Date loading...

Generative AI Hackathon

Build applications using NLP!

🗓️ This will be a 48-Hour Virtual Hackathon from 2 - 4 December 💻 Technology: You will build applications with generative AI supplied by Cohere ✔️ Level: All levels are welcome 😊 For whom?: Builders, creators & innovators! 💲 The Event is totally free! 🏆 $2000 cash prize pool!
Generative AI Hackathon event thumbnail

Cohere NLP

Cohere provides through it's API unprecedented access to affordable, easy-to-deploy large language models capable of powering the next generation of game-changing AI native applications.

Powerful NLP Model

Cohere trained their models on billions of words to understand the nuances and context markers of human communication.

Flexible API

The Cohere API works with many different libraries that fit every stack. Cohere's Python, Node, and Go SDKs make AI easy to integrate into your app.

Cohere Sandbox

Introducing the new Sandbox for developing and deploying advanced natural language processing (NLP) projects, quickly.

Cohere Challenge

The challenge for this hackathon is to create an innovative solution using Cohere API

*You can get additional points if your project uses Cohere’s Generate endpoint.

Prizes and Awards

🥇 $5000 API credits + $1000 cash
🏆 $4000 API credits + $1300 cash to be distributed among the finalists

Additionally, all winning teams will receive exclusive holiday swag and have the chance to: Meet Cohere Founder for a virtual coffee & record a video of their demo that will be promoted on Cohere's channels!

Cohere NLP Hackathon details

Join lablab and Cohere during 48h to innovate and build the new generation of NLP powered applications. Find all the relevant details below.

🗓️ Where and when

The hackathon starts on December 2nd and ends on December 4th. Over the weekend, you'll have the opportunity to learn from Cohere and lablab experts during workshops, keynotes, and mentoring sessions. The hackathon will take place on the platform.

🦸🏼‍♂️ Who should participate?

Previous experience in AI is not required but welcomed. While many participants are industry experts, we also welcome people with other types of domain knowledge that want to understand & explore how AI can be used in their fields.

🔐 Access to Cohere API

To get started with Cohere NLP API please signup using the following link: Your trial API key are free and has and can handle up to 100 calls per minute free of charge. You can find more information about the API here.

😅 How about teams?

If you don’t have a team you will be able to match and team up with other participants around the world. Finding & creating teams can be done from the dashboard you can access after you enroll. We also recommend checking our Discord server to find teammates and discuss ideas. You can join it here

🛠️ How to participate in the hackathon

The hackathon will take place online on platform and Discord Server. Please register for both in order to participate. To participate click the "Enroll" button at the bottom of the page and read our Hackathon Guidelines.

🧠 Get prepared

To get prepared for the hackathon, we recommend you to start at our Cohere technology page where you can find all the relevant information about the API and how to use it plus cohere tutorials and cohere boilerplates.



Sandbox is a collection of experimental, open-source GitHub repositories that make building applications and/or showcasing how such applications are built using large language models fast and easy with Cohere. Sandbox repositories aim to enable all developers, regardless of ML experience, to:


A framework for building conversational agents on top of the Cohere API.

Route Generation

Build a functional chatbot that recognizes users' intent from descriptions.

Grounded QA

A powerful, contextualized, factual question-answering Discord bot.


A suite of tools that help you make sense of text collections.

Toy Semantic Search

A simple semantic search engine built with the Cohere API

Applications build on Cohere

Learn about the winning projects from previous episodes of the Cohere hackathons.

Perfect Prompt

Prompt engineering and image generation tool.

Tip of my Tongue

An application that improves the efficiency of chat-based support systems.

Turing Test

A tool for finding and browsing books based on short prompts, keywords, or story plot.


API Access

Signup for API Access

Cohere's API is currently free-to-use for everyone. Sign up for Cohere and start integrating NLP into your builds now!

Speakers, Mentors and Organizers

  • Edward Grefenstette

    Edward Grefenstette

    Head of ML, Cohere; Honorary Professor, UCL

  • Meor Amer

    Meor Amer

    NLP at Cohere | ML Visuals at kDimensions

  • Sandra Kublik

    Sandra Kublik

    Developer Relations at Cohere

  • Luis Serrano

    Luis Serrano

    Author of Grokking Machine Learning | AI scientist and communicator

  • Jay Alammar

    Jay Alammar

    Director, Engineering Fellow (NLP) at Cohere

  • Mathias Asberg

    Mathias Asberg

    Founder New Native

  • Paweł Czech

    Paweł Czech

    Founder New Native

  • Aleksander Jankowski

    Aleksander Jankowski

    Operations and Partner Manager at New Native

  • Ervin Moore

    Ervin Moore

    PhD Student in Computer Science

  • Omar Atef Sesa

    Omar Atef Sesa

    Teaching Assistant || Machine Learning Eng. & Researcher || AI | ML

  • Souvik Bhattacharya

    Souvik Bhattacharya

    Product Manager at Meta

  • Anastasiia Strakhova

    Anastasiia Strakhova

    Community Manager at New Native

  • Olesia Zinchenko

    Olesia Zinchenko

    Social Media Manager at NewNative

  • Jakub Zakrzewski

    Jakub Zakrzewski

    Event Manager at New Native

Hackathon FAQ

Who can join the Hackathon?

We welcome domain experts from all industries, not just AI or tech. Successful AI solutions require a combination of technical expertise and domain knowledge. Coding experience is recommended.

Do I need a team?

You are welcome to join as a team or solo, if solo. We encourage you to look for a team before the event. We recommend you to join the Deep Learning Labs Discord channel: and posting in the #looking-for-team channel to get to know your potential future team members.

Do I need a Github account?

It is recommended, that at least one team member has a Github account. You can create one for free if you don't already have one.

Do I have to use Cohere's Generate?

You can use other APIs but with Generate you will be able to get some additional points.

I have other questions.

Feel free to reach us on social media, or through our Discord channel.

Event Schedule

  • To be announced

Submitted concepts, prototypes and pitches

Submissions from the teams participating in the Generative AI Hackathon event and making it to the end 👊

Klurdy XR

Klurdy XR

This is a demonstration of using NLP to create voice-activated experiences for interacting with products using 3D technologies. It uses NLP to generate product descriptions and intent recognition to create actions from voice. It leverages Web Speech API for text-to-speech and ThreeJS for rendering 3D, currently works on Chrome.

Klurdy XR

Sincerely Mr Darcy

Sincerely Mr Darcy

Travel back in time and meet your oldest new friend - Mr. Darcy! Our project is a unique pen pal experience; customers subscribe to snail mail one letter every week. We scan and process the letter, using a combination of Google Cloud OCR and Cohere's LLM. This allows Cohere to generate a response in the style of Mr. Darcy, from Pride and Prejudice. To complete the 18th century feel, we send the result to HandWrytten, a robot handwriting service that mails cards with authentic-looking handwriting. Our users are able to experience the joys of a true 18th century friendship, as the Mr. Darcy bot evolves to match the customer's whims through a long history of conversation. Even in the digital age, sometimes we all need a brief return to the analog systems of the past.

Party Pisters

AI chat bot

AI chat bot

It’s an AI based chatbot, the customers will put their queries and the system will analyze and then provide the best possible answer according to the query.




The solution is based on helping the content writers to easily generate content for their materials. Presently, content creators have to deeply think to write their content which is very time consuming and full of mental stress. This service can tremendously make content creator’s job easy. They can purchase monthly subscription to use tool.

Team selftech



Osusume is a Text-Based Recommendation Engine Powered by Cohere. We are attempting to create a sentiment-based recommendation system using Cohere's Text Embedding and use Text Generation to Explain why it is recommended. We implement Osusume as a framework for people to use their data for more comprehensive implementation for Cohere to be the core processor.


MongoDb Quesries

MongoDb Quesries

To get MongoDB queries (output) as a response to the UI. In other words, MongoDB Query is a way to get the data from the MongoDB database. MongoDB queries provide the simplicity in process of fetching data from the database, it’s similar to SQL queries in SQL Database language.

AI isnt AI

Smarty personal assistant

Smarty personal assistant

Smarty quiets the noise around you so you can work peacefully to get things done. It is a personalized task planner that evaluates the importance and urgency of your tasks, then prioritizes and batches them rigorously so you can focus on accomplishing what matters the most.


Prompt Tune Generation

Prompt Tune Generation

Prompt Tune Generation is a prototype model which has ability to generate music using Cohere prompt by understanding the user input. Using Prompt Tune user can play with different set of Genre as input prompt to the model which will generate music notes followed by a short music clip tuned using custom virtual Keyboard which has single octave. This is one step closer diffusion based model where Generative AI plays a vital role in generating contents on its own.

int elligence



vidSummarizer helps you to analyze sentiment & summarize of your audio & video files into simple text within few seconds. It also increase accessibility for users who are deaf.




Zo:diac is an interactive web app that provides unique, personalized horoscopes on-demand to users. It prompts the user for their information, including their birth date, and then returns a horoscope specific to their astrological information. It then allows the user to specify a topic, which zo:diac will then return additional horoscope content for. This process can be repeated, allowing the user to delve deeper into their astrology by generating new content. Both the initial horoscope reading and followup topic-based horoscopes are created using co:here’s generate endpoint, by modifying the input prefix to get the appropriate output. The application is created using react, and hosted by cloudflare. It can be accessed either on a desktop or mobile browser. The app is available at:

Rowdyruff Boys



This application can convert any given text into a visualization. We use LLMs to convert the text into a structured format, and then we use existing visualization libraries to generate infographics from the structured data. Right now in the demo we have built this end to end workflow for Graphs and Timelines but potentially this same tech can be used to power any infographic generation from raw text.



StoryTimeAI is a innovative, creative application of stable diffusion model ( paired with transformer model( We leverage powerful features of those models in attempt to solve vital problem: storytelling. It's important to recognize crucial drive of humans to create stories. Now, with help of artificial intelligence our stories could get even more creative and picturesque. Think of all the possible aplications of on-demand stories generator. Batteries (and stylish ilustrations) included! Our solution allows parents to tell brand-new fairy tales to their children. Writters, marketing specialists, basically any proffesion or bussines that deals with creating stories would also benefit from




Baskful is a tool to ease mass asset liquidation. The tool is meant to document items that are to be sold on sites such as Amazon and Ebay. Target users include estate sales, moving companies, and company closings. AI is used to generate copy for the products.


Virtual AI Patient

Virtual AI Patient

"Virtual AI Patient" is a new way dedicated to medical students in order to help them practice on their virtual patient so that they can act more professional and much faster when they face a similar cases in the reality.

Virtual AI Patient



DiscernAI is designed to tell you whether a text is misinformation or benign


Project chAI

Project chAI

An AI-based chatbot


Code Generation

Code Generation

We first tried to push the dataset to the API and train the model through Python script but couldn't find any documentations on that. So trained on web platform and also provided dataset as prompts.


I Rene

I Rene

I-Rene Provides CBT for the lovely user using Cohere Conversant AI tool. The NFT is minted for free by the lovely user to track the CBT sessions and be proud of their healing process. It is a free, open-source, specific & effective mental health therapy needed by everyone, anywhere at anytime. The mental health AI chatbot will be developed as a standalone application that users can download and install on their mobile devices or access through a web-based platform. The chatbot will collect and use user feedback to improve its performance and effectiveness. This will involve monitoring user interactions and responses, and using machine learning algorithms to continuously adapt and improve the chatbot's responses and support. The mental health AI chatbot will use sentiment analysis to understand the emotional state of users and react accordingly. For example, if a user is feeling sad or anxious, the chatbot can provide appropriate support and resources to help the user manage their emotions and feelings. The mental health AI chatbot will use entity extraction to provide context-dependent answers and support, rather than just generic responses. This will involve analyzing the user's messages and extracting relevant entities and information, such as the user's goals, concerns, and challenges. The chatbot can then use this information to provide personalized and tailored support. The mental health AI chatbot will be integrated with a decentralized autonomous organization (DAO) and the Metaverse, which is a virtual shared space for communities and organizations. This will enable the chatbot to access and use decentralized resources and data to provide more accurate, relevant, and engaging support to users.

Mental Health AI



Using Cohere's API, we developed a solution to building more dynamic lessons by making lesson content creation easier and more efficient. By creating a more sustainable workflow for teachers, we hope this idea helps to step away from repetitive tasks to maximize class time with unique learning experiences and engage in more meaningful social interactions in the class room. The spark for this project was focused to build a culture of collaboration amongst fellow teachers to design more cross-curricular activities as well as interdisciplinary / multidisciplinary lessons to go beyond the textbook material in order for students to be exposed to more real-world connections for deeper understanding. With the numerous benefits of collaboration amongst peers, working together can exponentially improve educational experiences for teachers similarly to the idea that teachers encourage for their students. This project holds great meaning for us as we are passionate learners ourselves and we believe working together truly produces amazing results. We hope you enjoy it!

LA Hackers

Twitter Helper

Twitter Helper

Twitter Helper uses cohere's Api to helps you increase your tweets engagement with your audience by generating hashtags or mention accounts relevant to your tweets. It can also summarize your long tweets to overcome twitter's 280 characters limitation


Image to Emote

Image to Emote

The system generates emotions from images, primarily intended for game NPCs so that they would react emotionally to the game environment. The sentiment analysis model is an LSTM-based Dense Neural Network that are fed Word2Vec embeddings. The model was trained using generated data from using the prompt: "I felt <emotion> when I saw <img2text>" System Flow: img2txt -> generator -> text2emote -> LSTM+DenseNN The images are passed to a CLIP Interrogator (BLIP + CLIP (ViT-32-B)) to generate text descriptions. Such text descriptions are elaborated by generator to generate emotional responses using the prompts: "When I saw <img2txt output>, I felt emotions such as"


AI Chatbot

AI Chatbot

Chatbots in the healthcare field are providing patient assistance and care. AI-powered medical assistant can book appointment, monitor a patient health status and perform other time-intensive responsibilities such as inventory, billing and claims management . There are three key limitations: 1)Explainability 2)Datarequirement 3)Transferability STATEMENT: To be able to enter a prescription with structured data in a software system, within a comparable time to hand written prescription. IDEA: 1) Automation of handwritten and digital prescriptions to reduce entry time. 2) Improve the effectiveness of customer service terms. 3) Reduce the potential for human error. 4)Collect candid and meaningful customer feedback. 5) Guide customers along the path to purchase. 6) Build stronger customer relationships Chatbots reside in the most commonly used apps in the form of assistants on various websites where they can converse with the users. With advanced machine learning algorithms and natural language processing methods enabled , these chatbots can create maps linking symptoms and diseases. Chatbots in the industry for medical care ,ask some standard questions and help create a profile based on age ,sex, and medical history . They can record the users history and analyze symptoms based on users inputs. They can also use image and voice processing to record and match symptoms against the database using the gathered information it automatically print handwritten and digital prescriptions. Natural language processing Deep learning Context aware processing Intelligent robots Neural networks Fuzzy logic Support vector machines Genetic algorithms Hybrid system


Virtual Story

Virtual Story

Today the number of literature readers is declining worldwide, especially among younger generations, which is affecting overall education level very negatively. This is mostly due to increasing popularity of online social media and gaming activities. However, technological development shouldn't mean for important knowledge to fade away. It is important to digitalize books and cognitive literature and adapt it to modern norms. That why we created Virtual Story app, which is hybrid of books and video games, based on various literature and with help of refined audio-visual and gaming elements, it will make reading process educational like books and engaging, fun and interactive like video games.

Virtual Story

Cover Letter Generator

Cover Letter Generator

Generates the Cover letter Based on prompt with the help of cohere playground API. Feather is AI based model that automatically generates magnificent coverletter within a minute based on prompts feather helps you create eloquent cover letter for your dream.


AGI Chat

AGI Chat

A ChatGPT alternative based on Cohere’s LLM. In the future, intelligent assistants that are smarter than humans will be a part of everyone's lives. They will assist us in our work, help us have fun, and improve our lives overall. And this is already happening with OpenAI's ChatGPT, which received amazing feedback over the last few days. Some even call it a Google killer! However, we want the future of AI assistants to be open and not solely belong to one company. is an initiative to create an open platform for these intelligent assistants. Currently, only Cohere models are supported, but we plan to add customization, switching between different language models, and more. We see as WordPress for AI-powered assistants.




We created an application to ease the lives of team leaders, by creating a fast and effortless pipeline to propagate the needed information to their teams, other than storing trivial information in pills for a more concise backtracking experience. Starting with OpenAI Whisper, we generate a transcription of the meeting, then by crossing the work of Cohere Generate and Classify, we managed to extract the needed information, then we organize them into a comfortable format to make sure they are easily findable. We developed a platform designed that recaps full business meetings and provides concise summaries including all the relevant information, a list of tasks mentioned during the meeting and the questions asked, with the relative answers. We thought this information was the most useful for a team's member, so the leader can send them the information fast, in order to fill a lack of knowledge and consequent slowdowns in the team's productivity.


Baith al suroor

Baith al suroor

Baith al suroor بَیتُ الْسرور (house of happiness in Arabic) 🏡🤖 is deeptech solution the power of artificial intelligence to transform your space. With the Cohere language Command model, it can generate descriptions of your desired design, and the Stable Diffusion generative model creates relevant images and transitional videos to bring your vision to your thoughts.


Teams: Generative AI Hackathon

Check out the rooster and find teams to join at Generative AI Hackathon


1740 /