
Overview
Every company processes hundreds of invoices every month. It costs $17 per invoice manually, takes 7-10 days, and existing AI tools approve invoices confidently — even fraudulent ones — with zero ability to verify their own reasoning. PlutusAudit AI fixes all three problems at once.
FIVE AGENTS, ONE PIPELINE
Agent 1 — Document Intelligence: Gemini 2.5 Flash reads any PDF or image directly using native multimodal vision. No OCR. No templates. Every field extracted with arithmetic validation.
Agent 2 — AI Chartered Accountant: Searches 80+ real GAAP and IFRS rules using hybrid FAISS + BM25 retrieval with HyDE query expansion, then generates a double-entry journal entry citing the exact standard paragraph.
Agent 3 — Fraud Detector: Computes 9 deterministic signals including Benford's Law MAD analysis, near-duplicate detection, round-number patterns, and invoice splitting. Passes signals to Featherless Qwen3-32B for calibrated 0-100 risk scoring. Financial data never touches a closed API.
Agent 4 — Verifier: Three independent aspect verifiers vote on every accountant output — numerical consistency, citation grounding, and schema conformance. If they disagree, the system retries with a structured critique. The system catches its own mistakes before they reach your books.
Agent 5 — Explainer and Audit Trail: Writes plain-English rationale for every decision and appends it to a SHA-256 hash-chained Postgres log. Edit any row directly in the database and the system detects the tamper in under one second. SOX-grade. EU AI Act Annex IV compliant.
LIVE RESULTS ON VULTR LONDON 57% touchless rate vs 30-50% industry average. 45 second processing time vs 7-10 days manual. $0.04 per invoice vs $17 manual cost. Fraud surfaced before payment released.
Note: the demo URL is substituted with the GitHub repository link.
No comments yet
Be the first to comment on this project.

FloatGPT — Omnipresent, Local-First AI Desktop Companion
FloatGPT is an omnipresent desktop AI companion that floats over Windows to automate OS workflows, plan tasks, and generate real-time executive dossiers. Operating 100% privately on your PC or powered by the cloud, it transforms daily computing with screen awareness and calm execution.

ClaimTrace
ClaimTrace audits the citations in a scientific manuscript: it checks that every reference exists and is described correctly, and that each cited source actually says what the citing sentence claims, with a verbatim quote as evidence. On 1,728 reference test cases it never marked a fabricated or altered reference as verified.

seashield ai
Ocean buoys feed disaster-warning centres, which trust what they receive. A hacked buoy can fake giant waves to trigger a false alarm, or hide a real storm. SeaShield AI checks every reading with four layers: cryptographic signatures, physics rules learned from real data, an AI anomaly model, and comparison with nearby buoys. Suspicious alerts are held for human review. Our live demo on Vultr replays real NOAA data from Hurricane Helene: launch attacks yourself and watch SeaShield stop them.




