Laptop, coffee mug and notes on a wooden desk by a window with plants

AI product advisory, engineering and assurance

AI that holds up in production.

We help organisations in Vietnam and Southeast Asia decide where AI pays off, build it on their own data, and keep it measurable, secure and accountable after launch.

Request a scoping call View case studies
Marc Nguyen
Marc Nguyen, Founder and Principal Product leader who designs and ships AI systems end to end.
  • 10 years of product leadership in EdTech and Fintech
  • Production AI: retrieval, agents, evaluation and audit
  • CSPO and PSM I certified
Marc Nguyen

Marc Nguyen, Founder and Principal10 years of product leadership. Ships AI to production.

How we work

From pilot to production, with controls at every step.

  1. Two people planning over coffee and a notebook
    01
    Discover

    Define the business problem, the data available and the success metric in numbers.

  2. Laptop showing a results chart
    02
    Validate

    Run a small, time-boxed test on your own data before any build commitment.

  3. Server rack lights and cables
    03
    Build and measure

    Deliver in increments, each checked against an evaluation set drawn from real tasks.

  4. A hand passing keys across a desk
    04
    Hand over

    Code, data, documentation and the evaluation suite stay in your accounts.

Reference implementations
9
AI systems designed, built and documented, each with a case study.
Technical briefings
18
Published analyses on evaluation, governance and retrieval.
Services
8
Each one backed by a system already running in production.
Years in product
10
Product leadership in EdTech and Fintech before AI.

Case studies

Reference implementations in production

View all case studies
Library shelves in soft green light
Reference implementation

Enterprise knowledge assistant

In production

Semantic search across 42,000+ documents in isolated workspaces, available in Claude on desktop, web and mobile, with cited sources.

  • 42,000+ documents
  • Workspace isolation
  • Cited answers
Phone beside a coffee cup
Reference implementation

Priority inbox triage

In production

An agent that ranks email threads P0 to P2, verifies against project tools, and surfaces only items that require action.

  • ~90 to ~8 min a day
  • 568 to 7 priority items
  • Human approval
Organised network patch panel
Reference implementation

MCP connector hub

In production

One governed connector layer giving Claude access to Google Workspace, Slack, GitHub, Jira and Linear across three isolated workspaces.

  • 150+ tools
  • 3 isolated tenants
  • OAuth and passkeys
View all case studies

Services

Advise. Build. Assure.

View all services

Advise

Decide where AI creates value and how success will be measured.

Build

Production AI systems on your data, delivered with the code and the evaluation suite.

Assure

Measure quality, find security and privacy exposure, and verify usability and accessibility.

View all services

Works with the platforms your teams already run

  • Claude
  • ChatGPT
  • Gmail
  • Google Drive
  • Slack
  • GitHub
  • Jira
  • Cloudflare
  • Swift

Insights

Insights and technical briefings

View all insights
Toggle switch on a dark green panel

Governing a coding-agent rollout: caps, a central off switch and CI cost

· Governance and operations
View all insights

Start here

Have a problem AI might solve?

Describe the outcome you need. Within two working days you receive a written view on whether AI is the right tool, the risks to manage, and a proposed first step.

Request a scoping call [email protected]