dcata004 commited on
Commit
03aa44d
·
verified ·
1 Parent(s): 1b29b2c

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +41 -31
README.md CHANGED
@@ -1,8 +1,8 @@
1
  ---
2
  title: README
3
- emoji: 💻
4
- colorFrom: purple
5
- colorTo: green
6
  sdk: gradio
7
  pinned: false
8
  sdk_version: 6.2.0
@@ -12,13 +12,17 @@ sdk_version: 6.2.0
12
 
13
  # 🛡️ Cata Risk Lab
14
  ### Sovereign AI Assurance & Technical Gatekeeping
15
- Miami | Serving Swiss, UK & Australian Markets
16
 
17
  [![License: MIT](https://img.shields.io/badge/License-MIT-yellow.svg)](https://opensource.org/licenses/MIT)
18
- [![DOI](https://zenodo.org/badge/1129726606.svg)](https://doi.org/10.5281/zenodo.18174088)
19
  [![Compliance: nFADP](https://img.shields.io/badge/Compliance-nFADP%20Ready-red)](https://www.fedlex.admin.ch/eli/cc/2022/491/en)
20
  [![Compliance: EU AI Act](https://img.shields.io/badge/Compliance-EU%20AI%20Act-blue)](https://artificialintelligenceact.eu/)
21
 
 
 
 
 
22
  </div>
23
 
24
  ---
@@ -31,49 +35,55 @@ Our mission: Empower any developer to run enterprise-grade sovereignty audits in
31
 
32
  **Built with care. Powered by people. Open by design.**
33
 
34
-
35
- ### Core Methodology
36
- We operate on a **"Compliance-in-the-Loop"** architecture designed for:
37
- * **Swiss Banking Standards (nFADP)**
38
- * **EU AI Act (High-Risk Classification)**
39
- * **UK & Australian Privacy Principles**
40
 
41
  ---
42
 
43
- ## Deployed Architectures
44
 
45
- ### [🛡️ Veritas: The Hallucination Auditor](https://huggingface.co/spaces/Cata-Risk-Lab/Veritas-Auditor)
46
- *Status: Live (v1.0.0)*
 
47
 
48
- Veritas is our flagship **RAG (Retrieval Augmented Generation) Auditor**. It ingests financial and regulatory documentation (PDFs) and answers queries with strict adherence to the source text.
 
 
49
 
50
- * **Zero-Trust Retrieval:** Returns explicit "FAIL" verdicts for missing data.
51
- * **Audit Trail:** Generates citation-backed logs.
52
- * **Tech Stack:** `LangChain` | `Azure OpenAI` | `ChromaDB` | `Python`
53
 
54
- > "A guess in a regulatory audit is not a glitch. It is a lawsuit."
 
 
55
 
56
  ---
57
 
58
- ## Technology Stack
59
- We build using "Industrial-Grade" open source and enterprise foundations:
60
 
61
- | Layer | Technology |
62
- | :--- | :--- |
63
- | **Orchestration** | LangChain, LlamaIndex |
64
- | **Inference** | Azure OpenAI (GPT-4o), Google Gemini 1.5 Pro |
65
- | **Vector Search** | ChromaDB, Azure AI Search |
66
- | **Deployment** | Microsoft Foundry, Hugging Face Spaces |
 
67
 
68
  ---
69
 
70
- ## Contact & Governance
71
- **Cata Risk Lab** operates as a technical due diligence partner for Enterprise Clients.
72
 
 
 
73
  * **GitHub:** [github.com/dcata004](https://github.com/dcata004)
74
- * **Verification:** DOI Minted via Zenodo for all Audit Artifacts.
75
 
76
- ---
77
  <div align="center">
 
78
  <i>"Sovereignty is the new Compliance."</i>
79
  </div>
 
1
  ---
2
  title: README
3
+ emoji: 🛡️
4
+ colorFrom: blue
5
+ colorTo: red
6
  sdk: gradio
7
  pinned: false
8
  sdk_version: 6.2.0
 
12
 
13
  # 🛡️ Cata Risk Lab
14
  ### Sovereign AI Assurance & Technical Gatekeeping
15
+ **Miami | Serving Swiss, UK & Australian Markets**
16
 
17
  [![License: MIT](https://img.shields.io/badge/License-MIT-yellow.svg)](https://opensource.org/licenses/MIT)
18
+ [![DOI](https://zenodo.org/badge/DOI/10.5281/zenodo.18174088.svg)](https://doi.org/10.5281/zenodo.18174088)
19
  [![Compliance: nFADP](https://img.shields.io/badge/Compliance-nFADP%20Ready-red)](https://www.fedlex.admin.ch/eli/cc/2022/491/en)
20
  [![Compliance: EU AI Act](https://img.shields.io/badge/Compliance-EU%20AI%20Act-blue)](https://artificialintelligenceact.eu/)
21
 
22
+ <br/>
23
+
24
+ > *"In an era of generative hallucination, a guess is not a glitch. It is a lawsuit."*
25
+
26
  </div>
27
 
28
  ---
 
35
 
36
  **Built with care. Powered by people. Open by design.**
37
 
38
+ We do not build "creative" chat bots. We build **Sovereign Auditors** that enforce:
39
+ * **Data Sovereignty:** Ensuring data never crosses borders illegally (nFADP/GDPR).
40
+ * **Citation Accuracy:** If the AI cannot cite the source, the AI must fail.
41
+ * **Liability Containment:** Shifting risk away from the enterprise.
 
 
42
 
43
  ---
44
 
45
+ ## 🏛️ Deployed Sovereign Tools (Live)
46
 
47
+ ### 1. [🇨🇭 Swiss Risk Calculator](https://huggingface.co/spaces/Cata-Risk-Lab/Swiss-Risk-Calculator)
48
+ * **Role:** Regulatory Risk Assessment
49
+ * **Function:** Maps AI deployments against the **Swiss nFADP** and **EU AI Act**. Calculates risk tiers based on data sensitivity and user volume.
50
 
51
+ ### 2. [🛡️ Veritas: The Hallucination Auditor](https://huggingface.co/spaces/Cata-Risk-Lab/Veritas-Auditor)
52
+ * **Role:** RAG Auditing Engine
53
+ * **Function:** Ingests financial PDFs and forces strictly cited responses. Returns `FAIL` verdicts for hallucinations using the Ragas framework.
54
 
55
+ ### 3. [🇦🇺 Wattle Guard: Australian Sovereignty](https://huggingface.co/spaces/Cata-Risk-Lab/Wattle-Guard)
56
+ * **Role:** APP 8 Compliance Validator
57
+ * **Function:** Automates cross-border disclosure audits for Australian entities. Detects server jurisdictions to prevent SOCI Act violations.
58
 
59
+ ### 4. [📜 Liability Scanner](https://huggingface.co/spaces/Cata-Risk-Lab/Liability-Scanner)
60
+ * **Role:** Contract Forensics
61
+ * **Function:** Scans vendor "Terms of Service" URLs for high-risk clauses (e.g., "Right to Train," "Perpetual License") that violate data privacy.
62
 
63
  ---
64
 
65
+ ## Industrial Tech Stack
66
+ We build strictly on enterprise-grade, auditable infrastructure.
67
 
68
+ | Layer | Technology | Purpose |
69
+ | :--- | :--- | :--- |
70
+ | **Orchestration** | `LangChain` / `LlamaIndex` | Logic flow and chain-of-thought governance. |
71
+ | **Inference** | `Azure OpenAI (GPT-4o)` | Private, firewalled reasoning engine. |
72
+ | **Memory** | `ChromaDB` / `Azure AI Search` | Vector storage with strict access controls. |
73
+ | **Deployment** | `Hugging Face Spaces` | Public audit infrastructure. |
74
+ | **Validation** | `CERN Methodology` | Reproducible testing protocols for AI outputs. |
75
 
76
  ---
77
 
78
+ ## Contact & Governance
79
+ **Cata Risk Lab** operates as a technical due diligence partner. We provide fixed-price audit packages for Shadow AI Discovery and Vendor Due Diligence.
80
 
81
+ * **Principal:** Anthony D. Cata
82
+ * **Locations:** Miami (HQ) | Zurich (Partner Network)
83
  * **GitHub:** [github.com/dcata004](https://github.com/dcata004)
84
+ * **Verification:** All software artifacts are DOI Minted via Zenodo for permanent audit trails.
85
 
 
86
  <div align="center">
87
+ <br/>
88
  <i>"Sovereignty is the new Compliance."</i>
89
  </div>