Skip to content
Dwg. FIF-001 · Full-stack AI engineer23.81° N 90.41° E · GMT+6

AI products,
engineered
end to end.

I build LLM features, agents and ML models together with the backend and interface they live in — so you get one working product, not a demo and a handoff.

Start a project See the work

Status: Taking on new projectsReplies within 24h

Portrait of Faysal Islam Fahad
Fig. A — The engineerDhaka, Bangladesh

Shipped & public

Axo heyaxo.devSellWise live appQueueStorm sourceGitHub 60+ public repos

How I think about AI systems

Models where they help. Code where it has to be right.

Most AI features don't fail at the model. They fail at the seams — the unchecked output, the missing fallback, the decision that should never have been left to a probability. I design those seams first.

  • Deterministic code
  • Model output
  • Guardrail
  • Data
A

Detail — QueueStorm Investigator, a finance support copilot

  1. Ticket + transactionsIn / out
    Bangla, English or Banglish
  2. Request validationGuard
    Pydantic v2 schemas
  3. Reasoning engineCode
    Match, dedupe, route, set severity
  4. LLM draftingModel
    Agent summary + customer reply only
  5. Safety post-processorGuard
    No PIN/OTP asks, no refund promises
  6. Structured decisionIn / out
    Verdict, department, human-review flag
Why the model never makes the decision
01

Selected work

Systems I've designed, built and shipped.

Each one is public — live, or with its source open. No invented metrics; the links are the evidence.
All work →
  1. Sheet 01QueueStorm Investigator2026Hackathon build

    A support copilot for digital finance that can't make promises it shouldn't.

    Investigates customer complaints against transaction history and returns a structured, routable decision. Rules decide; the model only writes.

    • Python
    • FastAPI
    • Pydantic v2
    • OpenRouter
    • Gemini 2.5 Flash
    • pytest
    Read the case study Source on GitHub
    1. Ticket + transactionsIn / out
      Bangla, English or Banglish
    2. Request validationGuard
      Pydantic v2 schemas
    3. Reasoning engineCode
      Match, dedupe, route, set severity
    4. LLM draftingModel
      Agent summary + customer reply only
    5. Safety post-processorGuard
      No PIN/OTP asks, no refund promises
    6. Structured decisionIn / out
      Verdict, department, human-review flag
  2. Sheet 02Axo2026Live

    An AI product architect that turns an idea into a blueprint and build-ready prompts.

    Describe a product in plain language; get a structured blueprint — features, user flows, stack, architecture — and prompts tuned for Lovable, Claude, Cursor and Bolt.

    • LLMs
    • Prompt engineering
    • Structured generation
    • Agentic workflow
    Read the case study heyaxo.dev
    1. Product ideaIn / out
      Free text, any level of detail
    2. BlueprintModel
      Features, user flows, stack, architecture
    3. Saved blueprintData
      The reviewable source of truth
    4. Builder promptsModel
      Generated from the blueprint
    5. ExportIn / out
      Lovable · Claude · Cursor · Bolt
  3. Sheet 03SellWise2026Live

    Forecasts and customer intelligence for small online shops.

    A business-intelligence dashboard with three ML modules — sales forecasting, customer segmentation and churn prediction — served from an independent Python microservice.

    • React
    • Node.js
    • Express
    • PostgreSQL
    • FastAPI
    • Prophet
    Read the case study Live app
    1. Orders, customers, stockData
      PostgreSQL · CSV import
    2. Node.js REST APICode
      Orders, inventory, invoices, reports
    3. Demand forecastModel
      Prophet · 7 / 14 / 30 days
    4. Segments & churnModel
      RFM · logistic regression
    5. DashboardIn / out
      Forecasts, customer risk, stock alerts
  4. Sheet 04BUBT AI Assistant2025Open source

    A university chatbot that answers from official documents — and cites them.

    Retrieval-augmented generation over university PDFs: upload a handbook, ask a question, get an answer with the source documents listed.

    • TypeScript
    • Node.js
    • Express
    • React
    • Gemini
    • FAISS
    Read the case study Source on GitHub
    1. University PDFsIn / out
      Handbooks, admission guides
    2. Parse & chunkCode
      1,000 chars · 200 overlap
    3. EmbedModel
      Gemini text-embedding-004
    4. FAISS indexData
      Cosine similarity · persisted
    5. Grounded answerModel
      Top-5 chunks → Gemini
    6. Answer + sourcesIn / out
      Cited documents
02

What I build for clients

Four things I do well — each with proof.

Services in detail →
  • A

    AI copilots & agents for operations

    Assistants that read the request, pull the data, propose the next step — and hand anything risky to a human.

    For: Teams buried in repetitive triage: support tickets, inbound leads, back-office checks, internal requests.

    Proof QueueStorm Investigator

  • B

    Answers from your own documents

    Search and chat grounded in your PDFs, wikis and drives — with citations people can check.

    For: Organisations whose knowledge lives in documents, and teams that answer the same questions every week.

    Proof BUBT AI Assistant

  • C

    Forecasts & customer intelligence

    Demand forecasts, customer segments and churn risk from the sales data you already have.

    For: E-commerce and small businesses with a few years of orders and no data team.

    Proof SellWise

  • D

    AI-native MVPs, end to end

    The whole product — interface, backend, database and AI features — from one engineer who owns all of it.

    For: Founders who need a working product to put in front of users, not a model in a notebook.

    Proof Axo

03

How I work

Engineering habits you can hold me to.

  1. Rule 01

    Deterministic where it must be right.

    Money, permissions, routing and anything with consequences is decided by plain code that can be tested and audited. Models read, interpret and draft — they don't get the final say.

  2. Rule 02

    Guardrails are code, not prompts.

    A system prompt is a request. Validation, schema checks and post-processing are guarantees. Every model output is checked before a user or a database sees it.

  3. Rule 03

    It keeps working when the model doesn't.

    Providers time out, keys expire, outputs drift. I design a safe fallback path for each model call so the product degrades gracefully instead of failing loudly.

  4. Rule 04

    You own all of it.

    Code in your repository, prompts in version control, keys in your accounts, and no lock-in to a single model vendor. Swap providers without rewriting the product.

Working together

  1. Step 01

    Intro call

    30 minutes, free. You walk me through the workflow; I ask about your data, your systems and what “done” means.

  2. Step 02

    Written scope

    A short document: what gets built, what's explicitly out, milestones, and a price. No surprises later.

  3. Step 03

    Build in the open

    A demo on a live staging URL every week. You see working software, not status reports.

  4. Step 04

    Handover

    Your repository, deployment, documentation and tests. Support after launch if you want it.

04

About

I'm Faysal, a full-stack AI engineer in Dhaka. I write the retrieval pipeline, the API, the database schema and the interface — so there's nobody to hand the hard parts to but me.

B.Sc. in Computer Science & Engineering at BUBT, former backend developer at Rangpur IT, and builder of Axo and SellWise. I work remotely with clients worldwide — async-first, with overlap into European business hours.

More about me

Next step

Have a workflow that should run itself?

Tell me what it is, what data it touches and what “done” looks like. You'll get a straight answer on whether AI is the right tool — and what it would take.

Start a project

Free 30-min intro callReplies within 24h