# AI Code Review That Understands Your PR's Intent

## Executive summary

As coding agents write thousands of lines and open numerous PRs, the bottleneck shifts from writing code to reviewing and trusting it. Tessl Code Review addresses this by providing automated review capabilities that are aware of the Pull Request's (PR) intent, not just the diff. Key features include customizable 'review lenses' scoped via `globs` for specific standards (e.g., security or random design), ensuring accountability remains with the human reviewer while automating consistency across an organization's codebase.

## Key takeaways

- The Shift in Bottleneck: With agents writing code at scale, manual review and establishing trust in agent-written code is now the primary bottleneck. Reviewing becomes the critical 'final gate' (00:00:35).
- Intent-Aware Review: Tessl Code Review differentiates itself by reading the PR summary and title to understand the intended goal of the change, allowing it to review according to context rather than just line changes (00:00:55).
- Customizable Review Lenses: Review lenses are customizable skills that can be evaluated and distributed across a repository. They can be precisely scoped using `globs` to target specific sections of the codebase (e.g., security or random design) (00:02:03).
- Owning the Standard: The review standard is defined by a versionable configuration file within the repository itself, ensuring that the team owns and controls the rules rather than relying on external web UI settings or black boxes (00:03:14).

## Technical details

- Review Lenses & Scoping: Review lenses allow for fine-grained, customizable review skills that can be applied and scoped to specific code sections using `globs` (e.g., 'random design' or 'security') (00:02:03).
- Software Factory Integration: Tessl Code Review is designed as a first-class component of a software factory, integrating directly into the build process to ensure that autonomously shipped code remains trustworthy (00:04:01).

## Practical implications

- Teams can reduce time spent 'babysitting' PRs by automating review standards and increasing trust in agent-written code.
- By defining the review standard as a versionable repo file, organizations can apply consistent baseline review levels across multiple repositories.
- The system supports autonomous development workflows by allowing agents to work more independently while maintaining required quality gates.

## Topics

Code Review, AI Agents, Software Factories, CI/CD, Version Control, Tessl Code Review, tessl.io

Source: https://www.youtube.com/watch?v=ptwholFiAZg