Portfolio
Orqen
A platform for building AI workflows visually, connecting Google Gemini, external APIs, conditions, database writes and human approval steps.
Developed by AbrarAli S.
The challenge
A single AI prompt rarely does a whole job. Real work needs its output checked, routed to other systems and sometimes approved by a person before anything happens.
The approach
Model each workflow as a directed graph, run it on the server rather than in the browser, and enforce each organisation's boundaries and roles in the database as well as in the server functions.
What we did
Abrar built the workflow editor, the execution functions and the access rules, working to a written technical brief. All commits in the public repository are Abrar's.
The solution
Users drag steps onto a canvas and start a run. Runs pause at approval gates until an Editor or Owner approves, and live GraphQL subscriptions show progress without polling.
Key features
- Drag-and-drop workflow editor built with React Flow
- LLM, HTTP request, condition, database write and approval steps
- Approval gates that pause a run until an authorised person responds
- Live run monitoring through GraphQL subscriptions
- Separate organisations with Owner, Editor and Viewer roles
- Row-level security in PostgreSQL through Hasura
Where it stands
The source code is public, and the project runs on a Nhost backend you set up yourself. There is no hosted demo, and no client results are claimed.
More projects
Personal projectWorking projectBuySmart AI
Developed by AkbarAli N.
A microservices application that pulls live product data, asks Google Gemini to analyse it and returns a score with a Buy or Not Buy recommendation.
- Java
- Spring Boot
- React
- TypeScript
Personal projectResearch projectTIPS
Developed by AbrarAli S.
A six-stage Python pipeline that analyses recorded interviews across speech, audio and video to produce scores that show how a candidate's answers change over time.
- Python
- FastAPI
- OpenCV
- MediaPipe
- Personal projectWorking project
DataTalk Pro
Developed by AbrarAli S.
A conversational tool that answers plain-English questions about a MySQL database by generating and running SQL with Google Gemini.
- Python
- Streamlit
- LangChain
- Google Gemini
