Watch verified intelligence compound.
Every metric on this page is read directly from Seed's verification engine — the inputs behind the Verified Intelligence Index (VII), Knowledge Reliability Score (KRS), Knowledge Consistency Index (KCI), and the Continuous Intelligence Benchmark (CIB). No simulations, no projections — only the real shape of the system as it learns from real conversations in chat.
Knowledge growth · last 30 days
Cumulative verified facts vs total events processed by the verification engine.
How Seed builds verified intelligence
Seedthink is not a single model. It is a swarm of narrow, specialised Seeds that collectively feed a shared substrate — the verified knowledge layer that learns from every conversation, verifies every fact, and continuously improves its Verified Intelligence Index (VII).
Narrow Seeds grow in chat
Users plant Seeds for specific topics. Each Seed remembers context, learns from corrections, and builds its own verified fact graph.
View data sources →Facts are verified before joining the shared substrate
When a Seed learns something new, it runs through the verification engine. Only facts above the confidence threshold enter the shared knowledge pool — raising the Knowledge Reliability Score (KRS).
View data sources →Every verified fact feeds the shared substrate
The shared Seed reads the verified corpus — never private user data. The Knowledge Consistency Index (KCI) keeps the graph coherent as new facts arrive and old ones decay.
View data sources →Verified intelligence compounds
As verified knowledge grows, the Continuous Intelligence Benchmark (CIB) tracks reliability over time. The lightweight reasoner gets sharper because its grounded context gets cleaner — no retraining required.
View data sources →The Verified Intelligence Maturity Model (VIMM)
Verified intelligence is not a switch — it is a ladder. Seed climbs it one verified fact at a time.
Self-aware fact graph
LiveSeed already knows what it knows. It can answer questions, cite facts, and admit when it does not have enough confidence.
Self-directed learning goals
In progressSeed starts setting its own learning goals based on gaps in its knowledge graph. It actively seeks the sources and conversations that will teach it the most.
Swarm orchestration
NextSeed reads all planted Seeds and coordinates the swarm. It merges overlapping niches, splits overgrown ones, and routes queries to the best narrow Seed.
Self-improving verification
FutureSeed proposes refinements to its own prompts, verification rules, and lifecycle thresholds, runs evals against the CIB baseline, and merges only the changes that measurably improve VII and KRS.
What you're looking at
These are real platform metrics, updated every time Seed answers a question and the verification engine extracts new facts. Nothing here is simulated. See the live stream on /learning.