We Scored Oracle's Database Skill Live: 95% Isn't Enough
The video demonstrates how Oracle's database team utilized AI 'skills'—encapsulated in a repository like `oracle/skills`—to guide AI agents in writing secure and best-practice compliant SQL. The process involved running an automated review (using Tessl) on a skill designed to improve database code generation, which initially scored 95%. Through iterative refinement and applying changes via a 'run, review, fix' cycle, the skill was successfully upgraded to a 100% success rate, showcasing a robust mechanism for encoding complex domain knowledge into AI workflows.
Key takeaways
-
Purpose of Database Skills
5:51
The primary function of the skill is to help agents write better SQL and database code by making them knowledgeable about the database's capabilities (e.g., property graphs, vector data). It helps discover what the database can do, rather than relying solely on general agent knowledge.
-
Skill Review Process
13:44
The skill was subjected to an automated review comparing it against best practices. The process involves running a 'run, review, fix' cycle, which applies changes and re-runs the validation in an agile style approach.
-
Achieving 100% Compliance
14:35
After making specific developer-suggested changes (e.g., adding a recommended sequence task), the skill's review score reached 100%, demonstrating continuous improvement and validation of domain knowledge.