● Available for projects · Karachi, working US hours
I build AI systems that survive production.
RAG pipelines, agent workflows, and automation infrastructure. Designed, shipped, and maintained by the same engineer who runs systems like these in production every day.
Systems, not demos
Every one has constraints, decisions, and what failed first.
A WhatsApp booking agent that cannot double-book
Lives on WhatsApp, answers from the clinic's own records, books appointments and captures leads. A booking can only land on a slot the system offered; the database, not the prompt, prevents double-booking.
A financial research agent for the Pakistan Stock Exchange that shows its sources
Four agents over Qdrant documents, Supabase time-series and PSX prices, fused into cited answers with a confidence score. A three-person final year project.
A lower policy rate reduces financing cost for leveraged industrials [W1]. ENGRO's leverage and coverage are in its latest quarterly report [D3]; recent price action is in the exchange feed [P].
confidence: high · sources agree (docs + prices + web)
An ops hub where the AI can't certify its own claims
Calls, forwarded emails and typed notes become deduplicated, confidence-tagged tasks behind a Slack approval gate. A fact is verified only if it matches what the platform actually sent, never because the model sounded sure.
The judgment is the product
Right-sized tooling
An n8n workflow when that's enough. A LangGraph backend when it isn't. You're paying for the judgment about which one your problem actually needs, not for the most impressive possible architecture.
Production mindset
Error handling, retries, evals, observability. The difference between a demo and a system is everything that happens after the happy path. That's the part I build first.
Direct
No account managers, no handoffs, no "our team will get back to you." You talk to the person who designs, builds, and ships the thing.
Three ways in
System Design Sprint
Your problem in; an architecture doc, tool selection with reasoning and a build plan out. Useful even if someone else builds it.
Fixed-Scope Build
A defined system: RAG pipeline, agent workflow, automation backbone. Scoped and quoted before work starts.
Systems Partner
A retainer to extend, maintain and iterate on systems that have become load-bearing.
Bring me the problem. Leave with how I'd build it.
A 20-minute architecture call. No pitch, no slide deck. If I'm not the right person for it, I'll say so and point you somewhere better.