02 · KICE + TICE7-Layer Extraction

KICE + TICE

Stage 02 — twin agents mine the corpus in parallel across seven layers of knowledge, from rare concepts down to tribal know-how.

● available now — the L1–L7 extraction taxonomy, declared and documented

Roadmap: end-to-end KICE + TICE extraction runs against a frontier teacher

bus · nucleus.kice.corpus.updated

The technical how — seven layers, two extractors

The extraction stage of the Nucleus pipeline: two complementary agents work the same corpus in parallel across seven knowledge layers. KICE (Knowledge Injection & Corpus Evolution) owns the certifiable, cross-referenceable layers L1–L6; TICE (Tacit knowledge Injection & Corpus Evolution) owns L7 — the implicit expert know-how, tribal knowledge, and folklore the teacher absorbed but no one ever documented. The split is a deliberate lifecycle boundary: KICE runs fully autonomously over public, verifiable sources, while TICE's value concentrates in user-provided proprietary data and may cycle many more rounds in Mode 2, where the teacher has never seen the domain. Material arrives on three tracks — autonomous source connectors, user-dropped documents from ingest, and teacher-probed seed corpus — and each agent executes as a NATS-triggered service (KICE on port 8002, TICE on 8012) running traced, checkpointed execution graphs, writing scored ExtractionExamples into a versioned Lance columnar store where every append is an immutable, replayable corpus version, announced as a corpus-updated event per layer completed. Both agents are wired end-to-end today — all seven layers have run over a real user document; detection is keyword-heuristic in this phase, and the roadmap promotes L5–L7 detection to teacher inference.

The seven layers of knowledge depth

The L1–L7 taxonomy that grades a corpus by knowledge depth, from rare concepts down to what was never written down. Seven-Layer Extraction

LayerWhat it minesBase scoreAgent
L1Rare Concepts0.5KICE
L2Edge Cases0.5KICE
L3Historical Conflicts0.5KICE
L4Subsystem Interactions0.5KICE
L5Nuanced Reasoning0.6KICE
L6Ambiguity Detection0.6KICE
L7Tacit Knowledge0.7TICE

Scores are baselines, not verdicts — the rubric evolves across cycles as downstream evaluation reveals where the student is weak. L7 carries the highest baseline because tacit signal is the scarcest and most valuable.

Two agents, one corpus

KICE

The certifiable-knowledge extractor — layers L1–L6 of the seven-layer dig, run autonomously over public sources.

KICE — Knowledge Injection & Corpus Evolution — is the Nucleus agent that extracts certified, cross-referenceable knowledge across layers L1–L6: rare concepts, edge cases, historical conflicts, subsystem interactions, nuanced reasoning, and ambiguity detection. Each layer carries its own detection logic (keyword heuristics for L1–L3 and L6, cross-reference counting for L4, multi-indicator thresholds for L5) and a baseline quality score from 0.5 to 0.6 that evolves across cycles as the swarm's AutoResearch meta-agent reweights sources, shifts layer emphasis, and promotes keywords between layers. Knowledge arrives on three tracks: autonomous source connectors (git commits, mailing lists, CVE feeds, man pages, teacher probes, paper/repo/doc scouts), user-provided documents, and teacher-generated seed corpus. The agent runs as a NATS-triggered service on port 8002, publishing a completion event per layer and a corpus-updated event whenever the versioned Lance store advances. Wired end-to-end today, with connector-discovered sources stub-backed in dry runs; richer LLM-grade detection is the roadmap.

In the World →

TICE

The tacit-knowledge extractor — layer L7, the unwritten expert rules that no documentation scrape can find.

TICE — Tacit knowledge Injection & Corpus Evolution — is KICE's complement: where KICE extracts certified public knowledge (L1–L6), TICE extracts layer L7, the esoteric, tribal, implicit knowledge experts carry but rarely write down. Its detectors key on the language of lived experience — "everyone knows", "in practice", "rule of thumb", "the trick is", "gotcha", "foot gun" — and the layer carries a 0.7 baseline quality score, the highest of any layer, because tacit signal is the scarcest and most valuable: a single L7 example can be worth ten L1 examples. The richest L7 source is user-provided data, which is why TICE dominates Mode 2 runs and lives on its own lifecycle, cycling more rounds than KICE; mailing-list asides and code-review comments yield far more than commit messages, which record what changed rather than the unwritten rules behind the change. TICE runs as a NATS-triggered service on port 8012, writing scored examples into the same versioned Lance store as KICE. Wired end-to-end with unit-tested layer logic today; keyword indicators are the current detector, with teacher-inference detection on the roadmap.

In the World →

Both agents are NemoBots with deterministic execution graphs and Lance checkpoints: every run is traced and replayable, and every append to the versioned Lance store is an immutable corpus version announced per layer completed.

Inputs

Chunked corpus · teacher model (Tier 1 + Tier 2)

Outputs

L1–L7 raw extraction · auto-discovery rubrics

NATScorpus readiness announces on nucleus.kice.corpus.updated

Worked exampleA Mode 2 run over a user's maintenance manual: KICE's L4 detector flags a paragraph that cross-references two subsystems and scores it 0.5, while TICE's L7 indicators ("the trick is", "everyone knows") catch an aside no formal doc contains and score it 0.7 — both land in Lance as ExtractionExamples, the corpus version advances, and the synthesis stage downstream turns the haul into reasoning chains.

The vocabulary

For agents

$ curl "https://qukaizen.com/what?term=kice-tice&world=nucleus"

# the raw compiled artifact: /worlds/nucleus/terms.json

Dictionary →