# Lab

> Current explorations in agentic development, context, retrieval, evaluation, tool protocols, agentic commerce, and ML/data quality.

Lab entries are current explorations and working models. They are not claims of shipped production systems.

- [Agentic Development](https://akiovaska.com/lab/agentic-development.md): Status: Exploring. Practical ways to make coding agents useful inside real engineering constraints.
- [Local RAG](https://akiovaska.com/lab/local-rag.md): Status: Exploring. Exploring private, inspectable retrieval workflows for local technical knowledge.
- [MCP & Tooling](https://akiovaska.com/lab/mcp-tooling.md): Status: Exploring. Exploring small, explicit tool interfaces that connect agents to useful systems.
- [Universal Commerce Protocol](https://akiovaska.com/lab/universal-commerce-protocol.md): Status: Exploring. Exploring how open commerce protocols could let agents act through standardized capabilities instead of platform-specific integrations.
- [Self-Improving AI Agents](https://akiovaska.com/lab/self-improving-ai-agents.md): Status: Exploring. Exploring how agents improve across attempts through execution feedback, verification, memory, and evaluation.
- [ML & Datasets](https://akiovaska.com/lab/ml-and-datasets.md): Status: Exploring. Exploring how raw data becomes a reliable machine-learning dataset, and what has to be true before training starts.