Skip to Main Content

ASAP is an AI-powered agent that enables people to communicate naturally in their local languages and delegate everyday tasks to AI. AI agents are becoming increasingly capable of performing real-world tasks, from discovering products and shopping to ordering food, booking services and making payments. However, most AI experiences are designed around people who can comfortably communicate in English or other dominant languages. In Nigeria alone, hundreds of languages are spoken. Millions of people communicate through their native languages, local expressions, slang and a natural mixture of languages. While they may understand what they want to accomplish, expressing those needs through written English prompts or navigating complex digital interfaces can be difficult. Some instructions are simply easier to explain through speech than typing. ASAP addresses this gap by allowing users to interact with an AI agent through voice notes or text in the languages they naturally speak. Instead of requiring users to translate their thoughts into English or learn how to write effective AI prompts, ASAP is designed to understand their requests, identify their intentions, ask relevant follow-up questions and use connected tools and services to carry out tasks on their behalf. For example, a user could send a voice note in Yoruba, Hausa or Igbo asking ASAP to find a product, check its price or help them make a purchase. The agent interprets the request, interacts with relevant services and guides the user through completing the task. What makes ASAP different is that it goes beyond speech recognition, translation or conversational responses. It connects multilingual communication with agentic execution, allowing people to move from expressing a need in their own language to getting something done. We are starting with Nigeria and focusing on making AI-powered services accessible across its diverse linguistic communities, with a broader vision of extending this experience to other African languages and multilingual populations. Our belief is simple: people should not have to change the way they communicate to access AI. AI should learn to understand people, in the languages they naturally speak, and help them get things done.

Team

herren

More from Meta Global AI Developer Hackathon

Cardo turns the world around you into Kurdish flashcards. Kurdish is spoken by tens of millions of people, but it has very few learning tools, and most…

Kurdolingo project preview

oqed is an LLM-guided superoptimizer for x86-64. You point it at a C or C++ project and it does the rest: - builds the project and runs its workload…

oqed project preview

Playtest Agent plays a game from screenshots, looks for bugs, then replays each report and has a judge check it. I make games alone. Solo developers and…

Adrian project preview

Open-source npm malware detection on Meta's models: a live monitor that flags new malware about a day before the public lists, a Muse agent that investigates…

Gatekeeper project preview

Video2URDF turns one short phone video of a real articulated object (a laptop lid, a drawer, a desk lamp, a microwave door) into a measured URDF/MJCF a robot…

Video2URDF project preview

Glimmer Scope opens up Muse Glimmer 30B so you can see and steer the concepts it thinks with. I trained sparse autoencoders on nine layers of Glimmer's…

Kroonen AI project preview