How I Use AI to Review My Own Pull Requests Before Anyone Else Sees Them
An inside look at how to automate PR reviews using localized AI agents, catching bugs and syntax errors before code reviews.
There is a distinct embarrassment in submitting a pull request, only to have your senior dev immediately point out a missing try-catch block or a formatting error. To bypass this, I built a personal Git pre-push hook that runs a local AI code reviewer over my branch modifications before I push. Here is the exact setup and workflow story.
The Psychological Benefit of AI Pre-Reviews
Submitting code for human review is a necessary step, but catching simple syntax slip-ups or missing error wrappers beforehand saves human review cycles and increases dev confidence. The AI isn't there to replace human feedback; it is there to act as a tireless editor that flags obvious flaws.
Figure 1: High-fidelity conceptual render analyzing How I Use AI to Review My Own Pull Requests Before Anyone Else Sees Them.
Automating the PR Review Pipeline
The setup utilizes a Python script triggered during a Git pre-push event. The script runs git diff main to isolate changed files, gathers the line differences, and sends them to a local LLM server. The AI responds with code sanity notes, highlighting potential memory leaks, variable naming discrepancies, or missing tests directly in the terminal.
Electromagnetic Wave Propagation & CSI Physics
To fully grasp how wireless sensing works, we must investigate the mathematical principles of modern radio frequency (RF) propagation. Traditional signals like RSSI only provide the average overall power of a received wireless packet. Conversely, Channel State Information (CSI) extracts complex vectors mapping individual Orthogonal Frequency-Division Multiplexing (OFDM) subcarrier channels. In a standard 20 MHz or 40 MHz WiFi spectrum, the signal is split into 56 to 114 separate subcarrier channels. For each subcarrier, the CSI packet header records the exact Amplitude (signal attenuation) and Phase (fractional cycle shift).
Human bodies are comprised of more than 60% water, making them highly conductive dielectric objects in the path of 2.4 GHz and 5.8 GHz frequencies. As waves travel between the transmitter and receiver, they bounce off walls, obstacles, and humans in a phenomenon known as Multipath Propagation. The physical displacement of a human body perturbs this multipath beam network, creating constructive and destructive interference waves. For a comprehensive overview of how these physical shifts are visualized in real-time, try our Interactive 3D WiFi Radar Demo.
Selecting and Configuring ESP32 Microcontrollers
Implementing a spatial WiFi radar does not require industrial SDR (Software Defined Radio) equipment. The RuView project operates entirely on standard, inexpensive microcontrollers. For high-fidelity telemetry, we highly recommend the ESP32-S3 DevKit. The S3 series features dual XTensa LX7 cores with custom vector instruction extensions that provide hardware acceleration for raw signal matrices.
A typical DIY radar setup consists of a transmitter (Tx) emitting beacon packets and a receiver (Rx) listening on the same WiFi channel. During selection, look for boards featuring an external IPEX antenna connector instead of a standard PCB trace antenna, as high-gain external antennas heavily minimize noise. For a full list of certified microcontrollers and specific command line flashing commands, read our extensive ESP32 WiFi Radar Guide.
Figure 2: Technological block diagram demonstrating Selecting and Configuring ESP32 Microcontrollers.
Privacy Preserving Spatial Sensing & Surveillance Alternatives
As ambient computing spreads, security systems raise massive privacy concerns. Cameras record actual visual images, creating permanent files that are vulnerable to hacks. Passive WiFi sensing is **100% privacy-preserving**. It captures no optical features, faces, or bodies — only numeric signal amplitude vectors.
The data is entirely ephemeral: processed locally and instantly discarded. It is impossible to reconstruct a face from a CSI matrix. This makes WiFi sensing ideal for bedrooms, bathrooms, and private offices. For a comprehensive introduction to camera-free spatial computing, explore our starter overview What is RuView? Complete Beginner Guide.
FAQ
Does the AI review script run inside GitHub Actions?
It can! You can trigger the script locally as a Git hook or incorporate it directly into your GitHub Actions CI pipeline to post review comments on the pull request.
Can this setup be run with free models?
Absolutely. I run this pipeline with Gemma 4 or Llama 4 locally, meaning the entire automation is free and private.