Share graph · provenance running forward
Marcus Lee
Delivery lead · Telco · firm
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
Route through a gateway you control; do not standardise on a vendor's
Not yet: realtime voice for AU contact centres above tier-1 triage
Distil to a small model only after the frontier baseline is measured on the same eval
Put backpressure on agent fan-out before you put it on the model
Retrieval or fine-tuning for this?
Which memory layer should a new agent use?
When do we need to move to post-quantum crypto?
Learning without weights: where continual learning actually lands
Memory layer bake-off on a 40-session support corpus
Cost-aware routing across three model gardens
Voice agent latency floor for AU telco
Edge SLM for in-store classification
Agentic QA on a regression-heavy codebase
Backpressure patterns for agent fan-out
Non-weight-bound learning via retrieval-updated skills
Sensing agent over store telemetry
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.