Your hallucination checker only sees the final paragraph

Your hallucination checker only sees the final paragraph. That’s the bleed. A fluent wrong number often starts earlier: empty retrieval, a swallowed tool error, a stale cache after a fact update. Score the prose alone and you miss the cause — then the model fills the gap confidently. Old way Most “anti-hallucination” tools optimize one job: grade the answer text (encoder / HHEM-class model / LLM-as-judge). Useful. Incomplete for agents. What they usually can’t do: Halt before generation when the preload is already broken Name a cause-side failure (empty retrieval, tool fail, stale cache) Return an auditable gate you can log in an incident channel — not only 0.87 New way After the model speaks (and optionally before it does), run a verdict: Cause — handbook forensics on runtime evidence Effect — ground the answer against the preload you provided One output — ShineVerdict: decision + named resolution_gate + evidence_hash That product is PrismShine (Apache-2.0, pip install). It is not a prompt-injection firewall (that’s PrismGuard). It is not an agent runtime (that’s ChorusGraph). One job: verify answers against evidence. Proof (in-post — Shine-only receipt) Public comparative vs Vectara HHEM-2.1-Open on HaluEval (Azure ACI · ONNX Tier-3 · receipt 2026-07-20_run4_onnx): System B1 QA F1 B2 numbers F1 B1 p50 LLM prismshine-fast 0.831 1.000 (0 FP) ~90 ms 0 hhem-2.1-open 0.746 0.926 ~216 ms 0 Receipt folder on GitHub: benchmarks/progress/2026-07-20_run4_onnx (link in first comment). Plan — try it in under a minute bash pip install "prismshine==0.2.2" prismshine verify --demo prismshine capabilities Core path = Tiers 0–2, CPU, 0 LLM calls by default. from prismshine import EvidenceBundle, PreloadChunk, ShineGate gate = ShineGate.build(profile="default") bundle = EvidenceBundle( run_id="demo", question="What was revenue?", answer="Revenue was $1000 in Q1.", preload=[ PreloadChunk( chunk_id="c1", text="Revenue was $1000 in Q1.", source="retrieval", ) ], ) verdict = gate.verify(bundle) print(verdict.decision, verdict.resolution_gate, verdict.evidence_hash) 0.2.2 drop-in helpers: validate_grounding · get_gate · enforce_mode_from_env Shadow without blocking: PRISMSHINE_ENFORCE=0 Docs: INTEGRATION.md §0 (link in first comment). There’s also a no-API-key browser demo (link in first comment) — pass → fabricated number block → empty-retrieval halt. Honest limits (BIP) PASS ≠ world-true — grounded in your preload only Buffered answers (not mid-stream token verification) Bare pip install prismshine ≠ Tier-3 span SotA; use prismshine[spans] + ONNX when you need that path Wired runtime moat is a separate Docker receipt — don’t mix it unlabeled with the HHEM table above Soft ask If you try verify --demo and hit a snag, paste the traceback in the comments — I’ll help. Where would you wire the gate first — after the LLM node, before generation (halt empty retrieval), or both? ### First comment (after publish) Links (kept out of the lesson above on purpose): Landing → https://www.insightits.com/products/prismshine.html Demo → https://insightitsgit.github.io/PrismShine/demo.html GitHub → https://github.com/insightitsGit/PrismShine PyPI 0.2.2 → https://pypi.org/project/prismshine/0.2.2/ Receipt → https://github.com/insightitsGit/PrismShine/tree/main/benchmarks/progress/2026-07-20_run4_onnx YouTube → https://www.youtube.com/watch?v=OZCelVhP844 Product Hunt → (paste live PH URL) Smoke: pip install "prismshine==0.2.2" && prismshine verify --demo Enter fullscreen mode Exit fullscreen mode