Symbols and Relations • Layers of Abstraction • Emergence • Mental Architecture building @arsumbrisai

Europe
Joined October 2018
{ I N P U T } retweeted
build structures for agents to think with (sound on)
1
4
2
24
3,933
{ I N P U T } retweeted
Agentic knowledge systems will change the way we work
1
2
1
36
6,191
{ I N P U T } retweeted
Build apps on top of your files
Introducing @arsumbrisai - own your knowledge, and everything you build on top
1
2
12
1,829
a substrate and surface to think in capture and structure your knowledge expand on it build custom apps and own it all
Introducing @arsumbrisai - own your knowledge, and everything you build on top
7
684
this is exactly why we are building @arsumbrisai
it's crazy how far out the labs are building at the application layer on the one hand it makes sense, on the other hand do you really want all of your company knowledge, docs, workflows built so locked in to a single model?
1
1
5
490
{ I N P U T } retweeted
knowledge and code bases can get too complex to take in all at once so you work with shadows: projections and abstractions that reveal different aspects of the same structure learning to shape those shadows and move between them is an art
2
37
1,487
Imagine a lab released a model that performs 1:1 like the average human across the board. Would be such a down grade
1
8
716
could play with this for hours focal tree projection in @arsumbrisai
2
5
1
146
6,631
a less balanced example
1
8
315
type tree changing the balance depth
1
6
236
{ I N P U T } retweeted
excited to share a walkthrough of @arsumbrisai build knowledge bases in typed markdown with your agents via mcp, then build your own apps and plugins on top of it everything lives in repos you can share and extend. a bit like packages for knowledge work
12
4
4
113
12,654
{ I N P U T } retweeted
okay hear me out: an agent framework that operates on top of composable repos, with a type engine that reads them as one typed graph thats the substrate repos are like packages for knowledge and the capabilities for working with it you can package your knowledge together with the skills and mcp tools your agents use to work on it the ui components also live there the app is a shell that renders views on top of your substrate and those views are themselves defined in the substrate, through the same type system so you and your agent can work on your knowledge AND build the environment you use to work with it say youre building your company brain in there your customer notes and deal history already live in the graph you dont want to pay for a separate crm system when the data is already there so you and your agent build a crm on top of that data, right inside the same app e.g. a view of your sales pipeline, with each deal linked to the customer and the conversations behind it you can also share that view together with the types and agent workflows it needs to let them use your setup (but not necessarily your data) so someone else brings the repo into their workspace and uses it with their own company data
technical overview of @arsumbrisai - many repos of md + yaml → one typed graph - type refinements, cross-repo types - lists, tuples, inline vs [[linked::repo]] refs - abstract, sealed, unions, intersections - typed md bodies, location rules, meta - au-host: views as typed projections - au-mcp: tools/hooks/skills as typed plugins
7
5
1
45
5,114
technical overview of @arsumbrisai - many repos of md + yaml → one typed graph - type refinements, cross-repo types - lists, tuples, inline vs [[linked::repo]] refs - abstract, sealed, unions, intersections - typed md bodies, location rules, meta - au-host: views as typed projections - au-mcp: tools/hooks/skills as typed plugins
4
1
3
29
10,886