Skip to content
Muhammet Şafak
tr
Cover image — Tan works on a laptop held in the arms; behind, a line of indigo pipes runs through a funnel that filters it, with rising score bars beside the screen

In Devrazzi a formula sets the score, the model only explains it

A formula sets Devrazzi's 0–100 score; the model only writes the explanation, behind a verification gate. The decision and how it was built.

What it does today

Collects release and vulnerability announcements across the software ecosystem into a single feed, gives every event an importance score from 0 to 100 and explains its impact in Turkish; it also tracks deprecation/EOL and RFC announcements. Useful to software engineers who want to see what changed in their stack without combing through hundreds of sources by hand every day.

Started
October 2026 — October 2026
Left Labs
Updated

Form

Web

Technologies

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

This one became a product:

Devrazzi

When a vulnerability gets a score of 85, behind that number stands a formula, not a model. It was the first rule I set when I rewrote Devrazzi from scratch on Laravel on 13 October 2026: a language model may explain something, but it cannot assign the score.

Where the radar looks

Devrazzi is an engineering intelligence radar. 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. EPSS does not produce new events, it only feeds the scores of security records. The output is on the web only and in Turkish only: the feed, event pages and a technology index. The feed starts with the newest by default; the “Most important” ordering sorts the last 30 days of events by score, and the filters work by technology, ecosystem, event type, severity band and date range.

A formula sets the score

Every event gets a score from 0 to 100 and falls into one of four bands: Critical (85 and above), High, Medium, Low. The score comes from components such as CVSS, KEV membership, EPSS, version jump, how widespread the technology is and the number of independent sources; the breakdown of the components is visible on the event page, and the rules are written on the scoring page. The score is the same for everyone; there is no personalisation. The cost is plain: this score is not a substitute for a risk assessment of your own stack.

The model’s job, and the gate in front of it

A Haiku-class model matches news to events and a Sonnet-class model writes the impact explanation. In the Medium and higher bands the 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: on an error, a timeout, a 429/5xx or a validation failure, the chain moves on to the next. The providers in the chain are Anthropic, OpenAI, Gemini and DeepSeek; model names live in configuration, not in code, and the target for monthly LLM spend is 100-300 USD; the ceiling is enforced on the application side, with a counter in PostgreSQL.

The real work is at the gate. For an explanation to be publishable, it has to cite at least one source; the CVE, GHSA, version and package names it uses have to appear in the source text; it has to stay within the length limits; and it has to be in Turkish. A response that fails is sent back once for correction, then the next model is tried. If none passes, the event drops into review; a Critical event, though, is published with the template explanation, noted as automatically generated. A low-confidence response does not go out either; the one exception is an event that rises to the Critical band while it is waiting.

The contribution I haven’t switched on yet

The architecture has room for the model to make a capped contribution to the score, but today that contribution is off, and the scoring page also says artificial intelligence makes no contribution to the score. That has a cost: deprecation, EOL and RFC events take their score only from adoption and source count, so today they stay below the publishing threshold; the radar tracks them but does not carry them into the feed. The reason is measurement: on the 74 release and news items of the golden set, none of the three models tested cleared the threshold; for two of them, the area that held them back was deprecation detection. After fixing the labels and the prompt I measured again, and the result still fell short.

Next

First, raising agreement on the deprecation label above the threshold, then measuring the contribution again. Until the threshold is cleared, the contribution’s flag stays off. The product’s profile is in the portfolio.

Tags: #llm#scoring#cve#radar
Share:

More Records

All records

Build notes on keeping multi-account personal and business finance in a single account and transaction model, and how it reached web, iOS and Android.

What it does today

One account/transaction model carries multi-account management, budgeting, goals and reporting on a single core; the web, iOS and Android clients are all live. Anyone who wants personal and business finances tracked in one place can use it.

Open-Source Web Mobile PHP Laravel Go +4 more
March 2024 — October 2024

A self-hosted Go gateway holds the provider keys and injects RAG context, so the application talks to one OpenAI-compatible endpoint.

What it does today

Lets an application talk to one OpenAI-compatible endpoint while a project's configuration decides which model the request reaches and, when a document store is linked, which documents it draws context from. Anyone who does not want provider keys spread across applications, and wants spend capped per project, can run it on their own server.

Open-Source Web Go PostgreSQL pgvector +8 more
August 2026 — September 2026

Build notes on putting textbook theory and problems met in industry into one lesson flow: a free, text-first platform whose lessons need no signup.

What it does today

Live as a learning platform whose lessons are free to read without signup: the curriculum–course–topic–lesson hierarchy, full-text search and progress tracking work, while the course-end exam, verifiable certificates and the study assistant sit in a Pro tier. Anyone who wants to read the computer-science curriculum can use it today.

Web Laravel PHP Livewire +6 more
August 2026 — September 2026

Search the site

Start typing to search posts, projects and pages.

Esc to close Powered by Pagefind