Work
-
Useful Apply
AI agent that runs the entire job search in one app: find roles, check fit, generate the full application, track it. Solo-built SaaS, live with paying customers.
-
Useful Brain
Company knowledge agent that cites every answer and refuses when the evidence is not there.
-
Useful Voice
macOS app for voice dictation anywhere on the system.
-
Useful Build
Applied AI product studio. Custom software, agents and workshops.
More projects
-
Kursfind
Two-sided AI marketplace matching German job seekers with funded vocational training courses.
-
Swipekit
AI carousel generator for LinkedIn and Instagram posts.
-
Safwa
Live stream Q&A comment filter for Persian and Dari speakers.
-
Pulse
Chrome extension that tracks work hours automatically.
-
Agent skills
Open toolkit of Claude agent skills: Skill Scanner, Design Craft, Premium UI Pass and Prompt Optimizer.
Experience
-
Product Builder Useful Build
Jul 2026 to now
Building AI products and systems at Useful Build: knowledge assistants, workflow automation and internal tools that take repetitive work off company teams.
-
AI Specialist Nature Heart
May 2026 to Sep 2026
Built 10+ internal AI tools and apps, including Aktionsplaner, an AI-powered campaign forecasting app for Shopify, an onboarding app, a payment register, a newsletter-to-blog pipeline and an A/B test evaluation tool.
-
Founder Useful Apply, Karko AI Inc.
Jan 2026 to May 2026
Solo founder. Concept to launched product, 380+ commits, live with revenue.
-
Founder Wasim Academy
2023 to 2025
AZAV-certified training company, 30,000+ EUR course revenue.
-
E-commerce Self-employed
2022 to 2025
Ran Amazon stores in 4 markets, 150,000+ EUR revenue.
Writings
-
From 41 hidden questions to zero: making a live Q&A filter safe to trust
A filter that sorts a live stream's Dari comments into a question queue used to hide real questions. With one strong model and a probability check before every hide, it hid none of 618 real questions and none across three recorded broadcasts.
-
7.8 times less CPU: a live-chat question filter at 400 comments
A Chrome extension that sorts a live stream's comments into a question queue was slowing the broadcast tab down as the chat grew. After four AI models audited it and seven rounds of fixes, a 400-comment session takes 7.8 times less processor time.
-
From six confusing cards to none: fixing a live Q&A filter by replay
A teacher's live-stream question filter showed cards labelled "this person's 3rd question" that were neither hidden nor joined. Replaying the recorded broadcast through the real system reproduced all six, found the cause, and nine replays later the fix scored 115 of 115 with no real question hidden.
-
Wrongly hidden questions 4.0% to 1.9%: the test design chose the model
Twenty-eight AI models were scored on sorting a live stream's Dari comments into a question queue. The best combination cut wrongly hidden questions from 4.0% to 1.9% on the test, and four choices in how the test was built changed which model came out on top.
-
From 116 to 118 of 120: why I threw away the fix that scored perfectly
A company knowledge assistant that only quotes its documents reached 118 of 120 (98.3%) on its live test. The first fix repaired all four misses on replay and was discarded anyway, because it only worked for this set of documents.
-
From 72% to 95%: fixing an assistant that only quotes its sources
A company knowledge assistant that answers only in sentences quoted from its documents went from 72% to 95% correct on a 120-question test, without loosening a single scoring rule.
-
Same score, one ninth the price: choosing a knowledge assistant's model
Five language models ran the same 120-question test behind a company knowledge assistant that only quotes its sources. The cheap one tied the expensive one at 95.0% correct, and two big-name models could not finish the warm-up.