# How Bytefuse uses Weights & Biases

**50K**: “approximately 50K teachers and Grade 12 learners who used Maski to prepare for their final exams”

As published on [wandb.ai](https://wandb.ai/site/customers/bytefuse/), April 2025. Captured by usedby on 2026-11-11.

- Company: [Bytefuse](https://www.usedby.ai/companies/bytefuse.md)
- Tool: [Weights & Biases](https://www.usedby.ai/tools/weights-and-biases.md)
- Industry: [Artificial Intelligence](https://www.usedby.ai/companies/industry/artificial-intelligence.md)
- Teams: ML team

## The use case: how Bytefuse deploys Weights & Biases

Bytefuse uses W&B Weave to trace and debug the system of agents behind Maski, its WhatsApp-based AI tutor for South African students and teachers. It also uses Weave to compare custom and third-party models, collect user thumbs-up/thumbs-down feedback, and uses W&B Models and Registry to log experiments and automate model deployment and regression testing.

Summary written by usedby from the source page, in English. The figures are those of Weights & Biases and Bytefuse, not ours.

> Built on a PydanticAI framework, Maski’s agentic workflow switches between custom LLMs and providers, depending on the use case that’s needed. Van der Merwe and his team have fine-tuned some of their own custom models as well, and found that it was extremely hard to monitor how the actual LLMs were performing, especially at scale.

> W&B Weave Traces makes it super easy to see from user input what every single route that message went through in our agentic system until it got back to the user. So when something goes wrong, it's a very easy debug. Especially in this LLM world, where things are so unpredictable, you really need to know what's going on. That's where W&B fits in for us.
>
> Ruan van der Merwe, Co-founder and Technical Lead

Source: [wandb.ai](https://wandb.ai/site/customers/bytefuse/), captured 2026-10-08.

## Weights & Biases users in Artificial Intelligence

- [Aleph Alpha](https://www.usedby.ai/companies/aleph-alpha.md) — Confirmed
- [Captur](https://www.usedby.ai/companies/captur.md) — Confirmed
- [Cohere](https://www.usedby.ai/companies/cohere.md) — Confirmed
- [Decart](https://www.usedby.ai/companies/decart.md) — Confirmed
- [Gretel](https://www.usedby.ai/companies/gretel.md) — Confirmed
- [Inverted AI](https://www.usedby.ai/companies/inverted-ai.md) — Confirmed

## What usedby checked

We compared the story with its live page on 2026-11-11.

- Checked: the publication date is read from the page’s own metadata, never guessed.
- Checked: Bytefuse uses Weights & Biases. Confirmed line. Latest check across sources: 2026-11-20.
- Not checked: the result itself. We quote it; we did not measure it.

---
Source: https://www.usedby.ai/case-studies/bytefuse-weights-and-biases · How we check: https://www.usedby.ai/methodology
