Update README.md

README.md

@@ -1,6 +1,68 @@
-YDC is deeply committed to fostering an open-source ecosystem around AI Governance. YDC AI Governance artifacts include the components, controls, and regulations to support AI Governance. 
-Please select the AI Governance component from the list or select all. The system will output the list of associated controls and sample regulations.
+## Overview of the YDC_AIGOV Platform
 
-Disclaimer – These artifacts are not meant to provide legal advice. Please consult an attorney before making any decisions.
+The YDC AI_GOV platform employs multiple AI  agents to improve the AI Governance Posture of applications with embedded AI. 
 
+### Problem We Are Trying to Solve
+
+The primary challenge tackled by YDC AI_GOV is a lack of transparency and accessibility in AI policies associated with various applications. Key issues include:
+
+- Difficulty in Locating AI Policy URLs: Users often struggle to find the privacy policies relevant to the applications they use (AI policies are often embedded with company privacy policies).
+- Understanding AI Model Integrations: Many users are unaware if the applications they engage with contain embedded AI models and if their data is utilized in training these models.
+- Clarifying Opt-Out Options: There is often confusion regarding whether users have the option to opt-out of having their data used for AI training purposes.
+- Streamlining Compliance: Organizations face challenges in ensuring compliance with data governance regulations due to the complex nature of policy trails. 
+
+The YDC AI_GOV agents streamlines this process, making it easier for both users and organizations to navigate and understand the policies surrounding AI technologies.
+
+### Agent Architecture
+
+Agents used are as below :
+
+1. **Embedded AI Detector Agent**
+
+   Search the internet and fetch relevant data to determine if the application uses AI.
+
+2. **Policy Finder Agent**
+
+   AI Agent from CrewAI to find the privacy policy URL.
+
+3. **Policy Analyzer Agent**
+
+   Provides answers to the following questions:
+     - Is user data used for AI/ML training?
+     - Is there an opt-out option for AI/ML training?
+
+4. **Policy Decision Agent**
+
+    Makes final determinations on AI policies based on extracted insights from privacy policy text.
+
+### Risks
+
+**Hallucinations:** AI agents might generate incorrect or fabricated information when the required data is not available or poorly structured.
+
+**Incomplete Data:** Web scraping might miss or misinterpret content due to website restrictions or dynamic loading.
+
+**Bias and Misclassification:** AI may misclassify the presence of opt-out options or embedded AI due to ambiguous language.
+
+#### Agent-Specific Risks:
+
+1. **Embedded AI Detector Agent**
+
+   Fetches irrelevant or outdated information.
+
+2. **Policy Finder Agent**
+
+   Fails to find or retrieve incorrect URLs.
+
+3. **Policy Analyzer**
+
+   Misinterprets policy text due to ambiguous language.
+
+4. **Policy Decision Agent**
+
+   Hallucinates answers when information is incomplete or ambiguous.
+
+### Accuracy Metrics
+![accuracy_metrics](./accuracy1.png)
+
+--- 
 You can learn more about us [here](https://yourdataconnect.com/).