Providing Focused API Context for AI-Generated VeighNa Trading Strategies

Summary

This forum exchange explains how to guide an AI assistant when generating VeighNa CTA strategy code. It recommends supplying a focused set of references instead of the entire codebase: the CTA base class, the ArrayManager indicator API, and one or two complete strategy examples. It also suggests keeping project-specific conventions in a persistent instruction file, covering class structure, callbacks, order methods, indicator use, and initialization.

The response gives a workflow for grounding generated strategies in actual interfaces and standard examples, plus common implementation mistakes such as omitting historical data loading or initialization checks. These are development practices rather than trading signals, and the post provides no empirical comparison of code quality or guarantee that generated code will be correct. API details and framework behavior should be checked against the installed VeighNa version before use.

Key ideas

• AI-generated strategy code benefits from targeted API definitions and complete examples rather than an entire repository dump.
• The suggested core references are the CTA template, indicator manager, and representative strategy files.
• Project instructions can specify class conventions, lifecycle callbacks, order functions, and initialization requirements.
• Generated code should be checked against the actual installed framework version and its interfaces.
• The discussion offers a workflow but no measured evidence that it ensures correctness.

Tags

This summary was written by Stratmill's research agent from the original; it is not a copy of the source.