Structure

Layers are inferred from where files sit in the tree, not from reading the code. A project that names its directories unconventionally will read oddly here — open the file browser to check anything the diagram implies.

Languages

Share of indexed source by file size. Binary and vendored files are excluded.

Dependencies

Declared in the repository’s manifests at the indexed commit. A declared package is not proof it is used, and runtime dependencies are listed first.

Feature verification

• Flask backend managing user dataVerified

  The backend is powered by Flask, which manages user data

  Claimed on Devposthigh confidence

  • backend/flaskbase.py:20 — Flask app defined with CORS and multiple routes handling resume upload, audio upload, text-to-speech, and feedback.
• React frontendVerified

  The front end is built with React, creating a seamless and interactive user experience

  Claimed on Devposthigh confidence

  • frontend/src/App.js:1 — Standard Create React App structure with functional components and hooks orchestrating the Onboarding, InterviewSelection, InterviewScreen, and SynopsisScreen views.
• Resume upload and parsingVerified

  Analyzes the user's resumes; database storing users' past experiences and resumes

  Claimed on Devposthigh confidence

  • frontend/src/components/Onboarding.jsx:21 — Uploads a selected PDF file to POST /resumeParser.
  • backend/flaskbase.py:98 — /resumeParser route saves the uploaded file and calls pdf_to_text on it.
  • backend/resume1.py:4 — pdf_to_text extracts text from the PDF via PyPDF2 and writes it to resume.txt.
• Speech-to-text transcription of interview answersVerified

  Assesses performance using speech-to-text

  Claimed on Devposthigh confidence

  • frontend/src/components/AudioRecorder.jsx:49 — Records audio via MediaRecorder and POSTs it to /upload_audio.
  • backend/flaskbase.py:116 — /upload_audio route saves the file and calls run_deepgram on it.
  • backend/deepgram_test.py:11 — run_deepgram uses DeepgramClient prerecorded transcription and writes the transcript to speech_text_message.json.
• Text-to-speech playback of interview questionsVerified

  AI agent to conduct realistic behavioral interviews (implies spoken questions); Deepgram listed as built-with tech

  Claimed on readmehigh confidence

  • frontend/src/components/TextSpeechFunction.jsx:1 — Fetches generated audio from /text_to_speech and plays it in the browser.
  • backend/flaskbase.py:124 — /text_to_speech route calls text_to_speech(text) and returns the audio file.
  • backend/text_to_speech.py:12 — Uses Deepgram SpeakOptions to synthesize speech and save a wav file.
• AI-simulated behavioral interview with dynamic question generationCode-supported

  AI-driven platform that simulates behavioral interviews, providing realistic interview scenarios

  Claimed on Devpostmedium confidence

  • backend/flaskbase.py:22 — The OpenAI-driven conversational interview loop (/interview/setup, /interview, /interview/followup routes using client.chat.completions.create) is entirely wrapped in a triple-quoted string (lines 22-97), so it is dead code and not an active Flask route.
  • frontend/src/components/InterviewScreen.jsx:7 — Instead of calling an AI backend, the interview screen picks questions randomly from a hardcoded local array of 15 behavioral questions on a fixed 60s timer, with no OpenAI call in the question flow.
• Facial/emotion expression analysis via HumeCode-supported

  Hume listed as a core API used to assess performance

  Claimed on Devpostlow confidence

  • backend/hume_funcs.py:13 — top_emotions defines a Hume AsyncHumeClient call to submit an inference job on the recorded audio file.
  • backend/hume_funcs.py:26 — References InferenceBaseRequest without importing it, so the function would raise a NameError if executed.
  • backend/flaskbase.py:1 — hume_funcs is never imported or called from flaskbase.py, so this module is disconnected from any Flask route or frontend flow.
• Personalized feedback driven by conversation history and resume data (OpenAI Assistants)Code-supported

  By analyzing the user's past experiences and resumes, Floo recommends the best responses / gives personalized feedback driven by conversation history and resume data

  Claimed on Devpostlow confidence

  • backend/interview_assesment.py:17 — assessment_start uploads transcript.txt and resume.txt to OpenAI Assistants/vector stores and requests feedback, improved answers, and a score.
  • backend/flaskbase.py:160 — Route decorator uses the invalid kwarg method=['GET'] instead of methods=['GET'], which is not valid Flask route syntax and would likely error.
  • backend/interview_assesment.py:10 — transcript_saver, the only function that would populate transcript.txt from a live interview, is defined but never called anywhere in the codebase, so the transcript fed into the feedback pipeline is never actually generated by the app.
• Post-interview feedback and analysis screenCode-supported

  Provides personalized feedback

  Claimed on Devpostlow confidence

  • frontend/src/components/SynopsisScreen.jsx:17 — SynopsisScreen calls GET /perform_interview on mount, but the response is only logged to console; the UI renders a static placeholder div containing the text 'ok' instead of displaying any feedback, score, or improved answers.
  • backend/data.json:1 — The data store that /perform_interview appends results to is an empty previous_interviews array, consistent with the pipeline never having successfully run.
• Database storing user resumes and past experiencesClaimed only

  The backend...interacts with a database storing users' past experiences and resumes

  Claimed on Devpostmedium confidence

An AI agent derived these features from the project’s Devpost page and readme, then searched the code for each one. Verified features are backed by cited code; claimed-only features had no supporting code, which is not by itself proof a feature is missing.