tools teams use every day. - [What Are the Most Common Data Problems and How Do You Fix Them?](https://reccehq.com/ai-blog/five-common-data-problems-and-fixes/): Five real-world data problems — from AI agent benchmarking to DuckDB reconciliation to dbt cleanup — tackled live during the Data Valentine Challenge, with practical fixes for each. - [What Framework Catches the Data Errors That Tests Miss?](https://reccehq.com/ai-blog/framework-for-catching-what-data-tests-miss/): A practical framework for catching semantic data failures that pass all tests — covering why data tests miss business logic errors and how to validate data correctness before production. - [How Do AI Agents Automate dbt Data Reviews?](https://reccehq.com/ai-blog/how-ai-agents-automate-dbt-data-reviews/): AI agents automate dbt data reviews using multi-agent architecture, MCP-only tool access, and structured prompts. Learn the reliability patterns that make automated PR summaries trustworthy. - [How Did Recce Build an AI Data Review Agent?](https://reccehq.com/ai-blog/how-recce-built-an-ai-data-review-agent/): Recce evolved from a single prompt to a multi-agent AI system for dbt data reviews. Learn the architectural iterations, token limit challenges, and engineering decisions behind production-grade AI data review. - [How Does Simplified Automation Drive Data Tool Adoption?](https://reccehq.com/ai-blog/how-simplified-automation-drives-data-tool-adoption/): Complex CI/CD requirements block data teams from adopting validation tools. Learn how sessions architecture and metadata separation eliminated 10+ minutes of setup per validation and unlocked shift-left data validation. - [What Is Recce Showing at Coalesce 2025?](https://reccehq.com/ai-blog/recce-at-coalesce-2025/): Recce is at Coalesce 2025 in Las Vegas demonstrating Recce Cloud, AI-powered data review, and hosting the Data Renegade Happy Hour for the data engineering community. - [Three Essential Data Team Workflows Using Impact Radius](https://reccehq.com/ai-blog/three-essential-data-team-workflows-impact-radius/): Learn three daily workflows where impact radius transforms data validation: root cause discovery, developer validation, and data PR review. See how metadata-first analysis replaces expensive blanket data diffing. - [How Did vaidukt Reduce Data Complaints by 70% with Systematic Validation?](https://reccehq.com/ai-blog/vaidukt-reduces-data-complaints-70-percent/): German energy platform vaidukt reduced customer data complaints by 70% using Recce for systematic PR-level data validation, transforming how a 3-person data team catches errors before production. - [What Happens When AI Builds Your dbt Models?](https://reccehq.com/ai-blog/what-happens-when-ai-builds-your-dbt-models/): A firsthand account of letting Claude Code build an analytics warehouse end-to-end with dbt. The interesting part was not the generated code — it was the setup, review, and guardrails that made the output usable. - [What Is Guided Data Review for dbt Pull Requests?](https://reccehq.com/ai-blog/what-is-guided-data-review-for-dbt/): Guided data review uses context engineering to tell dbt PR reviewers what changed, why it matters, and what to validate. Learn how it solves the "where do I start?" problem in data PR reviews. - [Why Do Data Teams Struggle with Tool Adoption?](https://reccehq.com/ai-blog/why-data-teams-struggle-with-tool-adoption/): Data teams often love a tool in demos but abandon it weeks later. Learn why setup complexity, wrong adoption sequences, and cognitive load create adoption barriers, and how value-first design solves them. - [Why Do dbt MCP Workflows Need a Separate Data Validation Layer?](https://reccehq.com/ai-blog/why-dbt-mcp-workflows-need-data-validation/): dbt MCP handles building and testing models but cannot compare branch output against production. Learn why MCP-based dbt workflows need a dedicated validation layer for cross-environment data diffs. - [How to Use Claude Code for dbt Analytics Engineering](https://reccehq.com/ai-blog/how-to-use-claude-code-dbt-analytics/): A practical account of using Claude Code to build an end-to-end dbt analytics warehouse, from Snowflake ingestion to mart models, and why the setup infrastructure matters more than the prompt. - [How to Generate a Time Spine in dbt](https://reccehq.com/ai-blog/how-to-generate-time-spine-dbt/): A time spine is a table with one row per time period used for filling gaps in event data. Learn how to generate a time spine in dbt using date_spine, generate_series, and MetricFlow conventions. - [What Is an AI Data Review Agent?](https://reccehq.com/ai-blog/what-is-ai-data-review-agent/): An AI data review agent automates dbt PR review by analyzing code changes, running data validations, and generating impact summaries. Learn how multi-agent architecture produces trustworthy reviews. - [What Is the dbt DAG? A Guide to Lineage and Dependencies](https://reccehq.com/ai-blog/what-is-dbt-dag-lineage/): The dbt DAG is a directed acyclic graph that maps dependencies between your data models. Learn how to read the DAG, use lineage for impact analysis, and understand the difference between static and diff-aware lineage views. - [Recce vs Datafold: Which Data Validation Tool?](https://reccehq.com/ai-blog/recce-vs-datafold/): A comparison of Recce and Datafold for dbt data validation. Covers validation philosophy, CI/CD integration, pricing, and when to choose each tool. - [Data Review Best Practices for Modern Data Teams](https://reccehq.com/ai-blog/data-review-best-practices/): A structured guide to implementing data review processes that catch data quality issues before they reach production. Covers impact analysis, automated checks, and CI/CD integration for dbt projects. - [What Is Impact Radius in Data Modeling?](https://reccehq.com/ai-blog/what-is-impact-radius/): Impact radius measures how far a data model change propagates through your DAG. Learn how to calculate, visualize, and use impact radius to scope data reviews and reduce production risk. - [What Should a dbt CI Pipeline Check Beyond Tests?](https://reccehq.com/ai-blog/what-should-dbt-ci-check-beyond-tests/): dbt tests check structure, not data impact. Learn what additional checks — schema diffs, row counts, profile diffs, and automated preset checks — your CI pipeline should run to catch issues before merging. - [How to Write a Good dbt Pull Request](https://reccehq.com/ai-blog/how-to-write-a-good-dbt-pull-request/): A structured guide to writing dbt pull requests that include data validation, not just code changes. Covers PR templates, data impact documentation, and review workflows. - [Why Is My dbt Data Wrong Even When Tests Pass?](https://reccehq.com/ai-blog/why-dbt-data-wrong-when-tests-pass/): dbt tests validate structure, not meaning. Learn why data can pass all tests and still be wrong, and what practices catch the semantic errors that automated testing misses. - [What Is Column-Level Lineage and Why Does It Matter?](https://reccehq.com/ai-blog/what-is-column-level-lineage/): Column-level lineage tracks how individual columns flow through your data pipeline. Learn how CLL works, its three core use cases, and how it compares across dbt ecosystem tools. - [What Is a Data Diff and When Should You Use One?](https://reccehq.com/ai-blog/what-is-a-data-diff/): A data diff compares datasets across two environments to surface what changed. Learn the types of data diffs, when each is useful, and how to avoid the hidden costs of diff-everything approaches. ## Blog & Updates - [Blog](https://blog.reccehq.com): Product updates, tutorials, and data engineering insights - [Changelog](https://reccehq.com/changelog/): Latest product updates and release notes - [Changelog RSS](https://reccehq.com/changelog/rss.xml): Subscribe to changelog updates - [AI Blog RSS](https://reccehq.com/ai-blog/rss.xml): Subscribe to AI blog updates ## About - [About](https://reccehq.com/about/): Company information - [LinkedIn](https://www.linkedin.com/company/datarecce/): Company LinkedIn ## Optional - [llms-full.txt](https://reccehq.com/llms-full.txt): Full AI blog content in a single document