TaloSyn IT | Shohochori, Hospital AI & Bangla LLM

Three initiatives

One team, one standard, three directions.

PRODUCT — IN DEVELOPMENT

Shohochori: a Bangla-first fem-tech app

A private menstrual-health companion that helps women record their cycle and symptoms, understand patterns, and notice possible irregularities worth discussing with a healthcare professional.

Explore Shohochori →

HOSPITAL WORKFLOW INTELLIGENCE — PILOT STAGE

Practical AI systems for healthcare

We are developing a Hospital AI System with a hospital partner: an AI receptionist that listens to patients, matches them with the right doctor, and supports clearer queue management.

See the Hospital AI System →

RESEARCH — EARLY STAGE

A foundation language model for Bangla

We're fine-tuning open-weight LLMs on Bangla data so Bangladeshi businesses have a foundation to build on. Once the base model holds up, medical, marketing, and hiring versions follow.

Read about the initiative →

Track record

We've built AI systems before.

CodeAlignR, a US-based company delivering AI voice and chat automation since 2024. TaloSyn IT applies that engineering discipline to Shohochori, hospital technology, and Bangla language research.

More about the team

Since 2024

CodeAlignR

AI voice and chat automation for US clients, run by the team behind TaloSyn IT.

First product

Shohochori — সহচরী

Shohochori is a private, Bangla-first health companion for women in Bangladesh. It helps women track periods and symptoms, understand their cycle, and prepare for doctor visits — even offline. Pregnancy support, telehealth, and an AI health buddy are planned to bring more care into one place.

Version 1

Tracking & cycle insights

Log period dates, flow, pain, symptoms, and mood. Review your calendar, correct past entries, and see estimated next-period ranges and patterns worth discussing with a doctor.

Version 1

Reports & reminders

Prepare for appointments with a shareable doctor-visit report, and set discreet reminders for contraception and supplements.

Version 1

Privacy & offline access

Use Shohochori in Bangla or English, keep tracking offline, protect access with a PIN or biometrics, and choose whether to enable optional cloud sync.

Version 2 · Planned

Pregnancy, telehealth & AI buddy

Planned features include a pregnancy companion, telehealth consultations, and an AI health buddy for personalized education and guidance. These features are not yet available.

Talk to us about Shohochori Official website under development

Status: Version 1 is in development and preparing for launch. Version 2 is planned for a later phase.

Shohochori provides health information and identifies patterns in recorded data. It does not diagnose medical conditions or replace professional medical advice.

Hospital workflow intelligence — pilot stage

Hospital AI System

We are developing an AI receptionist and scheduling system for hospitals — it listens to patients, matches them to the right doctor, and keeps queues honest in real time. Not everything here is AI, and that's deliberate: we use AI where judgment is genuinely needed.

AI
Listens and matches a doctor

A patient calls or texts. The AI receptionist listens to the problem in Bangla or English and suggests the right doctor.
Automated
Books the appointment

Once the patient confirms, the slot is booked automatically — no human scheduler involved.
Automated
Tracks the real queue

A rule-based tracker counts how many patients are actually ahead of each appointment, in real time.
AI
Proposes a new time, doesn't impose one

If the queue is running behind, the AI works out a revised time and sends it to the patient — and everyone booked after them — for confirmation before anything changes.

Room 3 — Dr. Rahman ● illustrative example

Now serving 41

Your token 47

Automated tracking

Running ~15 min behind. New time sent to token 47 and everyone after.

AI decision

Status: Pilot stage.

Research

The Bangla LLM Initiative

We're adapting proven open-weight models — including Qwen and Gemma — into a language model that truly understands Bangla, dialects included, where most tools fall short.

Why

Most large language models treat Bangla as an afterthought. We're building one meant for it, so Bangladeshi businesses can build on it instead of working around it.

How

We fine-tune strong open-weight models on Bangla data rather than training from scratch — faster to a usable result, and light enough to run on hardware most companies can actually afford.

What's next

Once the base model holds up, we're tuning task-specific versions — starting with these areas:

Healthcare Social marketing Job search

Status: Early-stage research, not yet released.

About

Who's building this

TaloSyn IT is an IT solutions company based in Bangladesh. We also run CodeAlignR, delivering AI voice and chat automation to clients since 2024 — TaloSyn IT is where we build for Bangladesh directly.

Fahim Ibne Shams

Fahim holds a B.S. in Computer Science from the University of North Texas and an M.S. from Harrisburg University. He built his industry experience at PNC and Plus One (an Optum Company) as a Full Stack Software Engineer, focusing on traditional backend systems and modern AI application engineering. He brings a strong technical enthusiasm for designing custom AI applications, voice agents, and RAG workflows. His vision centers on leveraging these automated architectures to solve practical, real-world infrastructure challenges at a localized level. He is a full-time Software Engineering Faculty member and Technical Mentor at Thaddeus Stevens College of Technology in Lancaster, Pennsylvania, where he teaches computer science and coaches teams for competitive programming competitions.

LinkedInlinkedin.com/in/fis

Ramiza Maliha

Ramiza Maliha is a software and machine learning engineer based in Uppsala, Sweden, currently pursuing an MSc in Computer Science at Uppsala University. She spent two years as a Software Engineer at BJIT Limited, building backend systems for real clients, and previously served as both an instructor and researcher at North South University, work that led to a co-authored paper at KDD 2024. Her research interests span generative models, multimodal AI, and their applications in health and biological data. As a co-founder and lead developer at TaloSyn IT, she focuses on building AI that actually works for women. When she's not coding, she's either lost in a book or lost in a video game, sometimes both at once.

LinkedInlinkedin.com/in/rami1423

Mahira Jalisha

Mahira is a software and machine learning engineer based in Uppsala, Sweden, with an MS in Computer Science from Uppsala University. For the past two years she's worked at Padelmates as a founding engineer, helping scale the platform's backend from 3K to 100K monthly active users. Before that, she built and deployed ML systems into production. Her research interests center on multimodal LLMs, with a focus on AI in medtech and finance. Outside of work, you'll find her on the badminton court or out for a casual stroll in the wild.

LinkedInlinkedin.com/in/mahira-jalisha

Kalyan Roy

Kalyan is a researcher and IT entrepreneur with a Bachelor of Science in Computer Science and Engineering from North South University, Bangladesh. His work spans algorithms, graph theory, natural language processing, and machine learning, with research published at venues including ACM SIGKDD. During his undergraduate studies, he was active in competitive programming and participated in several national-level contests, including the ICPC Dhaka Regional. He is also a co-founder of CodeAlignR, a US-based company that specializes in AI voice agents, chatbots, and workflow automation.

Websitekalyan.is-a.dev

Contact