# Flask Projects at AI Tinkerers

> Canonical HTML: https://aitinkerers.org/technologies/flask
> Markdown URL: https://aitinkerers.org/technologies/flask.md
> Technology record last updated: 2026-09-18T15:13:55Z
> Generated: 2026-09-23T07:35:11Z

Flask is the flexible Python microframework: build web applications, APIs, and microservices fast with minimal boilerplate code.

Flask is a Python-based microframework, intentionally shipping without mandatory tools like a database abstraction layer or form validation, giving developers maximum control. Its core relies on the Werkzeug WSGI toolkit and the Jinja2 template engine for routing and templating. This minimalistic design makes it ideal for rapid development of small-to-medium projects, including RESTful APIs and modern microservices. Since its 2010 release by Armin Ronacher, its extensibility via community-maintained extensions has ensured its consistent popularity and ability to scale up effectively.

- Official technology site: https://palletsprojects.com/p/flask/
- Public AI Tinkerers demos and talks: 24
- Result page: 1 of 1

## Recent Public Talks and Demos

### [Edge-AI Kindergarten Attendance: Automating Check-ins with Computer Vision & Local LLM Workflows](https://wellington.aitinkerers.org/talks/rsvp_s0e9vu8YVco)

I built an automated, privacy-first facial recognition attendance system for daycares to replace manual paper check-in logs, utilizing a local Python, OpenCV, DeepFace, Flask, and SQLite stack. To bridge computer vision with generative AI, the system integrates a local open-weights LLM via Ollama and Qwen. During the live demo, I will showcase how real-time camera frames trigger automated face verification, log attendance locally into SQLite, and instantly invoke the local LLM endpoint (/api/ai-summary) to generate professional natural language daily attendance reports, pattern summaries, and administrative notes completely offline. Example Pipeline & Output: The system serializes recent database rows into a structured markdown text log (e.g., - Time: 10:05:05 | Guardian: Mahesh Endla | Child: Hrithvik Endla) and passes it through strict prompt constraints. This produces professional markdown reports featuring daily attendance patterns, anomaly flags, and administrative notes: Markdown **Daily Summary Report** **Date:** August 11, 2026 **Attendance Patterns:** Today was a busy day with multiple check-ins for Hrithvik Endla at approximately 10:05 AM by his guardian, Mahesh Endla. **Administrative Note:** Please confirm with the guardian regarding check-in frequency to ensure records are accurately reflected.

- Event context: AI Tinkerers Wellington: Inaugural Meetup · 26 August 2026 — 2026-08-26 — Wellington
- Public talk page: https://wellington.aitinkerers.org/talks/rsvp_s0e9vu8YVco

### [\[UW Data Science Club x HFF\] ParcoursLab: A Human-Centered Approach To Course Recommendations](https://toronto.aitinkerers.org/talks/rsvp_hbsKwKccnH8)

ParcoursLab is an academic co-pilot that saves students and academic advisors time by building a course plan that respects degree requirements and pre-reqs while also taking into account your goal, desired skills, extracurricular interests, and crowd-sourced student ratings. We use AI to automate the manual bookkeeping of reading through dozens of course descriptions and checking prereqs/eligiblity. However, despite this, the platform aims to be transparent, human-centered, and hallucination-free by retrieving course skills from a human-curated skills database (ESCO), providing you with justifications for each of its selection, and allowing you to update your plan conversationally. In the linked demo, the student picks "Computer Science" as their major and "bioinformatics" as their goal. They also mention their interest in Music and Art. Our platform fetches your degree requirements and lays out your required courses (e.g. algorithms, operating systems) using ASAP/ALAP scheduling. Your goal is used to derive a set of desired skills (e.g. biochemistry, machine learning), matched against the ESCO database, which in turn guides a search for the ideal electives. We perform course recommendation using an LLM on a UWaterloo dataset deterministically distilled based on prereqs and augmented with student ratings. We also find you school clubs that match your major, goal, and extracurricular interests (e.g. Waterloo iGEM, Visual Arts club). Courses can be dragged around, and prereqs are enforced. You can chat to replace courses. Adding a desired skill manually will add a course to your schedule that fulfils that skill. Lastly, the user can generate a printable AI summary that they can take to a meeting with an academic advisor for final human guidance.

- Event context: AI Tinkerers Toronto - April 2026 - hosted by Shopify — 2026-04-29 — Toronto
- Public talk page: https://toronto.aitinkerers.org/talks/rsvp_hbsKwKccnH8

### [Building an AI Cyber Threat Intelligence Dashboard](https://atlanta.aitinkerers.org/talks/rsvp_N1oUwQ-s0Q8)

I built an executive-focused cybersecurity dashboard that aggregates and analyzes threat intelligence from multiple sources to generate a concise, AI-powered daily briefing with verifiable source attribution. In the demo, I walk through the full pipeline—from ingesting data via RSS feeds, web scraping, and MalwareBazaar, to normalizing and enriching indicators, deduplicating and clustering signals, and finally generating a real-time “What’s Happening Today” brief. The system is exposed through backend APIs and a React interface where users can refresh feeds and regenerate structured incident summaries on demand.

- Event context: AI Tinkerers Atlanta: Community Demos & Technical Deep Dives — 2026-04-21 — Atlanta
- Public talk page: https://atlanta.aitinkerers.org/talks/rsvp_N1oUwQ-s0Q8

### [SQAAILab - Software Quality Assurance & Artificial Intelligence Laboratory. (This is pronounced SKYLAB - first American space station in 1973 :) )](https://montreal.aitinkerers.org/talks/rsvp_y9vu-klDzzM)

1. I will briefly explain my goal with this laboratory. 2. Then demonstrate, through some QUICK concrete examples, how I proceed. 2.1 Prompting (RCTFET Style) 2.2 Vibe Coding 2.3 Doc Generation 2.4 Analysis Assistance 2.5 Test Generation

- Event context: AI Tinkerers Montreal - February 2026 Meetup — 2026-02-24 — Montreal
- Public talk page: https://montreal.aitinkerers.org/talks/rsvp_y9vu-klDzzM

### [AI-powered language quiz generator](https://waterloo.aitinkerers.org/talks/rsvp_dKoLwNdgNlA)

* intro: Chisme born out of curiosity to explore AI integrations + desire to hide answers when asking chatGPT to create a quiz * quick UI flow of Chisme, an AI-powered language quiz generator: https://learn.findingluisa.com/ * brief overview on how to instantiate an OpenAI Client in python: https://github.com/LuisaTu2/ai-quiz-generator/blob/main/api/openai_client.py * share some learning/reflections and pitfall examples: https://learn.findingluisa.com/learn-reflections/

- Event context: AI Tinkerers Waterloo – December Meetup — 2025-12-15 — Waterloo
- Public talk page: https://waterloo.aitinkerers.org/talks/rsvp_dKoLwNdgNlA

### [How AI helps in language learning on the go - personalized podcasts with spaced repetition](https://lausanne.aitinkerers.org/talks/rsvp_LqcT96BZg4M)

I'll present Podcastify AI, a watchOS app that helps users learn languages through personalized podcast-style lessons. The app has the following abilities: - AI-Generated Content: Custom audio lessons personalized and tailored to user's proficiency level, necessary pace, and personal interests - Spaced Repetition: Smart scheduling that reinforces vocabulary at optimal intervals - Learn On-the-Go: Podcast format on Apple Watch allows passive learning through gestures during commutes, workouts, etc. - Personalization: Content adapts in real-time based on user progress and learning patterns PodcastifyAI demonstrates how AI makes language learning more accessible and efficient, specifically for busy learners.

- Event context: AI Tinkerers Lausanne December 2025 Meetup — 2025-12-03 — Lausanne
- Public talk page: https://lausanne.aitinkerers.org/talks/rsvp_LqcT96BZg4M

### [SecretAIry](https://san-diego.aitinkerers.org/talks/rsvp_ryH19JldtzI)

I hate phone calls, so I built an AI with a quirky personality to handle them for me. "SecretAIry" is my personal AI gatekeeper that not only screens calls but also remembers callers and develops a unique relationship with them over time. When a call comes in, my AI secretary chats with the caller to figure out who they are and what they want. Based on past interactions and the caller's vibe, it decides whether to put them through, take a message, or refuse their call. It's a fun, slightly chaotic solution to my phone-call phobia.

- Event context: AI Tinkerers x Google AI Meetup, San Diego — 2025-11-21 — San Diego
- Public talk page: https://san-diego.aitinkerers.org/talks/rsvp_ryH19JldtzI

### [Live Full-Stack PDF Insights Pipeline: Flask + AWS S3 + React UI](https://nyc.aitinkerers.org/talks/rsvp_u9T-10v0GWo)

I’ll walk through the end-to-end architecture of a full-stack web application that automates product insights and user recommendations using AI. The app uses a React front-end with a Flask backend API to process data pulled from AWS S3 storage, combined with embeddings and basic NLP to make personalized suggestions. This demo will focus on the technical layers, including React component rendering, Python data pipelines, secure REST API routes, and cloud orchestration via AWS.

- Event context: Auth0 x AI Tinkerers: Fall Social Demo Night 🍁 ft. Hex — 2025-11-06 — New York City
- Public talk page: https://nyc.aitinkerers.org/talks/rsvp_u9T-10v0GWo

### [Rafiki AI Tutor](https://nairobi.aitinkerers.org/talks/rsvp_iUacFEAbAc0)

🎯 Project Overview Project Name: Rafiki - AI Tutor for Every Phone Tagline: "Turning Every Phone into a Classroom" Sector: Education Target: Kenyan students (Primary & Secondary) in underserved communities Opening Hook: "This is a kabambe phone. No internet, no apps, no smartphone features. But watch what happens when 10-year-old Amina uses it to get personalized math tutoring..." Problem Validation: "18 million Kenyan students need help, but existing solutions are limited to basic Q&A. What if every phone could become a personal tutor?" Solution Demo: [Live demonstrations of SMS, voice, and dashboard] Impact Vision: "Rafiki democratizes quality education. Every child with a phone becomes a potential scholar." 🌟 The Problem I'm Solving Current Educational Crisis: - 18+ million students in Kenya with limited access to quality tutoring - 80-100 students per teacher in rural schools - 75% of Kenyans have no internet access - 25% have no electricity - Existing solutions (M-Shule, Eneza) are limited to basic Q&A My Innovation: The first conversational AI tutor that works on ANY phone - even basic "kabambe/kadudu" phones - providing personalized, emotionally intelligent tutoring in local languages. 💡 My Solution: Rafiki AI Tutor What Rafiki Does: 1. Conversational Learning: Students have natural conversations about math and science via SMS or voice calls 2. Emotional Intelligence: Detects when students are frustrated and provides appropriate encouragement 3. Multilingual Support: Responds in Swahili-English mix, just like Kenyan students naturally speak 4. Personalized Tutoring: Adapts difficulty and teaching style to each student's learning level 5. Teacher Amplification: Provides insights to help teachers identify class-wide learning gaps How It Works: - SMS Interface: Student texts "I don't understand fractions" → Rafiki explains using familiar examples (chapati, pizza) - Voice Interface: Student calls and asks questions in Swahili → Rafiki responds with audio explanations - Teacher Dashboard: Shows real-time analytics, student progress, and intervention recommendations 📊 Impact & Market Validation Proven Market Need: - M-Shule: 1M+ messages sent, 7% improvement in exam scores - Eneza Education: 6M+ learners, 22.7% increase in academic achievement - 99% of users prefer SMS interface over apps My Innovation Advantage: - Conversational AI vs. basic Q&A - Emotional support vs. transactional responses - Voice-first design vs. text-only - Unlimited content generation vs. pre-built libraries Projected Impact: - Year 1 Target: 1 million students - Cost: Under $1 per student per month - Expected Improvement: 25%+ in learning outcomes (based on case studies) - Scalability: Immediate deployment across East Africa 💰 Business Model & Sustainability Revenue Streams: 1. Mobile Operator Partnerships: Revenue sharing with Safaricom, Airtel 2. Government Contracts: Integration with CBC curriculum 3. School Subscriptions: Premium teacher dashboard features 4. Content Licensing: Curriculum content to other platforms Competitive Advantage: - First-mover: Only conversational AI tutor for basic phones - Network effects: More students = better AI training - Local partnerships: Integration with Kenyan education system

- Event context: AI Tinkerers Nairobi – Sep 25, 2025 Meetup — 2025-09-25 — Nairobi
- Public talk page: https://nairobi.aitinkerers.org/talks/rsvp_iUacFEAbAc0

### [Hashisstant my love and remembered dog assistant](https://pereira.aitinkerers.org/talks/rsvp_kEFbEOKKVR8)

Hashisstant is an intelligent personal assistant, accessible via WhatsApp, designed to perform everyday and work-related tasks through natural language instructions. The system interprets the user's intentions using LLM models and translates them into concrete actions such as scheduling appointments, raising tickets, managing reminders, or consulting information. Interaction with the assistant connects to a tool server using the Model Context Protocol (MCP), which allows for modular and scalable orchestration and execution of functionalities. The talk will feature a live demonstration lasting 15 to 20 minutes, showcasing: Real-world use case Complete interaction flow from WhatsApp. Intent processing with LLM. Task execution via MCP. Automated response and action traceability. Architecture diagrams, data flow (if available), prompt strategies, and code snippets will be included so that attendees can understand the project. What not to do and best practices for building the solution.

- Event context: AI Tinkerers - Pereira: Mentes en Beta: Prototipar, Fallar, Reinventar con IA — 2025-08-28 — Pereira
- Public talk page: https://pereira.aitinkerers.org/talks/rsvp_kEFbEOKKVR8

### [From Chaos to Concurrency: Building a Scalable Medical Document Processor with AI](https://pereira.aitinkerers.org/talks/rsvp_9bnOR7GfOXw)

This is a technical deep-dive into how we tried (and failed, repeatedly) to turn a messy pile of unstructured medical documents — scanned PDFs, DOCX files, and images — into a clean, structured clinical database, and what we learned along the way. We began with a naive approach: a single Python script (document_processor.py) that extracted raw text using PyPDF2 and python-docx, then sent it all to Gemini with a massive prompt asking for 80 fields in JSON format. That broke quickly — the model returned incomplete or hallucinated data, with under 30% success, and most scanned PDFs were unreadable by PyPDF2. In Phase 2, we split the problem: a fallback pipeline used pdf2image and Tesseract OCR for robust text extraction, we introduced specialized prompts for each section (e.g., _extract_basic_data, _extract_medical_history), and added a lightweight AI classifier to detect form type (initial vs. follow-up) and select the correct taxonomy. This improved accuracy but killed performance, with each document requiring 5–6 sequential API calls and batch processing taking hours. So we moved to Phase 3: a parallel architecture using Docker. We introduced a SQLite task queue, split the system into two containers — medical-survey-processor (a Flask API that registers documents as PENDING) and worker.py (a Python service that processes jobs and updates their status) — and scaled using deploy: replicas: in docker-compose.yml to run multiple workers in parallel. The result is a resilient, scalable system combining deterministic logic with contextual AI, capable of processing hundreds of medical documents in parallel. The live demo will show a real file upload triggering the pipeline, key pieces of the code (OCR fallback, classification, prompts, worker orchestration), and no slides — just raw code, terminal logs, and real-world pain turned into working architecture.

- Event context: AI Tinkerers - Pereira: Mentes en Beta: Prototipar, Fallar, Reinventar con IA — 2025-08-28 — Pereira
- Public talk page: https://pereira.aitinkerers.org/talks/rsvp_9bnOR7GfOXw

### [What I Built With The Mullet Method: One Flask App, Multiple Sites](https://seattle.aitinkerers.org/talks/rsvp_fnZ5nydIp_k)

The Mullet Method: Business rules in the front, AI party in the back. I'll show you three completely different websites (see URLs below), then reveal they're all running on a single Flask backend on a $20/month server. The secret? Use AI in the back to create deterministic, ordinary websites up front - no need to run the AI meter for users. This is pure show-and-tell: live sites → single backend reveal → development theory → architectural patterns. Simple, clean, and focused on the core insight that makes it all work. What I'll show: - Three completely different live websites - Single Flask backend reveal (one process, one database) - Development theory: AI in back → deterministic sites up front - Key architectural patterns that make it work - Why this approach beats running AI for every user request Key insights: - Use AI during development, not during user requests - Database-driven routing eliminates hardcoded patterns - Single codebase, infinite customization possibilities - Super low-cost scaling without AI infrastructure overhead

- Event context: Summer on the Lake - August Tinkerers Meetup! (Demos, Food, Friends) — 2025-08-28 — Seattle
- Public talk page: https://seattle.aitinkerers.org/talks/rsvp_fnZ5nydIp_k

### [Is AI the Solution to Alert Fatigue? The Problem Can Only Be Solved With a Deep Understanding of How it Was Created.](https://boston.aitinkerers.org/talks/rsvp_bLRjkuOkVhA)

Recent serious work on the problem of false positives and their effects [1] has measured the rate of false positive alerts, in security operations centers, as ranging between 75% to an astounding 99%. Rates in the nineties have been reported by researchers and data scientists doing work on the problem and I observe similar rates in my own measurements across a wide variety of tools and technologies. At the time of this writing, so-called “agentic” or AI-based products promising a solution to alert fatigue are numerous and increasing by the day. Extensive debate is taking place as to the veracity of these claims. Is AI the magical solution to the problem? To understand that, you need to know a little about how we got here, and about how security threat detections are developed, and some mistakes we made along the way. We know a lot about alert fatigue because we actually worked on manufacturing it. Have you ever wondered about how the people who created the problem would approach solving it, if they had a free hand? This is our answer, an open source project named PROTOSTAR that is the work of eight security researchers and data scientists over the past year plus. Is AI the answer? We think it has a place, but not exactly the way it is being sold today. We know a lot about alert fatigue because we actually worked on manufacturing it. Have you ever wondered about how the people who created the problem would approach solving it, if they had a free hand? One of the fascinating things you see, inside software manufacturers, is what goes on during “build weeks.” Twice a year, or on some interval, most teams are free to ignore product schedules and build whatever they choose, often in self-organized teams. What comes out of those periods - tools we build for ourselves vs for demos - tends to look quite different from the products we ship during the other 50 weeks of the year. PROTOSTAR is our approach to alert signal processing, using ML and AI, in a different direction. It is the result of over a years’ work by seven security researchers, developers, and data scientists while on walkabout, we could never have taken the time to do this while at our day jobs. It differs from the current crop of solutions to alert fatigue in several ways; 1) It generates data structures that enable intelligent processing of all detections, by an LLM or by a human, at reasonable cost. 2) is asymptotically efficient, decisioning more than ten thousand alerts per minute, and accuracy increases with volume. 3) It applies ML differently, and thoughtfully, in order to boost signal rather than increase noise. [1] 99% False Positives: A Qualitative Study of SOC Analysts' Perspectives on Security Alarms Authors: Bushra A. Alahmadi, Louise Axon, and Ivan Martinovic, University of Oxford

- Event context: AI Tinkerers Boston: Langchain & Beyond Meetup — 2025-08-25 — Boston
- Public talk page: https://boston.aitinkerers.org/talks/rsvp_bLRjkuOkVhA

### [Using evals to build robust chatbot assistants](https://dubai.aitinkerers.org/talks/rsvp_VES7t3DOtpk)

I'll be demonstrating a project I am working on where we are using evals to build robust LLM pipelines. Evals help us be more confident shipping LLM based apps to production. I am building a chatbot assistant that is functioning as a Natural Language to SQL agent, allowing users to interact with data in the database, and to get insights from the companies data. This is an actual live project for a business in the UAE The demo will be focusing on how we built evaluation sets to help write deterministic tests for the agent, to give us more confidence in its performance. We will discuss - how we break down the potential query space of the assistant into defined categories using dimensions and error analysis. This helps structure the set of queries we want our bot to work for, as oppose to having an infinite query space which is hard to design good products around. This gives us structure for designing a well performing assistant - we will show how we have written automated evaluation tests, where we pass queries to our bot, check the results it gets from the db, and we validate that against expected data. This is basically writing deterministic unit tests for our non-deterministic agent pipeline

- Event context: AI Tinkerers Dubai Meetup — August 2025 Demo Day — 2025-08-23 — Dubai
- Public talk page: https://dubai.aitinkerers.org/talks/rsvp_VES7t3DOtpk

### [Good Gov AI: turning public information into a public good](https://dc.aitinkerers.org/talks/rsvp_DiDhXs8hQEU)

I will be presenting the AI fine tuning process for Good Gov AI, where we are planning to go, and how we will get there using a mix of AI fine tuning, MCP protocol from our current RAG protocol, and with end user feedback and a design partner along the way. We have worked to make public information more publicly accessible in an action-oriented way.

- Event context: AI Tinkerers - DC Metro Meetup (July 10th 2025) — 2025-07-10 — DC
- Public talk page: https://dc.aitinkerers.org/talks/rsvp_DiDhXs8hQEU

### [DeepGit](https://nurnberg.aitinkerers.org/talks/rsvp_i1mN8F0FF7E)

I have recently released an open source deep research agent called "DeepGit". Its fully opensource end to end and has gained a lot of traction and communityt engagement. Link can be found here https://github.com/zamalali/DeepGit. My aim is to build a full opensource end to end implementation of the service that I envision. I want to build a powerful search engine, alongside deep research and conversational agents on top of DeepGit. This is to help the devs out there fully open source.

- Event context: AI Tinkerers Nürnberg First Meetup - July 3rd — 2025-07-03 — Nürnberg
- Public talk page: https://nurnberg.aitinkerers.org/talks/rsvp_i1mN8F0FF7E

### [Finding My Voice in AI: A Journey of Learning and Growth](https://regensburg.aitinkerers.org/talks/rsvp_KYEWsoAU8Yg)

As a master’s student in Applied AI for Digital Production Management at Deggendorf Institute of Technology, I am still at the beginning of my journey in AI. I come from a background where women don’t always have the opportunity to speak up or share their ideas freely. This makes it especially meaningful for me to explore technical spaces like this. While I don’t have a finished demo yet, I’d love to briefly share my ideas for potential thesis topics, and how I’m working to build the skills I need to bring them to life. My focus is on learning every day, asking questions, and slowly becoming more confident in my technical abilities.

- Event context: Regensburg AI Tinkerers – Summer Launch Meetup (July 3 @ BioPark) — 2025-07-03 — Regensburg
- Public talk page: https://regensburg.aitinkerers.org/talks/rsvp_KYEWsoAU8Yg

### [AI in Education](https://pune.aitinkerers.org/talks/rsvp_1Xnd9K40S8Y)

Conventional systems of education and career growth tend to provide non-tailored experiences, hence disengagement and less than optimal career readiness.This talk proposes ’Sahay,’ an artificial intelligence-based platform that seeks to rectify this situation through dynamic, tailored learning trajectories and career counseling. Sahay uses Retrieval-Augmented Generation (RAG) and Large Language Models (LLMs) to create adaptive educational material and career suggestions from the profiles of individual users. The platform consists of a dynamic assessment module to analyze user knowledge, learning styles, and career interests to facilitate customized learning routes and skill mapping in real time. Sahay also boasts advanced career features such as AI-based job matching, automated resume updating and interview prep tools. Importantly, the platform allows for uploading of multiple resumes, ATS score-based resume suggestions , and suggests the best resume per job match. In addition, Sahay incorporates blockchain technology for safe verification of credentials to build trust and transparency for employers and recruiters. The platform provides two different administrative logins: one for Training and Placement Officers (TPOs) and another for recruiters, allowing easy interaction and management. By using AI methods to work with userfriendliness, Sahay transforms the learning and career development sector

- Event context: AI Tinkerers Pune - Meetup — 2025-06-28 — Pune
- Public talk page: https://pune.aitinkerers.org/talks/rsvp_1Xnd9K40S8Y

### [Structured Outputs & Batch Processing w/AI](https://nyc.aitinkerers.org/talks/rsvp_G38IYdS2Bb8)

A short overview of some code that does batch processing and when and where you'd want to build it into your workflows. Structured outputs bring their own development challenges, I'll speak to a couple of things I've noticed from using structured outputs over the last 12 months.

- Event context: Building AI Agents with Google Cloud AI — 2025-06-25 — New York City
- Public talk page: https://nyc.aitinkerers.org/talks/rsvp_G38IYdS2Bb8

### [Perfile – Smart Profile Web App](https://mumbai.aitinkerers.org/talks/rsvp_CASvf6HxGgM)

Perfile is a modern, responsive profile page builder that lets users showcase their portfolio, skills, and contact details in one sleek link. Designed using HTML, CSS, and JavaScript, it emphasizes clean UI, easy navigation, and mobile-first design principles. Ideal for developers, freelancers, and students to maintain a personal brand.

- Event context: AI Tinkerers Mumbai Meetup - April — 2025-04-26 — Mumbai
- Public talk page: https://mumbai.aitinkerers.org/talks/rsvp_CASvf6HxGgM

### [Personalized AI Tutor](https://toronto.aitinkerers.org/talks/rsvp_s_xEQsS6lP0)

We will be presenting a web application built using a local LLM that provides personalized learning plans by dynamically assessing the user's knowledge level. The application also gracefully handles FAQ-style queries, enhancing the overall user experience.

- Event context: AI Tinkerers Toronto - April 2025 Meetup at Shopify — 2025-04-24 — Toronto
- Public talk page: https://toronto.aitinkerers.org/talks/rsvp_s_xEQsS6lP0

### [Socia](https://abu-dhabi.aitinkerers.org/talks/rsvp_CHaxHsxZZH0)

Socia is your personal communication coach, built to help you master public speaking and everyday conversations with AI-driven real-time feedback. Whether you're preparing for a big presentation, tackling social anxiety, or just looking to refine your speaking skills, Socia provides immersive practice environments, instant speech analysis, and gamified learning to make communication training engaging and effective. Powered by React Native with TypeScript on the frontend and Flask on the backend, Socia leverages Azure AI services to deliver cutting-edge speech recognition and analysis. Available on iOS, Android, and beyond, Socia ensures that anyone, anywhere, can become a more confident speaker.

- Event context: AI Tinkerers - Abu Dhabi Meetup #3 (Feb 2025) — 2025-02-21 — Abu Dhabi
- Public talk page: https://abu-dhabi.aitinkerers.org/talks/rsvp_CHaxHsxZZH0

### [Spoticry](https://ann-arbor.aitinkerers.org/talks/rsvp_aXC9uPQBYhQ)

SpotiCry is a full-stack emotional analytics platform I developed to help college students understand their emotions during stressful times. It uses D3.js and Chart.js for data visualization, with a Flask-based RESTful API serving data to a React frontend. The platform automates data extraction from Google Sheets and uses MongoDB for storage. I am now exploring AI integration, specifically NLP for analyzing user inputs and ML models for predicting emotional patterns. I will demo the current functionality and discuss the challenges and opportunities in incorporating AI to enhance emotional insights and user experience.

- Event context: AI Tinkerers: Ann Arbor - September 18 — 2024-09-18 — Ann Arbor
- Public talk page: https://ann-arbor.aitinkerers.org/talks/rsvp_aXC9uPQBYhQ

### [EcoLoop: a platform that uses advanced AI to help you evaluate new ideas easily and effectively](https://toronto.aitinkerers.org/talks/rsvp_WT4ZaQdSf5c)

- Chatbot Interaction: Effortlessly articulate problem-solution pairs with an intuitive chatbot interface. - Visualizations: Gain profound insights through graphical representations, maturity stage, and viability scores. - 3D-VR Integration: Immerse yourself in proposed solutions with realistic virtual reality experiences. - EcoLoop's intelligence is implemented using the Retrieval-Augment-Generator framework LangChain, which connects the Language Model to the extensive knowledge repository encoded in the vector database. -Technologies used: Pinecone (fast similarity search for vectorized data), LORA Model (generates the 3-d VR solution Web Scraper), Semantic Classifier (discern semantic meanings for idea categorization), Semantic Summarizer (summarize content based on its meaning Nextjs and TailWindCSS), and Flask (handles backend and endpoint creations, and runs the ML models)

- Event context: AI Tinkerers - Toronto - June 2024 Meetup — 2024-06-27 — Toronto
- Public talk page: https://toronto.aitinkerers.org/talks/rsvp_WT4ZaQdSf5c

## Related Technologies

- [Python](https://aitinkerers.org/technologies/python) ([Markdown](https://aitinkerers.org/technologies/python.md)) — 664 public demos
- [React](https://aitinkerers.org/technologies/react) ([Markdown](https://aitinkerers.org/technologies/react.md)) — 220 public demos
- [LangChain](https://aitinkerers.org/technologies/langchain) ([Markdown](https://aitinkerers.org/technologies/langchain.md)) — 446 public demos
- [OpenAI API](https://aitinkerers.org/technologies/openai-api) ([Markdown](https://aitinkerers.org/technologies/openai-api.md)) — 520 public demos
- [AWS](https://aitinkerers.org/technologies/aws) ([Markdown](https://aitinkerers.org/technologies/aws.md)) — 38 public demos
- [ChatGPT](https://aitinkerers.org/technologies/chatgpt) ([Markdown](https://aitinkerers.org/technologies/chatgpt.md)) — 83 public demos
- [Claude](https://aitinkerers.org/technologies/claude) ([Markdown](https://aitinkerers.org/technologies/claude.md)) — 174 public demos
- [JavaScript](https://aitinkerers.org/technologies/javascript) ([Markdown](https://aitinkerers.org/technologies/javascript.md)) — 40 public demos
- [OpenAI](https://aitinkerers.org/technologies/openai) ([Markdown](https://aitinkerers.org/technologies/openai.md)) — 112 public demos
- [OpenCV](https://aitinkerers.org/technologies/opencv) ([Markdown](https://aitinkerers.org/technologies/opencv.md)) — 26 public demos
- [PostgreSQL](https://aitinkerers.org/technologies/postgresql) ([Markdown](https://aitinkerers.org/technologies/postgresql.md)) — 106 public demos
- [Pytest](https://aitinkerers.org/technologies/pytest) ([Markdown](https://aitinkerers.org/technologies/pytest.md)) — 6 public demos
- [SQLite](https://aitinkerers.org/technologies/sqlite) ([Markdown](https://aitinkerers.org/technologies/sqlite.md)) — 28 public demos
- [Twilio API](https://aitinkerers.org/technologies/twilio-api) ([Markdown](https://aitinkerers.org/technologies/twilio-api.md)) — 2 public demos
- [Alembic](https://aitinkerers.org/technologies/alembic) ([Markdown](https://aitinkerers.org/technologies/alembic.md)) — 1 public demo
- [Amazon S3](https://aitinkerers.org/technologies/amazon-s3) ([Markdown](https://aitinkerers.org/technologies/amazon-s3.md)) — 8 public demos
- [Anthropic Bedrock](https://aitinkerers.org/technologies/anthropic-bedrock) ([Markdown](https://aitinkerers.org/technologies/anthropic-bedrock.md)) — 1 public demo
- [Augment](https://aitinkerers.org/technologies/augment) ([Markdown](https://aitinkerers.org/technologies/augment.md)) — 1 public demo