Effective Date: March 8, 2026
We believe in Transparency. Here is how AI is used in our platform and what you should know.
1. AI Models We Use
AI Prompt Architect uses Google Gemini large language models (LLMs) to power its analysis, generation, and refinement features. We currently use:
- Gemini 2.5 Pro: For advanced reasoning and complex architecture generation.
- Gemini 2.5 Flash: For fast, efficient analysis and refinement tasks.
2. How AI Outputs Are Generated
When you use our platform, your input (project description, requirements, constraints) is processed by our proprietary "Architect" logic, which constructs structured prompts sent to the AI model. The model generates probabilistic output based on its training data.
⚠️ Important: AI outputs are suggestions, not guarantees. They may contain errors, outdated information, or suboptimal code. Always review, test, and validate AI-generated content before using it in production.
3. Data Usage & Training
- We do NOT use your prompts or outputs to train AI models.
- We do NOT share your inputs with other users.
- Your data is processed only for the purpose of generating your requested output.
4. Automated Decision-Making
AI Prompt Architect does NOT make automated decisions that have legal or significant effects on users. All AI outputs are advisory tools for human review. Credit deductions are rule-based calculations, not AI decisions.
5. Limitations
- AI models can "hallucinate" — generating plausible but incorrect information.
- Outputs may not reflect the latest version of libraries, frameworks, or APIs.
- The quality of output depends significantly on the quality and specificity of input.
- AI cannot replace human judgement for security-critical or safety-critical systems.
6. Contact
For questions about our AI practices, contact luke@mcconversions.uk.