jamesli.work

I'm James Li. I build AI products

I'm an AI engineer and delivery lead with a background in business operations, web delivery and SEO. I use coding agents to build quickly while owning product decisions, architecture, retrieval, evaluation, human review, deployment, and operations.

AI delivery expert based in Brisbane. Building independent products and client systems.

View selected work Read resume
Illustrated portrait of James Li
Selected work

Selected work

Seven systems. Clear ownership. Real proof.

07Client DeliveryMuriersilk AI Sales ConciergeRetrieval-grounded commerce conciergeView case 02Client DeliveryTender LubanTender review and commercial bid assemblyView case 01Independent ProjectOptiTalentEvidence-first recruiting workflowsView case 04Client DeliveryMuriersilkD2C commerce and SEO recoveryView case 03Client DeliveryKinmedB2B medical web and programmatic SEOView case 05Open SourceMemtruthEvidence and document runtimeView case 06Open SourcePiveoSelf-hostable AI creative workstationView case

Explore the work by capability.

The same projects can demonstrate different capabilities. Start with the category, then inspect the case and its evidence.

01
AI-powered apps

Customer-facing assistants and multi-tenant products taken from discovery to production.

02
AI automation

Operational workflows automated end to end, with a person approving what matters.

03
Full-stack web delivery

Full-stack web and commerce systems delivered from brief to release.

04
Open source & contributions

What public work has survived maintainer review?

Open source

Public systems and framework contributions that survive review.

Claim discipline

Subsystem ownership is earned through review and maintenance.

I label ownership and contribution state precisely, and keep framework work distinct from the central runtime.

How I work

AI coding agents write most of the code. I decide what the system should do, shape the architecture, review the work and verify what ships.

Product path

Drag to explore

  1. 01

    Business domain core

    Model rules, data, and invariants before choosing an interface.

  2. 02

    Application capabilities

    Turn real business needs into small, callable, testable use cases.

  3. 03

    CLI + MCP + API

    Expose one capability layer through stable human and agent contracts.

    TUITUI is a development-stage observability sidecar.

  4. 04

    Thin GUI validation

    Test the human workflow, review gates, and exception paths early.

  5. 05

    Complete product GUI

    Productize the proven workflow with full states and responsive control.

Frontend path

Drag to explore

  1. 01

    Business goal

    Define the audience, trust promise, and conversion outcome first.

  2. 02

    IA / site tree

    Map routes, topic ownership, internal links, and calls to action.

  3. 03

    Design Read

    Set visual language, density, motion, accessibility, and constraints.

  4. 04

    Desktop + mobile references

    Generate and approve both compositions before implementation begins.

  5. 05

    Image-to-Code

    Translate the approved reference into reusable components and content.

  6. 06

    Browser verification

    Compare real breakpoints, motion preferences, overflow, and fidelity.

  7. 07

    Shipped page

    Release only after build, performance, public-boundary, and live checks.

Domain experience

Where I am useful.

I spent years leading operating change and tender pursuits across a multi-subsidiary engineering group. I later owned production web and growth delivery before extending the same discipline into backend state, retrieval, evidence, and agents. That path makes me attentive to workflow, adoption, risk, and the difference between a demo and an operated system.

Fatbunny DigitalIndependent Web, Growth & AI Delivery · 2022–Present

Brisbane / Remote across APAC

Agent-native operational systems

Capabilities shared by people and agents, with clear state, review, risk, and audit boundaries.

Search, retrieval, and ranking

Recall, fusion, ranking, evidence, and compute placement designed as one product system.

Evidence and document systems

Source-aware extraction, provenance, citations, structured outputs, and reviewable decisions.

Commerce, growth, and SEO

Information architecture, programmatic discovery, structured data, and commerce-safe delivery.

Product infrastructure and delivery

Typed contracts, multi-tenant boundaries, release gates, deployment, and live verification.

Skills & Stack

Concrete tools and working strengths, grouped by the systems they help me ship.

Working strengths

  • Systems thinking
  • Workflow discovery
  • Requirement translation
  • Evidence-led judgment
  • End-to-end ownership
  • Human-agent interaction

Core Languages

  • TypeScript
  • Rust
  • Python
  • Java
  • SQL

Frontend

  • React
  • React Router
  • Next.js
  • Astro
  • Vite

Backend & Interfaces

  • Node.js
  • Hono
  • FastAPI
  • Django
  • REST
  • MCP

Retrieval & Data

  • PostgreSQL
  • pgvector
  • Vespa
  • Qdrant
  • BM25
  • TF-IDF
  • RRF

Ranking & AI

  • LightGBM
  • ColBERT
  • Embeddings
  • Structured outputs
  • Evaluation harnesses

Infrastructure

  • Cloudflare
  • Docker
  • GitHub Actions
  • Dokploy

Product & Web

  • Information architecture
  • Site trees
  • Technical SEO
  • Schema.org
  • Imagegen
  • Image-to-Code

Education & Contact

Operating context, formal study, and a direct path to the next useful conversation.

2025Master of Science in FinanceAsset ManagementBrest Business School
2021Diploma of BusinessBusiness AdministrationTAFE Queensland

LanguagesEnglish · Mandarin · Cantonese

Brisbane · Remote across APAC

Have a hard workflow worth making useful?

AI automation, AI-powered apps, and full-stack web delivery — taken from discovery through production.

Start a conversation Read the resume