BitProofConsole
Engine: loading… Demo environment
Acme Support AI › Systems

Connect a system

Point BitProof at the system you want covered. Nothing sensitive leaves your environment until you choose how the harness runs.

Support Agent v2.4

Base model
Qwen2.5-7B-Instruct fine-tune
Use case
Customer-support agent, tool calls
Target
AIUC-1 pack Annex IV mapping

Coverage goal

Application
AI-liability policy (Lloyd's paper)
Workspace
Shared with underwriter after compile

Harness deployment

Evidence sources

Model endpointapi.acme.ai/v2/agentConnected
Eval sampless3://acme-evals/support-v24Connected
Cloud configread-onlyConnected
Policy documents4 of 7
Vendor contractsNot connected
What gets collected, and what never leaves your environment

Automated domains call your endpoint or run inside your VPC; only results and signed attestations reach BitProof. Documentary evidence (policies, contracts) is uploaded by your team and flagged into remediation tasks when gaps exist. Weights are never uploaded.

Acme Support AI › Support Agent v2.4 › Assessment run

Assessment run #R-0847

Seven sample domains plus one live domain: computational integrity runs the actual RefKernel referee — compiled to WebAssembly, executing in your browser right now.

Idle
Performance sample
Hallucination sample
Robustness sample
Adversarial sample
Data leakage sample
Bias & fairness sample
Security sample
Comp. integrity LIVE
Documentary workflow — 11 of 15 complete, 3 remediation tasks open

Owner & governance ✓ · Incident-response plans ✓ · Oversight gates ✓ · Training-data provenance gap · Vendor AI addendum gap · Supply-chain attestation missing

Gaps generate assigned tasks; re-runs update the pack delta. The evidence stays current between renewals — this loop is the subscription, not a one-time scan.

Meridian Specialty › Submissions › Acme Support AI

Evidence pack EP-2026-0847

Read-only relying-party workspace · point-in-time, model-version-pinned · free for underwriters, auditors and reinsurers.

DomainScoreMethodStatus
Performance94AutomatedPass
Hallucination91AutomatedPass
Robustness88AutomatedPass
Adversarial82Automated2 findings
Bias & fairness90Automated + auditorPass
Comp. integrityBit-exact re-verificationSealed · live
GovernanceDocumentary1 gap

Verify the attestation yourself

Proves the assessment run wasn't edited after the fact. Real cryptography, running here — no trust in BitProof required.

Not verified yet
Technical detail

Ed25519 over domain-tagged canonical JSON; the seal binds model version, hardware, committed samples and results. Run the fabricated-trace scenario first if the receipt is empty.

Reliance letter

Relying party
Meridian Specialty
Purpose
Policy AI-2026-114 underwriting only
Liability cap
Assessment fee / PI limits
Scope
Point-in-time · v2.4 only
Fee
$2–5K one-time · paid by applicant

A litigable instrument with a named relying party and a real cap — not a marketing PDF.

Underwriting decision

Accepting this pack replaces your internal technical assessment for this submission. Evidence verified, capped, version-pinned above.

Concept demo. Sample-tagged scores are illustrative; everything tagged LIVE is the real RefKernel referee (100-test Rust crate, bit-identical native ↔ wasm) executing in this page: real witnesses over real Qwen2.5-7B RMSNorm weights, real bisection, real Ed25519 receipts.