Spaces:
No application file
No application file
Updated contents
Browse files
README.md
CHANGED
|
@@ -29,25 +29,29 @@ The YDC_AIGOV agents streamlines this process, making it easier for both users a
|
|
| 29 |
|
| 30 |
Agents used are as below :
|
| 31 |
|
| 32 |
-
1. **
|
|
|
|
|
|
|
|
|
|
|
|
|
| 33 |
|
| 34 |
Search the internet and fetch relevant data to determine if the application uses AI.
|
| 35 |
|
| 36 |
-
|
| 37 |
|
| 38 |
AI Agent from CrewAI to find the privacy policy URL.
|
| 39 |
|
| 40 |
-
|
| 41 |
|
| 42 |
Provides answers to the following questions:
|
| 43 |
- Is user data used for AI/ML training?
|
| 44 |
- Is there an opt-out option for AI/ML training?
|
| 45 |
|
| 46 |
-
|
| 47 |
|
| 48 |
Makes final determinations on AI policies based on extracted insights from privacy policy text.
|
| 49 |
|
| 50 |
-
|
| 51 |
|
| 52 |
Classifies an input applications as High risk, others and prohibited along with its rationale.
|
| 53 |
|
|
@@ -72,23 +76,27 @@ Agents used are as below :
|
|
| 72 |
|
| 73 |
#### Agent-Specific Risks:
|
| 74 |
|
| 75 |
-
1. **
|
|
|
|
|
|
|
|
|
|
|
|
|
| 76 |
|
| 77 |
Fetches irrelevant or outdated information.
|
| 78 |
|
| 79 |
-
|
| 80 |
|
| 81 |
Fails to find or retrieve incorrect URLs.
|
| 82 |
|
| 83 |
-
|
| 84 |
|
| 85 |
Misinterprets policy text due to ambiguous language.
|
| 86 |
|
| 87 |
-
|
| 88 |
|
| 89 |
Hallucinates answers when information is incomplete or ambiguous.
|
| 90 |
|
| 91 |
-
|
| 92 |
|
| 93 |
Often targets specific keywords from the description, which may give incorrect responses in some cases.
|
| 94 |
|
|
|
|
| 29 |
|
| 30 |
Agents used are as below :
|
| 31 |
|
| 32 |
+
1. **Fuzzy Matching Agent**
|
| 33 |
+
|
| 34 |
+
Transforms the entered application name into the correct app name by correcting spelling errors, removing special characters, and addressing other inconsistencies.
|
| 35 |
+
|
| 36 |
+
2. **Embedded AI Detector Agent**
|
| 37 |
|
| 38 |
Search the internet and fetch relevant data to determine if the application uses AI.
|
| 39 |
|
| 40 |
+
3. **Policy Finder Agent**
|
| 41 |
|
| 42 |
AI Agent from CrewAI to find the privacy policy URL.
|
| 43 |
|
| 44 |
+
4. **Policy Analyzer Agent**
|
| 45 |
|
| 46 |
Provides answers to the following questions:
|
| 47 |
- Is user data used for AI/ML training?
|
| 48 |
- Is there an opt-out option for AI/ML training?
|
| 49 |
|
| 50 |
+
5. **Policy Decision Agent**
|
| 51 |
|
| 52 |
Makes final determinations on AI policies based on extracted insights from privacy policy text.
|
| 53 |
|
| 54 |
+
6. **Risk Classifier Agent**
|
| 55 |
|
| 56 |
Classifies an input applications as High risk, others and prohibited along with its rationale.
|
| 57 |
|
|
|
|
| 76 |
|
| 77 |
#### Agent-Specific Risks:
|
| 78 |
|
| 79 |
+
1. **Fuzzy Matching Agent**
|
| 80 |
+
|
| 81 |
+
Incorrect or incomplete app name matches due to imperfect algorithms and variations in spelling or formatting.
|
| 82 |
+
|
| 83 |
+
2. **Embedded AI Detector Agent**
|
| 84 |
|
| 85 |
Fetches irrelevant or outdated information.
|
| 86 |
|
| 87 |
+
3. **Policy Finder Agent**
|
| 88 |
|
| 89 |
Fails to find or retrieve incorrect URLs.
|
| 90 |
|
| 91 |
+
4. **Policy Analyzer**
|
| 92 |
|
| 93 |
Misinterprets policy text due to ambiguous language.
|
| 94 |
|
| 95 |
+
5. **Policy Decision Agent**
|
| 96 |
|
| 97 |
Hallucinates answers when information is incomplete or ambiguous.
|
| 98 |
|
| 99 |
+
6. **Risk Classifier Agent**
|
| 100 |
|
| 101 |
Often targets specific keywords from the description, which may give incorrect responses in some cases.
|
| 102 |
|