Starting from templates
Building a flow from scratch is straightforward, but starting from a proven template is faster. Ritemark ships with a set of flow templates that cover the most common writing automation patterns. Each template is a complete, working flow that you can use as-is or customize to fit your specific needs.
Templates are not locked. Once you load one into your project, it becomes a regular flow file that you can edit freely. Think of them as starting points, not constraints.
Release notes generator
This is one of the most requested templates. If your team maintains a changelog file, whether in KEEP A CHANGELOG format or a simple Markdown list, this flow turns raw developer notes into polished customer-facing release notes.
The flow reads your changelog file and extracts entries since the last release tag. It sends those entries to an LLM with instructions to rewrite them for a non-technical audience. Technical jargon gets translated into plain language. Internal references get stripped out. Bug fixes get grouped separately from new features so readers can scan for what matters to them.
The output is a formatted Markdown file ready to paste into your release page, email newsletter, or product blog. The tone stays consistent because the prompt is the same every time. No more spending twenty minutes per release wondering how to phrase "refactored the event handler debounce logic" for customers who just want to know what changed.
Blog post from outline
Writers who plan with outlines know the gap between having a structure and having a finished draft. This template bridges that gap. You write an outline with section headings and a few bullet points under each, and the flow expands it into a full first draft.
The flow reads your outline file and sends it to an LLM in two passes. The first pass generates prose for each section based on your bullet points, keeping the structure you defined. The second pass reviews the complete draft for transitions between sections, making sure the piece reads as a cohesive whole rather than a series of disconnected paragraphs.
You still need to edit the output. The flow produces a first draft, not a final one. But it gets you from outline to editable prose in about a minute instead of an hour. The two-pass approach is important here. A single prompt tends to lose coherence across longer pieces because the model generates each section without seeing what came before. The review pass catches those gaps.
Batch document processor
This template solves a different problem entirely. Instead of processing one file through multiple steps, it processes multiple files through the same step.
Say you have thirty help articles that need their tone updated after a brand voice refresh. Or fifty product descriptions that need a new disclaimer paragraph added. Doing this by hand means opening each file, making the edit, saving, and moving on. Even with AI assistance, the manual file handling adds up.
The batch processor flow takes a folder path as input and lists all Markdown files in it. It runs each file through an LLM node with your instructions, applies whatever transformation you specified, and writes the updated version back. You can configure it to overwrite in place or to write to a separate output folder if you want to review before committing.
The key setting is the batch size. Processing thirty files means thirty LLM calls, so the flow runs them sequentially to avoid rate limits. For large batches, you can set it running and come back when it finishes.
Translation pipeline
The fourth template tackles multilingual content. If you maintain documentation or marketing content in multiple languages, this flow automates the first-draft translation while preserving your file structure.
The flow reads a source file, sends it to an LLM with translation instructions and a glossary of preferred terms, and writes the translation to a mirrored file path. If your source is at content/en/getting-started.md, the output goes to content/et/getting-started.md. You provide the glossary as a separate file that the flow reads at the start, so brand terms and product names stay consistent.
This is not a replacement for human review of translations, especially for published content. But it eliminates the blank page problem. Your translator or bilingual team member starts with a reasonable draft instead of starting from zero.
Making templates your own
Every template is a JSON file in your project's .ritemark/flows/ directory. Open any template in the flow editor and you see all its nodes laid out on the canvas. Change the prompts to match your voice. Swap the file paths to point at your content. Add nodes if you need extra processing steps. Remove nodes you do not need.
The templates are meant to be modified. They show you what a well-structured flow looks like, and then they get out of your way.
Download Ritemark and start with a template that fits your workflow.