Read at InfoQ
Researchers at Microsoft and GitHub have conducted a study on building AI-powered product copilots, finding that developers struggle with integrating AI into projects and keeping up with best practices. They often resort to social media or academic papers for guidance. Safety, privacy, and compliance are also major concerns. One participant mentioned that AI models are fragile and require careful control and steering through prompting. Prompt engineering, the process of creating prompts for AI models, is identified as a significant challenge.
"A one-stop shop for integrating AI into projects remains a challenge. Developers are seeking a place to get started quickly, transition from a playground to an MVP, connect their various data sources to the prompts, and then move the AI components into their existing codebase efficiently," Austin Henley wrote. "A prompt linter could provide quick feedback. Developers also asked for a library or "toolbox" of prompt snippets for common tasks. Additionally, tracing the effect of prompt changes would be of huge value," Henley continued.