PraxisAI - Showcase Project
Listed October 6, 2026
About PraxisAI
Practice AI-agent coding interviews on real GitHub issues, graded by tests
Practice AI coding interviews with real GitHub issues and take-home projects in a browser workspace. See your score and verdict; paid plans add detailed feedback and replay. Coding interviews increasingly let you use an AI agent, and what gets graded is how well you work with it on a real codebase. PraxisAI gives you real SWE-bench issues (Django, Flask, SymPy, matplotlib) checked out at the commit where the bug still existed, browser VS Code, an AI agent, a timer and a token budget. Hidden tests decide whether you fixed it. Free: 2 full-model rounds per week, score + verdict + test outcome, no card. Paid ($8 / $15 per month): 6-dimension report with evidence, prompt coach, token and test-cadence analysis, and full replay of prompts and agent actions. Also 24-hour take-home projects and a leaderboard.
Project details
Website: https://www.praxisai.site