Erenext Erenext
1 / 9 Arrow keys or scroll
AI product company · Denver, Colorado

Decision AI for Turkish, and AI that writes original exam questions.

Erenext LLC builds software products in its AI Lab: Pusula, an open-source Turkish decision model, and QuestNext Cloud Generator, now in development.

Released · v2.0

Pusula

Open-source Turkish decision model, Apache-2.0.

In development

QuestNext

Autonomous exam-question generation. Not yet sold.

Company

Bootstrapped

Founded 13 July 2026. Pre-seed. Team of two. $0 outside funding.

The problem

Turkish institutions and exam publishers are underserved by today’s AI.

01 · Language

Decision models are built for English

Widely used decision models were developed primarily for English. Their accuracy on Turkish is limited, especially on informal writing, typos, and mixed Turkish–English text.

02 · Data residency

Regulated data cannot hit public APIs

Banks, health providers, law firms, and public services often cannot send customer messages to a public AI API under Turkey’s KVKK personal-data rules. They need models they can run themselves.

03 · Assessment

Original questions are slow to write

Schools and publishers need original, curriculum-aligned exam questions. Writing a new item for each learning objective still depends on scarce educator time.

Product · Pusula

An open-source Turkish decision model that returns probabilities, not generated text.

v2.0 · 31 October 2026 Apache-2.0

Pusula answers typed questions about a text and returns a probability for every option. Typical uses: routing, urgency, human handoff, fraud, and prompt-injection checks.

  • Built-in Turkish taxonomy: 20 domains, 103 subdomains, 333 intents, plus 20 ready-made templates.
  • Pusula (GPU): 26B-class Decision 3.0 — about 64 GB in BF16, or 24 GB in 4-bit.
  • Pusula Nano (CPU or any GPU): 149M parameters.
92.0

Turkish Decision Benchmark

Pusula 2.0 score, as published on the product page. We train and serve the model for institutions that cannot send customer messages to a public API.

Product: erenext.com/ai/pusula · Weights and code on Hugging Face and GitHub (erenextlabs/pusula)

Product · QuestNext Cloud Generator

Autonomous exam-question generation, now in development.

In development Not yet sold

QuestNext turns topics and learning objectives into original multiple-choice and open-ended exam questions for curricula and admissions tests.

Covered curricula and tests include IB, AP, A Level, YKS, IMAT, SAT, ACT, ESAT, TOEFL, and IELTS.

Status

Concept demonstration only

https://questnext.cloud/ is an interactive concept demonstration. It does not generate questions. The product is not yet sold.

Product page: erenext.com/ai/questnext

Status

Shipped open-source software, a product in development, and a revenue-generating company.

v2.0

Pusula is public

Open-source release on 31 October 2026, Apache-2.0, with a published 92.0 score on the Turkish Decision Benchmark.

In build

QuestNext is not yet sold

The generator is in development. The public site is a concept demonstration only.

Live

Profitable and bootstrapped

Founded 13 July 2026. Pre-seed, $0 outside funding, paying customers, revenue-generating and profitable. No outside capital.

We also apply the lab’s models to educator-checked, AI-generated video lessons. That line is a commercial application of the products, not a school.

Business model

Product-led, with institutions first.

Pusula · B2B

Deploy, fine-tune, support

We train and serve Pusula for institutions that need on-their-own-infrastructure inference under KVKK: deployment, fine-tuning, and support.

QuestNext

Not yet commercial

QuestNext Cloud Generator is in development and is not yet sold. When it ships, it is intended as a product for curriculum and admissions-question generation.

Application of the lab

Educator-checked lessons

Interactive video lessons for IB, AP, and A Level Physics, Chemistry, and Mathematics, produced with AI and checked by Erenext educators. A secondary custom-AI software line exists; Erenext is not a consultancy or a school.

Team

Two people, building the lab and the products.

Founder

Hasan Şahin

Founder of Erenext LLC and Pusula project lead. The company is a US LLC registered in Denver, Colorado; Hasan is based in Turkey.

Developer / Engineer

Ahmet Sayman

Second teammate, Developer/Engineer. The company is a team of two.

Use of Daytona

Isolated sandboxes for evaluation and training — planned, not live today.

Pusula

Evaluation and training jobs

We would use Daytona for isolated evaluation and training jobs for Pusula, including checks that should not run on a shared public API.

QuestNext · planned

Disposable generation pipelines

As a planned use, we would run and evaluate QuestNext’s autonomous question-generation pipeline in a disposable environment, without exposing institutional customer data or student personal data.

We are not already running this workload on Daytona. Intended use cases: AI evaluations and training & fine-tuning.