# Research

> Canonical: https://www.overmindlab.ai/research

Written by humans

Blogs, research and in-depth write-ups explored by our team.

**Featured:** [Think Smaller](https://www.overmindlab.ai/research/think-smaller)

## Articles

- [How to train your agent](https://www.overmindlab.ai/research/how-to-train-your-agent): Learnings from building, deploying and improving agents in production.
- [Unwrapping the wrappers](https://www.overmindlab.ai/research/who-trains-their-own-models): Application layer companies are training their own models. Why?
- [How do you turn traces into a training dataset?](https://www.overmindlab.ai/research/traces-to-training-dataset): Every agentic system can create its own training data.
- [Prompt engineering vs fine-tuning](https://www.overmindlab.ai/research/prompt-engineering-vs-fine-tuning): A perspective on when to tinker with the prompt, and when to train your own model.
- [What are the different types of fine-tuning?](https://www.overmindlab.ai/research/types-of-fine-tuning): What's the difference between SFT, LoRA and Distillation?
- [Open-weights LLMs vs frontier APIs](https://www.overmindlab.ai/research/open-weights-vs-frontier-apis): Own your intelligence, or rent the API?
- [The anatomy of an AI agent](https://www.overmindlab.ai/research/anatomy-of-an-ai-agent): An agent has a model, loop, tools and memory.
- [So, you have observability. Now what?](https://www.overmindlab.ai/research/so-you-have-observability-now-what): Observing your agent is table stakes.
- [Secret Agent Overmind](https://www.overmindlab.ai/research/secret-agent-overmind): Your agent is the most documented system in your engineering org and yet you can't answer simple questions.
- [Think Smaller](https://www.overmindlab.ai/research/think-smaller): Frontier models are overkill for most agent tasks. Specialised small language models beat them on cost, latency, and accuracy.

Subscribe: https://www.overmindlab.ai/research/feed.xml