My Android AI agent writes every file as Markdown first. Here's why that made DOCX, XLSX and PDF less painful

Description and use

Kryzz AI v1.1.2 shares one Markdown model so the Android agent writes output once as structured Markdown and each exporter reads the same structure, solving format-specific inconsistencies in headings, tables, numeric cells, multi-sheet workbooks and Unicode handling in PDFs. The model runs via OpenRouter or optional providers, no analytics or bundled keys, generated files stay private, and the release APK is a debug build for Android 9+.

Problem

Users of an Android AI agent app need to produce real DOCX, XLSX and PDF files from agent output, but each exporter has its own inconsistent interpretation of headings, tables, numbers and Unicode, causing format-specific rendering problems that are hard to debug and fix independently.

Outcome

Sharing one Markdown model across DOCX, XLSX and PDF exporters eliminated format-specific rendering inconsistencies: headings became real headings, tables kept shape across formats, spreadsheet cells stayed typed numbers, multi-sheet workbooks worked, and PDFs handled Unicode.

Workflow

• Agent writes its answer once as structured Markdown.
• DOCX exporter reads the same Markdown structure and renders real headings and lists.
• PDF exporter reads the same Markdown structure and preserves table shape and Unicode support.
• XLSX exporter reads the same Markdown structure and produces typed cells so numeric columns can be summed.

Evidence

Three formats get messy fast if each exporter has its own idea of what a heading or a table is. A table can look fine in one format and come out flat in another, and fixing one can break the next.

So in v1.1.2 all three share one Markdown model.

Headings and lists come out as real headings and lists in the DOCX, not bold text pretending to be a heading.

Tables keep their shape across DOCX and PDF.

Spreadsheets get typed cells. A number stays a number, so you can actually sum a column in the XLSX instead of fighting text that looks like numbers.

Multi-sheet workbooks work, so a research task can put sources on one sheet and the summary on another.

PDFs handle Unicode, which matters to me because I write in both English and French.

The models are not on-device. Requests go from your phone to OpenRouter (or the optional providers you turn on). No analytics, no telemetry, no bundled keys.

Generated files stay in private app storage until you share them.

The APK on the release page is a debug build, Android 9+.