Dev Blog/Our Approach

11 posts

How not to build a Process Foundation Model
Dei Vilkinsons

How not to build a Process Foundation Model

Why classic AI model architectures fail to handle the unique properties of process graphs

Bilal Mahmoud

Deriving slugs from embeddings: vec2slug

Building a tiny transformer decoder to extract URL slugs from vector embeddings

Deriving slugs from embeddings: vec2slug
Dei Vilkinsons

Embeddings as Encodings

Correctly conceptualizing and handling vectorization in knowledge graphs

Embeddings as Encodings
Ciaran Morinan

AI PR Reviewer

Improving code quality and accelerating feature delivery with a homegrown AI-powered code reviewer

AI PR Reviewer
Dei Vilkinsons

Design-Led AI

UX rules for building AI-powered professional tools

Design-Led AI
Ciaran Morinan

Collaborative data modeling

Allowing users to build a shared, structured understanding of the world

Collaborative data modeling
Alexander Kachkaev & Dei Vilkinsons

File structuring using fractal trees

Scalable code organizing for large projects and monorepos

File structuring using fractal trees
A real-life tech tree
Dei Vilkinsons

A real-life tech tree

Laying out our open-source development roadmap for HASH, in public

Ciaran Morinan & Ahmad Sattar Atta

Real-time collaboration across arbitrary blocks

Facilitating multiplayer interactions within novel, unrecognized UI components

Dei Vilkinsons

The non-negotiable principle

The utility of hard constraints in product design

Dei Vilkinsons

Open source at HASH

How our approach to open source informs what we do

Join our community of HASH developers

Explore open roles
Star us on GitHubGet in touch