# Wasim Jalali

> Applied AI engineer in Germany. I build production AI products end to end with AI coding agents: full-stack apps, internal tools and agent systems. Based in Kaiserslautern, Germany.

Wasim Jalali is a solo founder and applied AI engineer. He built Useful Bot (bot.usefulbuild.com), an open-source team of AI bots for the Mac, Useful Apply (usefulapply.com), an AI agent that runs the whole job search, and Useful Brain, a grounded, citation-first RAG agent on Cloudflare Workers. He works with AI coding agents (Claude Code, Codex, Cursor) and writes about evals, model selection and shipping AI products. Each writing below is also available as plain markdown at the same URL with `index.md` appended, and all of them together at https://wasimjalali.com/llms-full.txt.

## Writings

- [Changing the AI model cut made-up claims in job applications](https://wasimjalali.com/writings/from-24-made-up-claims-to-1-changing-the-model-behind-job-applications/index.md): Asked about skills an applicant didn't have, the old model made up a claim in 24 of the 33 answers a strict checker read. Claude Haiku 5.5 did it once in 29.
- [How I made a live-chat helper almost 8 times lighter](https://wasimjalali.com/writings/7-8-times-less-cpu-a-live-chat-question-filter-at-400-comments/index.md): A Chrome extension that sorts viewers' questions was slowing the teacher's laptop. Seven rounds of fixes cut its work 7.8 times.
- [Why I threw away the fix that scored perfectly](https://wasimjalali.com/writings/from-116-to-118-of-120-the-fix-i-threw-away/index.md): A company Q&A assistant now gets 118 of 120 questions right, with a fix that isn't tied to the test's own documents.
- [How I stopped an AI from hiding real questions](https://wasimjalali.com/writings/from-41-hidden-questions-to-zero-making-a-live-qa-filter-safe-to-trust/index.md): A filter for a live Q&A used to hide 41 of 618 real questions. A second, careful check brought that to zero.
- [Replaying a live broadcast to fix a confusing bug](https://wasimjalali.com/writings/from-six-confusing-cards-to-none-fixing-a-live-qa-filter-by-replay/index.md): Six cards on screen made no sense to the teacher. Replaying the broadcast found why, and the ninth replay got all 115 comments right.
- [I tested 28 AI models, and the test picked the winner](https://wasimjalali.com/writings/wrongly-hidden-questions-4-0-to-1-9-percent-the-test-design-chose-the-model/index.md): How the way you test changes which model looks best, and how wrongly hidden questions fell from 4.0% to 1.9% on the test.
- [The cheaper AI model did the same job for a ninth of the price](https://wasimjalali.com/writings/picking-a-model-for-a-grounded-rag-agent/index.md): Five models took the same 120-question test. The cheap one tied the expensive one at 95%.
- [Teaching an assistant to answer only from its sources](https://wasimjalali.com/writings/from-72-to-95-repairing-a-grounded-rag-agent/index.md): From 72% to 95% correct answers, without changing how the answers were graded.

## Optional

- [Landing page](https://wasimjalali.com/): Selected work, experience and contact
- [All writings](https://wasimjalali.com/writings/): Every post, newest first, grouped by month
- [RSS feed](https://wasimjalali.com/rss.xml)
- [GitHub](https://github.com/wasimjalali)
- [LinkedIn](https://www.linkedin.com/in/wasimjalali)