AI ENGINEER · ISLAMABAD · UTC+5
Abdul Rehman Baber — AI Engineer
AI and full-stack engineer with about four years building and operating production LLM systems. My lane is the reliability side — agents and MCP, including proactive, tool-using assistants on OpenClaw and Hermes — plus RAG, and the evals, observability and cost work that keep those systems honest, with a sharper edge in AI-search visibility (GEO).
How I work
three things I bringReliability over demos
Evals with negative controls, observability you can't fool, and RAG that's allowed to say I don't know. The unglamorous production layer most AI demos skip.
geocheck's eval harness →Agents that take action
MCP tooling and proactive assistants on OpenClaw and Hermes — subagents, memory, real tool use, and updates over channels like WhatsApp. Not chatbots; systems that do things.
One server, four clients →AI-search visibility (GEO)
Measuring whether and how a brand gets mentioned and cited inside AI answers — and moving those numbers. The specialty most engineers don't have yet.
See the work →Selected work
Currently
what I'm building nowCiteStreak + the GEO niche
Building CiteStreak, a GEO / AI-visibility monitoring SaaS — tracking whether and how brands get mentioned and cited across roughly six AI answer engines. The platform foundation is tested and shipped; the engine adapters and product surface are the work in front of me. Alongside it I'm closing the gap on a fully formal eval harness — held-out sets, Precision@K, judge-vs-human agreement, a CI regression gate — already partly demonstrated in geocheck.
Open source
🌱 early · 🌿 maintained · 🌳 referenceGlyphs mark how settled each repo is, not its importance.
