cookbook · vertical · tactical-edge-intel
Recipe · vertical

Disconnected ISR feeds, summarized in seconds.

A local .kolm that condenses raw ISR feed text (sigint, geoint excerpts, structured sensor logs) into a single-paragraph brief in the analyst's house style. Compiled inside the enclave on held-out analyst-graded notes; runs on a ruggedized laptop with no uplink.

base modelqwen2.5-7b-instruct
gold pairs520 (364 train / 156 eval)
k-score floor0.78
artifact size112 MB
compile time~50 min (in the enclave)
spec sourcesummarizer + grounded

What this recipe does

Analysts at the edge get raw feeds far faster than they can read them. This recipe compiles a small summarizer that produces a one-paragraph brief in the unit's house style. The grounded verifier rejects any claim that doesn't trace to a span in the input feed — the model can compress and structure but cannot invent.

The training corpus is pairs of (raw feed, analyst's actual brief) drawn from the unit's own archive. Held-out is a separate cohort the model never sees. Compile happens entirely inside the customer-controlled enclave; weights, gold corpus, and artifact never leave.

The spec

{
  "output_kind": "text",
  "length_bounds": { "min_words": 60, "max_words": 180 },
  "verifier": {
    "every_claim_must_be_grounded": true,
    "style_match_house_corpus": true,
    "banned_phrases": "./speculation-bans.regex"
  }
}

Compile (inside the enclave)

kolm compile "ISR-feed analyst brief in house style" \
  --base qwen2.5-7b-instruct \
  --pairs ./feed-brief-gold/*.jsonl \
  --offline-base-mirror ./base-models/ \
  --verifier grounded-claim,house-style \
  --k-floor 0.78 \
  --output tactical-edge-intel.kolm

ok wrote tactical-edge-intel.kolm
   k_score=0.81  signature=hmac-sha256
   grounded-claim 100% · house-style match 0.87

K-score gate

K-score 0.81 held-out 156 feeds · grounded-claim 100% · house-style 87% · analyst-rated useful 79%

Analyst rating: a panel re-read 50 held-out briefs and scored them useful / requires-rewrite / discard. 79% useful, 21% requires-rewrite, 0% discard. No held-out brief contained an ungrounded claim.

Run-time profile

Ruggedized laptop
3.4s
RTX 5090
680ms
Mac mini
3.1s
Embedded ARM
8.2s

Deploy

# Edge laptop — runs against incoming feed buffer:
on_feed_chunk = (chunk) => {
  const brief = kolm.run('tactical-edge-intel.kolm', chunk.text);
  cache.append(chunk.id, brief.text);
  audit.log({ artifact: 'tactical-edge-intel.kolm', chunk_id: chunk.id, k_score: brief.receipt.k_score });
};