The new company brain.
Context is the soul of your company, I learned today.
Since I wrote a book, “Age of Context,” years ago I see that context is what we now call our private data.
That data should be stored in a way to let AI agents and humans get more and more use out of it.
This is precisely what @PromptQL does and here @tanmaigo goes deep on how it now is a company brain, or, rather, a wiki that everyone updates and uses.
Positive users request a book link to learn more about PromptQL's shared context for AI agents, while negative users argue fragmented data makes such AI outputs useless without unified querying.
No Digg Deeper questions have been answered for this story yet.
@OpinionAILtd Here you go: https://a.co/d/01KryfxN
The new company brain.
Context is the soul of your company, I learned today.
Since I wrote a book, “Age of Context,” years ago I see that context is what we now call our private data.
That data should be stored in a way to let AI agents and humans get more and more use out of it.
This is precisely what @PromptQL does and here @tanmaigo goes deep on how it now is a company brain, or, rather, a wiki that everyone updates and uses.
@SherifKozman The one I saw this afternoon was a wiki. How does yours express itself?
@Scobleizer I wanna show you Eve https://evemem.com
@SherifKozman Someone should create a chart comparing them all so we can pick accordingly.
@Scobleizer Please share the link to book would love to read
@Scobleizer Most people seems to be falling into the benchmarks trap, but real value comes from proving that memory is structured, not just stored.
A functional memory breaks down into 4 categories. - Working state - Episodic - Semantic - Preference/Procedural
@Scobleizer Ah oh
@Scobleizer Check @EngramLab
Eve is built as operational memory for agents, not just stored notes.
So it decides what should become durable, keeps provenance, recalls the right context while work is happening, and lets memory be updated or forgotten as reality changes.
The goal is continuity across tools, teams, and time.
The Additional unique advantage is team memory, where a sub tenant is provisioned to be shared across team members on a single project and their agents, so all would learn from each other.
@Scobleizer No unified data = no context = useless AI output. The hard engineering problem isn't the model. It's making fragmented sources queryable.
@Scobleizer So, Palantir basically