+
+
+
+
+
+
+
+
+
+
+
+ ⓪ Not a CRM — an index that learns from you
+ loading growth numbers…
+ ▾ click to collapse
+
+
+ If you've worked on a legacy staffing CRM, your mental model is field inventory —
+ every concept must be a visible column, dropdown, or checkbox, or it doesn't exist. This
+ system works the opposite way: concepts don't need to be pre-declared because the
+ hybrid index + playbook memory learns them when you work a contract.
+ The rows below translate the familiar legacy surface into what actually happens here,
+ with real numbers for every claim.
+
+
+
+
Analyzing contracts and workers...
-
-
+
+
- Substrate Signals — Architecture Live
- Instant search · Hot-swap-ready index · Self-regulating memory
+ ① Live Market — Chicago right now
+ Public permit data pulled live · clock aligned to current shift · refreshed every page load
+ The clock shows where we sit in the 24-hour cycle. Colored arcs mark the 4 standard
+ staffing shifts; the red needle is now. The panel beside it summarizes what Chicago's
+ public permit system is asking for right now — staffing demand before anyone's acted
+ on it. This is the real world the rest of the page is reacting to.
+
- Live Contracts — Chicago Permits → Proposed Fills
+ ② Staffer's Console — what's on your plateReal public permit data + worker bench + past playbook patterns
+
+ This is what a recruiter or coordinator sees when they open the console. Each card is
+ one open permit ranked against our 500K worker bench. The fill-probability bar
+ shows cumulative chance of filling by day; the economics panel projects
+ gross revenue, margin, and payout window; the over-bill pool flags workers
+ whose pay exceeds the contract's bill rate — they go into a margin-watch bucket instead
+ of being rejected outright.
+
+ ③ Worker Search — find someone specific
+ Natural language search
+
+
+ Type a plain-English description — role, location, trait, certification.
+ The query hits the hybrid SQL + vector index over all 500K worker profiles
+ and ranks by semantic match, reliability, and availability. Try one of the
+ sample searches below or write your own.
+
+
+
+
+
+
+
+
+
+
+
+
- System Activity
- Learning from every interaction
+ ④ System Activity — how the substrate learns
+ Playbook memory, pathway traces, self-tuning indices
+
+ Every completed fill, every accepted playbook, every rejected candidate feeds
+ back into the substrate. This strip shows what the system has learned since
+ the last run — which patterns are compounding, which memories are fresh,
+ which indices are being exercised. If it's empty, the system hasn't seen
+ enough traffic yet to form a memory worth showing.
+
-
+
+
- Worker Search
- Natural language search
+ ⑤ Substrate Signals — architecture health
+ Live probes of the index, memory, and pathway layers
+
+
+ These tiles measure the architecture itself, not the staffing workload.
+ Instant-search latency, index shape, playbook-memory depth, pathway-matrix
+ compounding — four probes that answer "is the substrate healthy right now?"
+