> ## Documentation Index
> Fetch the complete documentation index at: https://oxy.tech/docs/llms.txt
> Use this file to discover all available pages before exploring further.
# Activity Logs, Enhanced Retrieval Accuracy, and Agent Preview Improvements
> Complete audit trail of all agent interactions in a comprehensive table view:
**July 17, 2025**
### **Activity Logs**
Complete audit trail of all agent interactions in a comprehensive table view:
* **Thread Overview** - View all conversation threads with their original prompts
* **Generated Query History** - See the exact SQL queries generated by agents for each request
* **Execution Metadata** - Track database targets, agent types, and verification status
* **Chronological Display** - All activities shown by creation date for easy review
### **Enhanced Retrieval Accuracy (Early Preview)**
*Note: This is an early preview feature and may encounter some edge cases during initial use*
Improve workflow and agent retrieval accuracy by specifying `include` and `exclude` keys in the `retrieval` configuration:
* **retrieval.include** - Prompts that should trigger this workflow or agent
* **retrieval.exclude** - Prompts that should not trigger this workflow or agent. For example, if prompting "Create annual user report" is erroneously triggering the `active_users` workflow, add it as an entry under the `exclude` key
Below is an example of how **retrieval.include** and **retrieval.exclude** can be utilized:
```yaml theme={null}
name: active_users
description: |
This workflow generates a report on active users.
retrieval:
include:
- "Create monthly report for active users"
exclude:
- "Create annual user report"
variables:
month: "{{ dimensions.month }}"
platform: "{{ dimensions.platform }}"
tasks:
- name: query_data
type: execute_sql
database: local
sql_query: |
SELECT * FROM monthly_active_user_by_platform.csv
WHERE month = '{{ month }}' AND platform = '{{ platform }}'
- name: report
type: agent
agent_ref: agents/local.agent.yml
prompt: |
Generate a report on active users based on the provided data.
The data includes user activity and their last login date.
[BEGIN DATA]
{{ query_data }}
[END DATA]
- Then generate a concise report using the following template:
Total active users:
Active users by organization:
Analysis:
- Analysis should focus on the activity levels without further judgment.
```
### **Enhanced Agent Preview Panel**
Significantly improved preview experience for agent development:
* **Artifact Support** - Preview panel now fully supports artifact generation and display
* **Rich Artifact Viewing** - Interactive artifact experience directly within the agent preview
### **Bug Fixes & Improvements**
Improved error handling when agents fail to answer questions, enhanced logging for better diagnostics, and minor footer UI updates for better visibility
