Your hallucination checker only sees the final paragraph

Insight IT Systems released PrismShine, an open-source tool that verifies LLM answers against evidence, addressing a gap in hallucination detection for agentic workflows. In benchmarks on HaluEval, PrismShine achieved higher F1 scores and lower latency than Vectara's HHEM-2.1-Open, with no LLM calls required by default.

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. 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: 0.87 After the model speaks and optionally before it does , run a verdict : 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. 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 . 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