Collect, analyze, and publish
research data — all in one place.

DeCiphr runs in strict coding mode — a core methodological safeguard designed for rigorous research.

🔒 Strict coding mode The AI is explicitly constrained to assign only the values defined in your framework codes. It cannot introduce observations, categories, or terminology beyond what you have defined. If the image does not clearly match a code, the AI outputs "uncodable" rather than guessing. This ensures your results reflect your framework — not the AI's assumptions.

It is instructed, not trained. Training would mean permanently modifying the underlying AI model — which is not possible here. Instead, DeCiphr uses prompt engineering: your framework, codes, and definitions are passed to the AI as precise instructions at the moment of analysis. The AI reads your image using its full visual capabilities, but what it is permitted to report is controlled by your framework and the mode you have selected. This distinction is important for methodological transparency in research publications.

Yes — this is one of DeCiphr's core use cases. The built-in frameworks are grounded in established analytical approaches in linguistic landscape studies, multimodal discourse analysis, and related fields. For any other analytical framework, you can create a custom scheme: enter the original codes and their definitions, write a master prompt that situates the analysis within the appropriate analytical context, and enable strict coding mode to ensure the AI applies only those codes. The .sigframe file format also allows you to share your configured framework with other researchers so the analytical procedure is fully replicable.

We recommend being explicit about the tool, the constraints applied to the AI, and the human analysis and oversight involved in your research.

DeCiphr makes this straightforward. Use the Methodology Export feature (Framework Editor → Export Methods Section) to generate a plain-text description of your framework, the exact AI prompt used, all code definitions, and your reference list — ready to paste into a methods chapter or appendix. Your institution's ethics board or journal reviewers can then evaluate exactly what instructions the AI was given, that it operated in strict coding mode, and how results were reviewed.

The AI Audit Trail in your CSV and Excel exports documents the exact prompt sent per item and the raw AI response, which you may also choose to include as a supplementary file for full reproducibility. For studies involving multiple coders, the built-in Inter-Rater Reliability tool calculates Cohen's Kappa per field and generates a report you can reference directly in your methods.

All your data — photos, coded results, frameworks, and analytic memos — is stored exclusively on your device. Nothing is uploaded to any server operated by the app developer. When you run an AI analysis, the image is sent to Anthropic's servers (Claude Vision API) solely to perform the analysis, and is not retained by Anthropic beyond the API request. The app developer has no access to your images, data, or frameworks at any time.