# AI use cases for Kition (KitionAI/kition) Repo: [KitionAI/kition](https://github.com/KitionAI/kition) | Use cases: 5 | Page: https://dedupedai.com/use-cases/kitionai-kition/ Kition is a desktop workspace that combines Markdown documents, structured tables, an infinite Whiteboard, a tool-using AI agent, web research, and visual workflows. This file holds every use case of this repo. Each one starts with a "## " heading and ends with its URL. - Review agent edits to a Markdown document line by line: https://dedupedai.com/use-cases/kitionai-kition/review-agent-edits-to-a-markdown-document/ - Turn receipt photos into searchable table records: https://dedupedai.com/use-cases/kitionai-kition/turn-receipt-photos-into-searchable-records/ - Generate 16:9 and 9:16 thumbnail batches from a table: https://dedupedai.com/use-cases/kitionai-kition/generate-campaign-thumbnails-in-a-table-batch/ - Route inbox messages into a table with a workflow: https://dedupedai.com/use-cases/kitionai-kition/sync-inbox-messages-into-a-workflow-table/ - Run the Kition web client from source for UI work: https://dedupedai.com/use-cases/kitionai-kition/run-kition-client-from-source-for-ui-work/ ## How to review agent edits to a Markdown document line by line with Kition Repo: [KitionAI/kition](https://github.com/KitionAI/kition) | Difficulty: Beginner | Time: 30 minutes | Basis: From the README Let the Kition Agent edit a real document, then accept or reject each addition and deletion. **Who it is for:** A writer, researcher, or team lead who wants an AI agent to revise a document but must approve every change before it stays in the file. **The problem:** Copying chat suggestions back into a document is slow and loses the context of the original file, and blind AI edits are risky. **The outcome:** An updated Markdown file in the workspace where every change was reviewed and each addition or deletion was kept or rejected. ### Steps 1. Download the latest desktop build from GitHub Releases (the .dmg on macOS, the installer on Windows, or the x86_64 .AppImage on Linux). 2. Open a Markdown document in a Kition workspace and make a backup copy of the workspace first. 3. Ask the Agent in natural language to make a scoped change to the active document. 4. When the file changes, open the document review surface and inspect the highlighted additions, deletions, and rewrites. 5. Accept or reject each change individually, or review the whole edit as one set. ### Prompt to paste into your agent ```text Using the Kition app in the workspace at , ask the Agent to revise the document with the goal . Confirm the document review surface lists each addition, deletion, and rewrite, and report the number of changes you kept and rejected. ``` ### Caveat The README says Kition is in beta, so back up the workspace and review every Agent change before relying on it in production. Disclaimer: Third-party repos we don't own or vouch for. AI-generated use cases can be wrong: review everything and run at your own risk. Full text: https://dedupedai.com/disclaimer/ URL: https://dedupedai.com/use-cases/kitionai-kition/review-agent-edits-to-a-markdown-document/ ## How to turn receipt photos into searchable table records with Kition Repo: [KitionAI/kition](https://github.com/KitionAI/kition) | Difficulty: Beginner | Time: 45 minutes | Basis: From the README Drop receipt images into an attachment field and let vision-powered fields fill in vendor, category, and text. **Who it is for:** A freelancer, small business owner, or household admin who keeps a pile of receipt photos for expense tracking. **The problem:** Typing receipt details by hand takes time, and photos in a folder cannot be filtered or summarized. **The outcome:** A table where each receipt row holds its image, vendor, address, category, structured JSON, and OCR text, ready to filter and summarize. ### Steps 1. Download and install the Kition desktop build from GitHub Releases. 2. Create a table file with an attachment field and AI fields for vendor, address, category, structured JSON, and OCR text. 3. Drop the receipt photos into the attachment field, one receipt per row. 4. Check the extracted values in each row and correct any mistakes. 5. Use table filters or ask the Agent to summarize the corrected rows. ### Prompt to paste into your agent ```text In the Kition desktop app, open the table that has receipt attachments and AI extraction fields. Ask the Agent to total the category values for the rows marked , and check that each total matches the corrected rows before you use it. ``` ### Caveat The README describes vision-powered fields but does not name the model providers or accuracy, so verify extracted values before relying on them. Risk, credentials: Receipts can show account numbers, addresses, and personal purchase details, so check what the AI fields send to your configured model before you upload them. Disclaimer: Third-party repos we don't own or vouch for. AI-generated use cases can be wrong: review everything and run at your own risk. Full text: https://dedupedai.com/disclaimer/ URL: https://dedupedai.com/use-cases/kitionai-kition/turn-receipt-photos-into-searchable-records/ ## How to generate 16:9 and 9:16 thumbnail batches from a table with Kition Repo: [KitionAI/kition](https://github.com/KitionAI/kition) | Difficulty: Beginner | Time: 45 minutes | Basis: From the README Fill a table of campaign messages and let AI fields create linked thumbnail variants for each record. **Who it is for:** A marketing or content lead who needs many thumbnail variants for a campaign and wants a review sheet for the batch. **The problem:** Producing and tracking thumbnail variants across channels in chat tools scatters files and loses which message each one came from. **The outcome:** A table where each record holds its key message, content type, and linked 16:9 and 9:16 thumbnails for review. ### Steps 1. Install the Kition desktop build from GitHub Releases. 2. Create a table with typed fields for the key message, content type, and intended emotion. 3. Add a face photo attachment and AI fields for 16:9 and 9:16 thumbnail variants. 4. Enter one record per campaign message and let the AI fields generate the variants. 5. Review the generated thumbnails in the table and regenerate any record that misses the brief. ### Prompt to paste into your agent ```text In the Kition desktop app, open the table
with campaign messages and AI thumbnail fields. Ask the Agent to list each record whose 16:9 or 9:16 variant is missing, and confirm the list before regenerating anything. ``` ### Caveat The README names 16:9 and 9:16 variants as an example scenario, so check the actual generated outputs against your brief before publishing. Risk, credentials: Face photos are personal images, so confirm you have permission to use each one and check where your configured AI service stores them. Disclaimer: Third-party repos we don't own or vouch for. AI-generated use cases can be wrong: review everything and run at your own risk. Full text: https://dedupedai.com/disclaimer/ URL: https://dedupedai.com/use-cases/kitionai-kition/generate-campaign-thumbnails-in-a-table-batch/ ## How to route inbox messages into a table with a workflow with Kition Repo: [KitionAI/kition](https://github.com/KitionAI/kition) | Difficulty: Intermediate | Time: 60 minutes | Basis: From the README Connect email and use a visual workflow to add incoming messages to a table as records. **Who it is for:** An operations or support person who triages a shared inbox and wants new messages logged in a table without manual copying. **The problem:** Reading mail and copying details into a tracker by hand is repetitive and easy to miss. **The outcome:** A table that receives inbox messages as new records through a workflow you can test and inspect. ### Steps 1. Install the Kition desktop build from GitHub Releases. 2. Follow the Email Connections guide in the docs folder to connect your mailbox. 3. Create a table to receive the messages and a workflow that uses an inbox trigger and a table action. 4. Test each workflow step individually and resolve any missing inputs before enabling it. 5. Check the run history to confirm records were created as expected. ### Prompt to paste into your agent ```text In the Kition desktop app, open the workflow that moves inbox messages into the table
. Ask the Agent to report the run history for the last run and list any step with missing inputs, and confirm the records match the messages. ``` ### Caveat The README says the Email Connections details live in a separate doc, so check that guide for supported providers before you start. Risk, credentials: Connecting an email account gives Kition access to mail, so use a dedicated account where possible and review the connection settings. Disclaimer: Third-party repos we don't own or vouch for. AI-generated use cases can be wrong: review everything and run at your own risk. Full text: https://dedupedai.com/disclaimer/ URL: https://dedupedai.com/use-cases/kitionai-kition/sync-inbox-messages-into-a-workflow-table/ ## How to run the Kition web client from source for UI work with Kition Repo: [KitionAI/kition](https://github.com/KitionAI/kition) | Difficulty: Intermediate | Time: 60 minutes | Basis: From the README Clone the public client and start the fast web preview for renderer and component changes. **Who it is for:** A developer contributing to the public React client who needs a quick local preview without the private runtime. **The problem:** Setting up the full desktop build for small interface changes is slow. **The outcome:** A local web preview of the Kition client running from your checkout, ready for renderer, component, editor, or style changes. ### Steps 1. Install Node.js 22.19.0 and pnpm 10.33.0 at the versions the README requires. 2. Clone the KitionAI/kition repository and enter the project folder. 3. Run `pnpm install --frozen-lockfile` in the project folder. 4. Run `pnpm dev:web` to start the web preview without the private runtime. 5. Read CONTRIBUTING.md before opening a pull request, and keep changes inside the public client and runtime contract boundary. ### Prompt to paste into your agent ```text In the kition repository at , run `pnpm install --frozen-lockfile` and then `pnpm dev:web`. Report whether the web preview starts and the local URL it prints, and confirm no runtime source is needed. ``` ### Caveat The README says the Kition runtime source is not in this repository, so the web preview covers client-side work only and not runtime integration. Disclaimer: Third-party repos we don't own or vouch for. AI-generated use cases can be wrong: review everything and run at your own risk. Full text: https://dedupedai.com/disclaimer/ URL: https://dedupedai.com/use-cases/kitionai-kition/run-kition-client-from-source-for-ui-work/