---
title: "Matthew Wisdom (@matt-wisdom) | Hashnode"
description: "Backend and AI Engineer. Read the latest articles by Matthew Wisdom on Hashnode."
url: "https://hashnode.com/@matt-wisdom"
---

@matt-wisdom

# Matthew Wisdom

@matt-wisdom · Nigeria · Joined October 2021

Backend and AI Engineer

[Website](https://matt-wisdom.github.io/)

### [The Tool Call Problem](https://bitsofwisdom.hashnode.dev/the-tool-call-problem?utm_source=hashnode&utm_medium=feed)

One of the things I spend a lot of time thinking about at work is what happens when an AI assistant decides to call a tool it should not, or calls the right tool with the wrong arguments. The assistan

9 min read · [bitsofwisdom.hashnode.dev](https://bitsofwisdom.hashnode.dev/the-tool-call-problem?utm_source=hashnode&utm_medium=feed)

[Jul 30](https://hashnode.com/posts/the-tool-call-problem/6a6bdc27fd443ab049b8b5bf)

### [Version Everything: The ML Practice a Lot of Projects Skip](https://bitsofwisdom.hashnode.dev/version-everything-the-ml-practice-a-lot-of-projects-skip?utm_source=hashnode&utm_medium=feed)

A long time ago, I was working on a model and doing what most people do early on: iterating fast, making transformations directly on the dataset to try to improve results, retraining, checking metrics

6 min read · [bitsofwisdom.hashnode.dev](https://bitsofwisdom.hashnode.dev/version-everything-the-ml-practice-a-lot-of-projects-skip?utm_source=hashnode&utm_medium=feed)

[Jul 25](https://hashnode.com/posts/version-everything-the-ml-practice-a-lot-of-projects-skip/6a6533139184385a72cc4e90)

### [Building Arishem: A Multi-Agent System That Tries to Hack Your AI App](https://bitsofwisdom.hashnode.dev/building-arishem-a-multi-agent-system-that-tries-to-hack-your-ai-app?utm_source=hashnode&utm_medium=feed)

AI agents are everywhere right now. They read emails, write code, and make decisions on your behalf. I use them a lot, for work and for side projects. And the more I use them the more one question kep

4 min read · [bitsofwisdom.hashnode.dev](https://bitsofwisdom.hashnode.dev/building-arishem-a-multi-agent-system-that-tries-to-hack-your-ai-app?utm_source=hashnode&utm_medium=feed)

[Jul 21](https://hashnode.com/posts/building-arishem-a-multi-agent-system-that-tries-to-hack-your-ai-app/6a5f62a92717d539179a933a)

### [We Built a Nigerian Language Search Model That Beat the State of the Art.](https://bitsofwisdom.hashnode.dev/built-a-nigerian-language-search-model-that-beat-the-state-of-the-art?utm_source=hashnode&utm_medium=feed)

I have been building RAG systems for a while now. One thing that kept coming up was how existing embedding models can have real deficiencies when it comes to Nigerian languages. To give you a sense of

6 min read · [bitsofwisdom.hashnode.dev](https://bitsofwisdom.hashnode.dev/built-a-nigerian-language-search-model-that-beat-the-state-of-the-art?utm_source=hashnode&utm_medium=feed)

[Jul 11](https://hashnode.com/posts/built-a-nigerian-language-search-model-that-beat-the-state-of-the-art/6a5214fe988a21a61527f98e)

### [LLM Systems in Production: Evaluating LLM Applications with DeepEval](https://bitsofwisdom.hashnode.dev/llm-systems-in-production-evaluating-llm-applications-with-deepeval?utm_source=hashnode&utm_medium=feed)

Learn how to evaluate LLM applications in production using DeepEval. Covers RAG pipeline testing, agent evaluation, and CI integration with examples.

6 min read · [bitsofwisdom.hashnode.dev](https://bitsofwisdom.hashnode.dev/llm-systems-in-production-evaluating-llm-applications-with-deepeval?utm_source=hashnode&utm_medium=feed)

[Jun 26](https://hashnode.com/posts/llm-systems-in-production-evaluating-llm-applications-with-deepeval/6a3efa0a607a454e427f232f)