Early access target:April 1, 2026

Agent-Grade Intelligence, Compact by Design

Powering precise code generation and real-time tool execution, cisimcik-9b is the base model for developers who move with purpose — leveraging deep reasoning, multi-step agentic flows, and native tool-call support to accelerate every build.

THE TEAM

The Builders

Two statistics students turning rigorous data into compact intelligence.

ÇO

Çağrı Okan

Agent Reliability & Evaluation | AI Researcher

Istanbul-based statistics student, AI researcher, and full-stack developer. Focuses on agent reliability and evaluation, building intelligent systems at the intersection of statistics, software, and design. Hackathon veteran — built an AI warehouse inventory agent in 48 hours.

🎓Statistics, Yıldız Technical University — 1st Year
💼Software Engineer Intern @ AI Business School
YC

Yiğitcan Coşkun

Machine Learning Engineer | Statistics Student @YTU

3rd-year Statistics student at Yıldız Technical University focused on LLMs, ML, Deep Learning, and AI Agents. Bridging the curriculum gap by self-studying Data Structures & Algorithms and OOP — built MCP-based AI agent architectures and end-to-end Power BI pipelines for enterprise clients.

🎓Statistics, Yıldız Technical University — 3rd Year
💼Data Analytics & BI Intern @ Otokoç Otomotiv
CAPABILITIES

What Makes cisimcik-9b Different

Built on a rigorous data pipeline that prioritizes signal quality over volume.

⚙️

Precision Fine-Tuning Engine

cisimcik-9b is trained on carefully curated data spanning coding, debugging, error handling, and agentic reasoning — across multiple programming languages and real production scenarios.

📊

Data Monitoring Dashboard

A real-time dashboard tracks dataset health, coverage metrics, category distribution, and training signal quality — ensuring every sample added meaningfully improves the model.

🛠️

Native Tool Call Support

Built-in XML-style tool calling supports no-tool, single-tool, multi-tool, and reasoning+tool flows out of the box — mirroring real production tool environments.

🧠

Structured Reasoning Blocks

Think blocks let the model reason through multi-step tasks, track constraints, and plan tool strategy before generating its final response.

🌐

Bilingual Intelligence

Native Turkish and English support with natural, non-robotic language. Turkish samples use real-world phrasing — never translated text in disguise.

Quality-First Dataset

High-signal samples only — covering success cases, edge cases, and failure recovery. Shallow, repetitive, or synthetic-sounding data is explicitly excluded.

SUPPORTERS

Backed By

The people and organizations supporting cisimcik.

No supporters yet

We're just getting started. If you believe in what we're building, we'd love to have you with us.