Skip to content
Muhammet Şafak
tr
The Devrazzi radar — a line running from source feeds to event merging, to a 0-100 score by formula, to a Turkish explanation that has passed the validation gate; Critical, High, Medium and Low band labels

Devrazzi

Ongoing Side Publications

Devrazzi is an engineering intelligence radar for software engineers. It tracks releases, security vulnerabilities (CVE/NVD, GHSA, OSV, CISA KEV), deprecation and EOL announcements, and RFCs, merges records describing the same event, gives every event a 0-100 score with a deterministic formula and explains the impact in Turkish. The language model makes no contribution to the score; it only writes the explanation, and no explanation is published until it passes citation, CVE, version and package validation. It is published on the web only and in Turkish only.

Role
Founder & Developer
Duration
October 2026 — Ongoing

Technologies

Laravel PHP PostgreSQL RabbitMQ Redis Livewire Filament Anthropic Claude OpenAI Google Gemini DeepSeek

Skills

AI Systems Engineering LLM Gateway Design Provider Fallback Output Validation Deterministic Scoring Event Correlation Cost Control Data Pipeline Design

Devrazzi is an engineering intelligence radar I built to track meaningful changes across the software ecosystem. It tracks the releases in a catalogue of about 2000 projects, CVE/NVD, GitHub Security Advisories and OSV records, the CISA KEV list, deprecation and EOL announcements, and RFCs; records describing the same event are merged into a single event. Every event is scored from 0 to 100 by a deterministic formula and falls into the Critical, High, Medium or Low band; the components of the score are visible on every event page and the rules are written at devrazzi.com/puanlama. The score is the same for everyone; the user only filters. The product is published on the web only and in Turkish only.

I deliberately kept the language model’s role narrow: it makes no contribution to the score, it only writes the Turkish explanation of the impact. A Haiku-class model matches news to events and a Sonnet-class model writes the explanation; in the Low band no model is called for the explanation, and the explanation is built from the sources with a fixed template. Calls go through a single gateway, and every job type has its own provider order and fallback chain; the target for monthly LLM spend is 100-300 USD, and the ceiling is enforced with a counter in PostgreSQL. Every explanation passes a validation gate before it is published: it must cite at least one source, and the CVE, version and package names it uses must appear in the source text. An event that fails drops into review; a Critical event, though, is published with a template noted as automatically generated.

This architecture is a concrete example of what I do and don’t have the model do in an AI-assisted system. It is built on Laravel, with PostgreSQL and RabbitMQ; it was rewritten from scratch on 13 October 2026 and went live on 14 October 2026. I’m leaving a known limit open: the model’s capped contribution to the score is off, because it did not clear the measurement threshold on the golden set; as a result, deprecation, EOL and RFC events are tracked but stay below the publishing threshold today. The next job is to improve agreement on deprecation detection and measure the contribution again.

More Projects

All projects
academia.sh lesson screen — the curriculum/course/topic/lesson hierarchy, a panel showing theory and the field problem flowing in the same lesson text, full-text search and certificate field-freezing summaries

Founder & Author

Tier: Active Development

academia.sh is a learning platform with free, no-signup lessons that never separates a lesson's theory from a real problem from the field. It's presented through a curriculum-course-topic-lesson hierarchy, progress and quizzes are measured per lesson without splitting theory from problem, and full-text search runs on Postgres; the course-end exam, certificates and study assistant sit in a Pro tier. Content lives in a separate GitHub repo; the first field is computer science, and the model was designed multidisciplinary from the start.

Laravel PHP Livewire +6 more
September 2026 — Ongoing
Garajdaş architecture diagram — a resolution comparison between a single make-level club and multiple make-model-level clubs, arrows from the schema's sole owner, the Laravel API, to the web (Next.js) and mobile (Expo/React Native) clients, the five completed MVP phases and a 97-test badge

Garajdaş

Ongoing

Founder & Developer

Tier: Active Development

Garajdaş is a community platform where every car make-and-model has its own club, keeping internal-combustion and electric vehicles under one roof. A single API schema is shared by the web (Next.js) and mobile (Expo/React Native) clients, the design system is defined in one file and synced by hand. The MVP phases are closed, the API has 97 tests; the platform is live.

Laravel PHP PostgreSQL +6 more
September 2026 — Ongoing
Qurandia matching engine — comparison bars showing number matching at 0-14% consistency against text fingerprinting at 91-99%, a nine-tile stat grid with surah, verse, translation, word, root, tafsir and hadith counts, PostgreSQL full-text search and Turkish translation coverage badges

Qurandia

Ongoing

Founder & Developer

Tier: Active Development

Qurandia is a free, open reading and research resource that matches hadith datasets that don't know each other, trusting not a number but the letter-level fingerprint of the text itself; Quran- and hadith-centred. Translation, word-by-word analysis, tafsir, asbab al-nuzul, the hadith corpus and search all sit under one roof; direct number matching is only 0-14% consistent, while text fingerprinting pushes matching up to 91-99%. Turkish hadith translation coverage stands at 83% today.

Laravel PHP Livewire +7 more
September 2026 — Ongoing

Search the site

Start typing to search posts, projects and pages.

Esc to close Powered by Pagefind