A little more of the work
Projects & Research
Working papers and research experience in AI governance, agent security, speech AI, and neuroscience. Open an entry for the question, methods, contribution, and limitations.
Research
- Open folderWorking paper
AI at the Last Mile: Security, Governance, and the Risk of Automated Exclusion
Examining how AI security and governance can protect a system while making it harder for people in low-resource environments to access services or recover from an automated decision.
- Open folderWorking paper
Fault Propagation and Risk Containment in Agentic AI Systems
A systems framework for understanding how a local reasoning, tool, or authorization fault can travel through an agent's action loop, and where containment should stop it.
- Open folderResearch initiative
Paza: Speech Data for Low-Resource African Languages
Research support for speech-data collection, quality control, and ASR evaluation where suitable language datasets are scarce.
- Open folderResearch initiative
Speech AI: Linguistic Variation and Fair Evaluation
Evaluation work that separates natural language-transfer patterns from speech pathology in code-switched, noisy African speech.
- Open folderResearch initiative
Computational Speech Therapy Analysis
Final-year research into speech-analysis approaches that preserve meaningful speech patterns and provide phoneme-level feedback.
- Open folderResearch initiative
Sensory Neuroscience in a Natural Environment
An observational study asking whether sensory-neuroscience findings from laboratory models generalize to free-ranging rhinoceroses.