I love many aspects of being an engineer but one thing that stands out is user feedback. Nothing really comes close to it.
You get to understand where the user's mind is at, how they interact with your system, and most importantly - where you got it wrong. That data is invaluable. No amount of internal testing replaces it.
This morning a user flagged something. Within minutes it was addressed and deployed. Not because I'm fast. Because when someone takes the time to tell you what's broken, the least you can do is take it seriously.
Every piece of feedback makes the system better. Every bug report is a contribution. Every 'this doesn't feel right' is someone who believes in what you're building enough to help you build it better.
We are listening. We are improving. Every single day.
https://t.co/HtIJtCuoOY
#AIforAfrica
I love many aspects of being an engineer but one thing that stands out is user feedback. Nothing really comes close to it.
You get to understand where the user's mind is at, how they interact with your system, and most importantly - where you got it wrong. That data is invaluable. No amount of internal testing replaces it.
This morning a user flagged something. Within minutes it was addressed and deployed. Not because I'm fast. Because when someone takes the time to tell you what's broken, the least you can do is take it seriously.
Every piece of feedback makes the system better. Every bug report is a contribution. Every 'this doesn't feel right' is someone who believes in what you're building enough to help you build it better.
We are listening. We are improving. Every single day.
https://t.co/HtIJtCuoOY
#AIforAfrica
Babel-Virahsawmy is named after Dev Virahsawmy (1937–2023) - the poet who translated Shakespeare, the Bible, the Bhagavad Gita and the Quran into Mauritian Kreol, insisting it was a language, not a dialect.
Our Kreol model carries his fight into the age of AI.
As Africans, we have always passed down knowledge and wisdom through oral tradition - from the scholars of Timbuktu to the storytellers of today.
So when we built Babel, we refused to give our models cold, forgettable codenames. Each one carries the name of a son or daughter of the motherland - a poet, a playwright, a linguist, a keeper of stories - who loved their language so fiercely that history could not forget them.
Babel-Virahsawmy honours Dev Virahsawmy, who spent his whole life insisting that Mauritian Creole was a language and not a lesser tongue - translating Shakespeare, the Bible, the Bhagavad Gita and the Quran into Creole so his people could meet the world in their own voice.
Mariama Bâ, who gave Senegalese women a literature of their own.
Chinua Achebe, who made the world read Africa on Africa's terms.
Hadraawi, the "Master of Speech," who would not stop writing the poems that put him in prison.
They were told their languages were too small to carry literature, science, scripture. They refused to believe it.
We carry that same refusal into the age of AI. Every time someone speaks to Babel in their mother tongue and is understood, the work these men and women began continues.
We didn't borrow their names for prestige. We took them so that a child using Babel might one day ask, "Who was Virahsawmy?" - and go and find out.
Their legacy lives on.
Now it answers back, in the languages of the continent.
https://t.co/w14Pq4nVa0
@DarajaAI
#AIforAfrica
As Africans, we have always passed down knowledge and wisdom through oral tradition - from the scholars of Timbuktu to the storytellers of today.
So when we built Babel, we refused to give our models cold, forgettable codenames. Each one carries the name of a son or daughter of the motherland - a poet, a playwright, a linguist, a keeper of stories - who loved their language so fiercely that history could not forget them.
Babel-Virahsawmy honours Dev Virahsawmy, who spent his whole life insisting that Mauritian Creole was a language and not a lesser tongue - translating Shakespeare, the Bible, the Bhagavad Gita and the Quran into Creole so his people could meet the world in their own voice.
Mariama Bâ, who gave Senegalese women a literature of their own.
Chinua Achebe, who made the world read Africa on Africa's terms.
Hadraawi, the "Master of Speech," who would not stop writing the poems that put him in prison.
They were told their languages were too small to carry literature, science, scripture. They refused to believe it.
We carry that same refusal into the age of AI. Every time someone speaks to Babel in their mother tongue and is understood, the work these men and women began continues.
We didn't borrow their names for prestige. We took them so that a child using Babel might one day ask, "Who was Virahsawmy?" - and go and find out.
Their legacy lives on.
Now it answers back, in the languages of the continent.
https://t.co/w14Pq4nVa0
@DarajaAI
#AIforAfrica
Seeing Babel power the translation layer of a pipeline like this - confidence, back-translation, a verdict you can trust - is exactly the future we’re building toward.
Translation you can measure is translation that can carry weight. Beautiful work @ianktoo
This is what the bridge is for, @ianktoo. Emergency translation where a wrong word costs more than silence - built by someone who measures trust before he ships it.
Proud to be the engine behind tafsiri.
Keep building!
Came across @DarajaAI and their African language models while building Crea (an emergency response app).
That stopped me.
Language is a barrier in emergencies, a wrong translation can be worse than none.
So I built tafsiri. An eval pipeline that runs on @DarajaAI API as translation engine. Right now, it translates into Swahili, Yoruba, Amharic (rides on Daraja).
Evaluates each output confidence (Daraja's own confidence), back-translation (asks Daraja the reverse translation) and LLM-as-judge (any frontier large language model).
Not just a translation. A score you can trust.
It's < 5 days old.
Open source. No stats yet. Try it out!
https://t.co/PzpYk2cosw
Over the past few weeks I have had the pleasure of interacting with brothers and sisters from all over Africa building solutions for the motherland.
@ianktoo is one of them.
He has built Crea - an emergency response application. But he didn't stop there, he took it one step further by building tafsiri - a pipeline that scores every output for trust, not just fluency. Because in an emergency, a wrong translation can cost more than no translation at all.
That he chose Babel as the engine behind that work is an honour. But what moves me more is the instinct - a builder already asking the hardest question there is: can this be trusted with a life?
This is exactly why we built @DarajaAI. A bridge is only worth building if people cross it. Ian crossed it, and built something of his own on the other side.
Impressive work!
https://t.co/yEyjO99vIx
Came across @DarajaAI and their African language models while building Crea (an emergency response app).
That stopped me.
Language is a barrier in emergencies, a wrong translation can be worse than none.
So I built tafsiri. An eval pipeline that runs on @DarajaAI API as translation engine. Right now, it translates into Swahili, Yoruba, Amharic (rides on Daraja).
Evaluates each output confidence (Daraja's own confidence), back-translation (asks Daraja the reverse translation) and LLM-as-judge (any frontier large language model).
Not just a translation. A score you can trust.
It's < 5 days old.
Open source. No stats yet. Try it out!
https://t.co/PzpYk2cosw
I love what @KelvRoman is working on @DarajaAI
It's a bridge (daraja), as we call it in Kiswahili. A bridge to underserved/overlooked languages in Africa!
Truly inspired!
Go @KelvRoman !
MedScan - medical imaging AI that screens for brain tumors, cervical cancer, and diabetic retinopathy and delivers results in any of 23 languages. Not replacing doctors. Reaching the patients they can't.
https://t.co/Yym3otHdMc
#AIforAfrica
A mother in Addis Ababa brings her child to a clinic. The doctor suspects something but the equipment to confirm is in the capital. The referral process takes weeks. The mother speaks Amharic. The referral system speaks English.
What if the first screening happened right there? In seconds. In Amharic.
That's MedScan. Medical imaging AI that screens and delivers results in the patient's own language. Not replacing the doctor - accelerating the moment the doctor says 'I need to act now.'
Brain tumors. Cervical cancer. Diabetic retinopathy. Three screenings. 23 languages. One mission.
https://t.co/HtIJtCuoOY | @DarajaAI
#AIforAfrica
A mother in Addis Ababa brings her child to a clinic. The doctor suspects something but the equipment to confirm is in the capital. The referral process takes weeks. The mother speaks Amharic. The referral system speaks English.
What if the first screening happened right there? In seconds. In Amharic.
That's MedScan. Medical imaging AI that screens and delivers results in the patient's own language. Not replacing the doctor - accelerating the moment the doctor says 'I need to act now.'
Brain tumors. Cervical cancer. Diabetic retinopathy. Three screenings. 23 languages. One mission.
https://t.co/HtIJtCuoOY | @DarajaAI
#AIforAfrica
A Wolof speaker in Dakar can now message a Zulu speaker in Durban. Without English. Without a translator. Without anyone in between.
The continent with the most borders now has the fewest barriers.
Live on translate and API👇🏾
@wgathu@KelvRoman There are 3 ways currently:
1. To converse with Babel, go to https://t.co/HxdZLDe7oO
2. To get your translations from Babel, go to https://t.co/JiAjCEI7DX
3. To integrate Babel into your app through the API, go to https://t.co/uW8eLoy2lr
“Africa has the most countries, the most borders, and the most languages of any continent. Technology has treated that diversity as a problem.
We built it as a feature.”
https://t.co/Yym3otHdMc
#AIforAfrica
A grandmother in Senegal speaks Wolof. Her granddaughter married a Tanzanian and moved to Dar es Salaam. The granddaughter's children speak Swahili. The grandmother and her grandchildren have never been able to write to each other without someone in the middle translating.
Until today.
Daraja's Bridge is live. Any language to any language. Wolof to Swahili. Lingala to Yoruba. Hausa to Zulu. Creole to Amharic. 23 languages across Africa, Europe, Middle East and Asia.
Africa has the most countries, the most borders, and the most languages of any continent. Technology has treated that diversity as a problem.
We built it as a feature.
The bridge is open. Everyone crosses.
https://t.co/ntzi8nreC8 | API: https://t.co/HtIJtCuoOY
https://t.co/HtIJtCuoOY
#AIforAfrica
A grandmother in Senegal speaks Wolof. Her granddaughter married a Tanzanian and moved to Dar es Salaam. The granddaughter's children speak Swahili. The grandmother and her grandchildren have never been able to write to each other without someone in the middle translating.
Until today.
Daraja's Bridge is live. Any language to any language. Wolof to Swahili. Lingala to Yoruba. Hausa to Zulu. Creole to Amharic. 23 languages across Africa, Europe, Middle East and Asia.
Africa has the most countries, the most borders, and the most languages of any continent. Technology has treated that diversity as a problem.
We built it as a feature.
The bridge is open. Everyone crosses.
https://t.co/ntzi8nreC8 | API: https://t.co/HtIJtCuoOY
https://t.co/HtIJtCuoOY
#AIforAfrica
The continent with the most borders now has the fewest barriers.
Daraja's Bridge is live - 23 languages, any to any. Wolof to Swahili. Lingala to Zulu. Chinese to Amharic. No English required.
Try it now at https://t.co/JiAjCEI7DX or build with our API.
https://t.co/Yym3otHdMc
I named my company Daraja. Swahili for bridge.
For months, that name was an aspiration. Each Babel model spoke one language and one language well. Creole. Swahili. Yoruba. Twelve languages, each a specialist, each connecting only to English.
But Africa doesn't run on English.
A trader in Kinshasa speaks Lingala. Her supplier in Lagos speaks Yoruba. A nurse in Addis speaks Amharic. Her patient's family speaks Somali. The real connections that Africa needs aren't language-to-English. They're language-to-language.
So I built the Bridge - 23 languages supported, any language to any language across Africa, Europe, Middle East and Asia. Live today.
A Wolof speaker in Dakar can now message a Zulu speaker in Durban. Without English. Without a translator. Without anyone in between.
The continent with the most borders now has the fewest barriers.
Live on translate and API
https://t.co/SjA7P1ewVM
#AIforAfrica
I named my company Daraja. Swahili for bridge.
For months, that name was an aspiration. Each Babel model spoke one language and one language well. Creole. Swahili. Yoruba. Twelve languages, each a specialist, each connecting only to English.
But Africa doesn't run on English.
A trader in Kinshasa speaks Lingala. Her supplier in Lagos speaks Yoruba. A nurse in Addis speaks Amharic. Her patient's family speaks Somali. The real connections that Africa needs aren't language-to-English. They're language-to-language.
So I built the Bridge - 23 languages supported, any language to any language across Africa, Europe, Middle East and Asia. Live today.
A Wolof speaker in Dakar can now message a Zulu speaker in Durban. Without English. Without a translator. Without anyone in between.
The continent with the most borders now has the fewest barriers.
Live on translate and API
https://t.co/SjA7P1ewVM
#AIforAfrica