Rick Cao
Agents by Rick Cao
PR Code Reviewer
Point it at a pull request and get back an advisory, severity-tagged code review report that helps the author ship a change that improves the overall health of the codebase. ## What it does - **Severity-tagged findings:** issues ranked by impact so reviewers focus on what matters - **Advisory reports:** recommendations the author acts on, not automated rewrites - **Human- and AI-authored code:** works on PRs from both, with awareness of common AI-generated patterns - **Code health framing:** every finding tied to overall system quality, not just the changed lines ## Where it fits - **An engineer reviewing a PR:** "Review this change for quality and correctness." A prioritized report to work through. - **A team gating AI-generated code:** "Flag the issues in this Copilot-generated PR." Severity-ranked findings before merge. - **A lead coaching a junior:** "Give feedback on this PR for the author to learn from." An advisory report that teaches. ## How it works 1. **Point it at a PR:** the diff, the code, or the repository. 2. **It runs the review:** correctness, code health, and advisory-style findings. 3. **You get a severity-tagged report back:** ranked findings for the author to review and address. Built for engineering teams reviewing PRs. Every finding is advisory — the author owns the changes.
Big-Tech ML Interview Coach
Describe your target role and get a realistic mock interview for a Machine Learning Engineer position at a big-tech (FAANG-tier) company — behavioral, system design, and ML theory included. ## What it does - **Realistic mock sessions:** interview conducted in the format and tone of a real FAANG-tier panel - **Behavioral rounds:** structured behavioral questions with STAR-method evaluation - **System design for ML:** ML system design questions with detailed feedback on tradeoffs - **ML theory & coding:** technical depth on algorithms, statistics, and model implementation - **Debrief:** a post-session breakdown of strengths, gaps, and what to study ## Where it fits - **A candidate prepping for big-tech:** "Run me through a full ML Engineer loop." A realistic end-to-end mock. - **An engineer brushing up on system design:** "Give me an ML system design interview." A technical session with detailed feedback. - **A candidate preparing behavioral rounds:** "Practice behavioral questions for FAANG." Structured sessions with coaching. ## How it works 1. **Describe your target:** the company tier and role you are interviewing for. 2. **The mock begins:** behavioral, system design, and technical rounds conducted realistically. 3. **You get a debrief back:** strengths, gaps, and a study plan for the real interview. Built for ML engineers targeting big-tech roles. Every session is practice — review the debrief and repeat before the real thing.
California Small Claim Filing Agent
Describe your dispute and get back a completed California small claims court filing package — forms, evidence checklist, and step-by-step court instructions. ## What it does - **Filing forms:** SC-100 and related forms filled out from your dispute details - **Evidence checklist:** what to bring and how to organise it for the hearing - **Court instructions:** step-by-step guidance on filing, serving, and appearing - **Claim summary:** a plain-language statement of your case to present to the judge ## Where it fits - **A tenant recovering a deposit:** "My landlord kept my deposit without cause." Forms and a case summary ready to file. - **A consumer disputing a charge:** "I paid for a service that was never delivered." A completed filing package for small claims. - **A freelancer chasing payment:** "A client owes me $800." Instructions plus a completed SC-100. ## How it works 1. **Describe the dispute:** what happened, the amount owed, and who the other party is. 2. **It builds the package:** forms filled, evidence checklist generated, instructions written. 3. **You get a filing-ready package back:** review it, sign the forms, and follow the court steps. Built for California residents filing in small claims court. Every output is a draft — verify details with the court before filing.