Conductor Update: Introducing Automated Reviews

In December, we introduced Conductor, an extension for the Gemini CLI designed to bring context-driven development to your terminal. By shifting project awareness out of ephemeral chat logs and into persistent, version-controlled markdown files, Conductor has helped developers worldwide plan before they build.

Today, we’re releasing a new feature to help make AI-assisted engineering safer and more predictable. Our new Automated Review feature allows Conductor to go beyond planning and execution into validation, generating post-implementation reports on code quality and compliance to the guidelines you’ve defined.

Close the loop with Automated Reviews

Our new Automated Review feature introduces a rigorous “verify” step to the development lifecycle. Once your coding agent completes its tasks, Conductor can now generate a comprehensive post-implementation report.

Key capabilities:

Code review: Conductor acts as a peer reviewer, performing deep static and logic analysis on newly generated files. Beyond just syntax, it proactively flags complex issues such as race conditions in asynchronous blocks, potential null pointer risks, and logic errors that could lead to runtime exceptions
Plan compliance: The system automatically checks the new code against your plan.md and spec.md. It ensures every phase of your roadmap was addressed and that no core requirements were omitted during the coding process.
Guideline enforcement: To maintain long-term code health, Conductor verifies that all new contributions adhere strictly to your project’s specific style guides as well as any custom guideline files generated during the planning phase.
Test-suite validation: Instead of relying on manual execution, Conductor integrates your entire test suite directly into the review workflow. It runs all relevant unit and integration tests, then incorporates the results and coverage data into the final report to provide a unified view of whether the new code actually functions as intended within your existing ecosystem.
Basic security review: Safety is integrated into the core of every review, with the system scanning for critical vulnerabilities before code is ever merged. It automatically flags high-risk issues such as hardcoded API keys, potential PII (Personally Identifiable Information) leaks, or unsafe input handling that could expose the application to injection attacks.

Actionable intelligence

The output of an Automated Review is designed for action. Findings are categorized by severity (High, Medium, and Low), providing developers with clear instructions on where to iterate. You’ll receive the exact file path and can start a track within Conductor to fix the issues.

This level of detail ensures that “agentic” development doesn’t mean “unsupervised” development. Instead, it creates a workflow where the AI provides the labor and the developer provides the high-level architectural oversight, backed by automated verification.