Hermes still needs close checks when you lack domain knowledge
A lack of Godot knowledge can waste a lot of time even when AI is helping. Checking results is harder when the project runs without a normal screen, and AI has trouble finding and fixing problems well. When progress reports and results were not reviewed closely, and almost every recommendation was accepted, the AI moved in a direction that did not match the intended goal.
The built work had to be deleted twice. The work became enjoyable again only after spending time learning more and seeing small parts actually work. Game creation needs strong systems, not only code structure.
In Godot, a felt easier to work with than leaning heavily on classes, inheritance, abstraction, and . The impact still needs more study, but became a core rule, and staying open to multiple models and tools, including Hermes, was useful.
Key points
- Do not accept every AI recommendation when you cannot judge the work well.
- Review reports and working results often so the agent does not drift away from your goal.
- Hard-to-feel problems like may need human testing, not only AI fixes.
- Use smaller tasks and check that each part works before moving on.
- Hermes can be useful as one tool among several models and tools.