Beever Atlas
Enterprise AI memory layer ·
An enterprise agent memory system that turns scattered team chat and personal data sources into a wiki.

I take AI that already works and ship it into real budgets, real compliance and R&D teams that apply AI-native workflows.
Adrian Leung
01Case studies
Shapped and Shipped 3 AI products.
Enterprise AI memory layer ·
An enterprise agent memory system that turns scattered team chat and personal data sources into a wiki.

PropTech / property management ·
A WhatsApp-native layer over Hong Kong building management — Vision and ASR do the reading; a person still owns the price and the compliance call.

AI meeting intelligence / GovTech + SaaS · 2025 — present
Cantonese meeting AI, sold two ways: air-gapped V-Note for regulated buyers, SaaS V-Note Live for everyone.

02Aspects we are covering
Navigating the line between precise logic and the pragmatic calls that drive real deals.
The solution must fit the real-world use case: Compliance, accounting, law, RBAC, medical. Even 0.001% uncertainty is not acceptable.
Where strategy, decisions, human experts, actual scenarios and expectation management smoothen out the product delivery.
Maximize the AI capability — adopt the latest technical breakthroughs and community innovations.
03How I work
I use both manual and agentic tools, whichever deliver the results.
Classic tools are there for a reason.
Excel — Accessible for all AI-readiness teammates.
Figma — Where I think through ideas and collab with teams.
Notion — My digital notebook, extra context source for AI Agents.
Linear — PM platform for roadmaps, milestones, and issues.
JIRA — No choice if we have to use. Enterprise standard.
Miro — Discovery workshops for design thinking, team sync.
Framer — Fast, shareable prototypes when a static page is enough.
Webflow — Marketing sites shipped without spending a dev sprint.
Adobe Creative Suite — Brand, print, and the graphic-design.
Optimal Workshop — Ran Treejack tree-testing for UX study.
Hotjar — Heatmaps and replays — where the UI actually loses people.
Slack — Team chat, and Slack came from a gaming company?!
Google Analytics — Funnels and drop-offs to check a design decision.
Tableau — BI dashboard and funnels at a glance.
The new LEGO bricks I keep learning.
Claude Code — My day-to-day helpers.
Cursor — Tread this as an IDE place for repos.
MCP — Connect to different sources for AI Agents.
Beever Atlas — Eat-your-own-dog-food AI memory system.
PostHog — Product analytics for the things we shipped.
Storybook CLI — Design system integrated with AI workflows.
AWS CLI — Let CC help me deploy faster.
GWS CLI — Lets Claude Code reach my Google Workspace.
Lovable — Quick and handy prototype option.
Playwright — Behavioural driven testing for our products.
Langfuse — LLM observability. See what the models actually did.
Ollama — Edge-device LLM let me work on planes. And free
Stitch — Spins up design.md / UX-UI concepts before I touch Figma.
Deepwiki — Points me at OSS repos and actually explains them.
GLM — Cheap tokens for the simple stuff, saves the good model.
04Community
Global Service Jam 2026HelperMar 2026
Lovable — She BuildsFacilitatorMar 2026
Votee — Vibe Design Thinking WorkshopMain HostApr 2026
AI Tinker — A2UI & AG-UI HackathonParticipantJun 202605Skills
Most of my skills at a glance.