AI Automation Projects in NairobiAI Automation Projects in Nairobi
Projects
People
Cover image for Currently building autonomous AI systems
Currently building autonomous AI systems that actually survive production — not just the demo. Most AI projects work beautifully in a controlled test and then quietly fall apart on real data, edge cases, and concurrency. I focus on the unglamorous engineering that closes that gap: data validation pipelines, boundary checks, error handling, and knowing exactly where deterministic logic should own the decision instead of the model. Recent work includes agentic workflows built with Python and FastAPI, an LLM reasoning layer for the genuinely ambiguous decisions, and automation orchestrated through Make with MCP. My background is technical support and operations, which means I design for the failure case first — I've spent years watching systems break in ways their builders never anticipated. If you have an AI pilot that impressed everyone in the demo and then stalled on the way to something dependable, that gap is exactly what I build for. Open to Applied AI / AI automation projects.
2
5
332
Cover image for Designed and documented a secure
Designed and documented a secure environment for running Robin, an AI-powered dark web OSINT tool, inside a compartmentalized Qubes OS and Qubes-Whonix setup. The environment was structured to separate research activity, Tor-routed traffic, sensitive credentials, untrusted content, and final reporting. Robin was deployed through Docker inside a dedicated research qube, with traffic routed through sys-whonix and sensitive notes stored separately in an offline vault qube. Disposable qubes were incorporated for opening potentially unsafe links and files. The setup was built around security by compartmentalization rather than relying on a single tool for protection. Particular attention was given to Docker mount restrictions, credential hygiene, network-boundary verification, lawful research scope, and keeping raw research data isolated from personal or client environments. The final result was a repeatable AI-assisted OSINT workflow that supports faster search refinement, result filtering, investigation summarization, and structured reporting while maintaining stronger operational security and clearer separation between collection, analysis, and final output.
0
118