Skip to content
View farvisun's full-sized avatar
👀
watching
👀
watching

Block or report farvisun

Block user

Prevent this user from interacting with your repositories and sending you notifications. Learn more about blocking users.

You must be logged in to block users.

Content in all repositories owned by your account will be closed.
Maximum 250 characters. Please don’t include any personal information such as legal names or email addresses. Markdown is supported. This note will only be visible to you.
Report abuse

Contact GitHub support about this user’s behavior. Learn more about reporting abuse.

Report abuse
farvisun/README.md

Hey, I'm Mohammad

Website · LinkedIn · GitHub

I build backend platforms, AI-assisted products, and automation systems. My work usually sits at the intersection of production engineering, developer workflows, data systems, and practical AI.

Right now my main focus is AI: agents, LLM-powered workflows, internal tools, product copilots, and systems that turn messy context into useful actions. I care about AI that connects to real software, real teams, and real operating constraints.

AI Focus

  • AI agents that can plan, call tools, use context, and help teams execute work.
  • LLM workflows for task management, knowledge retrieval, automation, and decision support.
  • RAG-style systems with embeddings, search, vector databases, and structured context pipelines.
  • Product copilots that sit inside real workflows instead of living as isolated chat boxes.
  • Evaluation, observability, and feedback loops for AI features after they reach production.
  • Practical prompt design, context engineering, and system design around model limitations.

What I Work On

  • Backend and platform architecture for high-traffic products.
  • APIs, queues, caches, service migrations, and production scaling.
  • Data, search, and analytics systems that make operations easier to understand.
  • Internal tools that reduce repetitive work and improve team velocity.
  • Engineering leadership: team design, ownership, roadmap planning, incident process, and delivery health.

Stack & Environment

Languages & frameworks

Go PHP Laravel JavaScript TypeScript Bash

AI & automation

OpenAI APIs AI Agents Tool Calling RAG Embeddings Workflow Automation Internal Assistants

Data & search

MySQL Redis ClickHouse Qdrant Meilisearch

Infrastructure

Kubernetes Docker Nginx Linux RabbitMQ CI/CD

Observability & operations

Grafana Prometheus Analytics Dashboards Incident Management Production Reviews

Current Interests

  • Making AI tools useful inside everyday engineering and product workflows.
  • Building agentic systems with clear boundaries, reliable actions, and measurable outcomes.
  • Connecting LLMs to backend services, databases, queues, search, and internal knowledge.
  • Keeping production systems boring while adding smarter automation around them.
  • Designing team workflows where AI helps without creating hidden operational risk.

How I Build

Make the critical path boring. Keep ownership clear. Add observability before panic. Use AI where it removes friction, exposes context, or helps people make better decisions.

Pinned Loading

  1. squi squi Public

    A fast, keyboard-driven SQL client for the terminal: PostgreSQL, MySQL, MariaDB, ClickHouse, SQL Server and SQLite, over SSH, safe on production

    Go 9

  2. nicedock nicedock Public

    A second Dock for macOS with 111 live widgets. Native Swift/SwiftUI, 10 languages incl. Persian (Estedad), local-first.

    Swift 1

  3. agentilo agentilo Public

    Claude Code, Codex and Cursor plan limits, paced against the clock, beside your MacBook notch.

    Swift 2

  4. marpora marpora Public

    A fast Markdown editor for macOS: live preview, Typora themes, AI, MCP agents and Marp slides.

    TypeScript 1

  5. mindio-magic-ai mindio-magic-ai Public

    PHP 1

  6. motty motty Public

    A fast, GPU-accelerated macOS terminal in Rust, with first-class support for coding agents.

    Rust 1