Share graph · provenance running forward
Adam Witanowski
Lab Director (acting) · lab
What they dropped, which clusters it landed in, what got elected, and which experiments and findings descended from it. Everyone’s is visible to everyone, symmetrically. Show outcomes, not counts — no totals, no rankings, no rollups.
Dropped
signals with this person attached
Landed in
distinct clusters
Elected
of those, now fields
Descended
experiments and published items
Drops
What descended
Use a structured episodic store with summarised recall, not a raw vector memory
Agentic delivery works when the spec is the artifact; do not start with the code
Which memory layer should a new agent use?
Is the vendor's 'agentic' claim real?
When does on-prem inference make sense?
The direction of agentic development
Sovereign inference and the end of US default
Table stakes, not moats: what a right to play costs in 2026
Memory layer bake-off on a 40-session support corpus
Spec-first agentic delivery on a live internal repo
Compiling agent experience into a persistent skill wiki
Confidential inference on a TEE for banking PII
Shared-context AI surface for a delivery pod
Survey run: nearest adjacency into pharma
Follow this person’s finds
Following someone whose drops are consistently good is the internal version of the external voice watchlist, and often a better source than any detector.