AI app for writers · no coding needed
Source-based writing and editorial delivery workspace
Reduce tool switching while keeping sources, drafts and approvals in one owned workspace.
Made for: Writers, editors and content teams producing source-based articles, briefs and creative material
What it does for you
The problem
Writing work is split across several AI subscriptions, so sources, prompts, drafts and approvals live in different tools.
What it gives you
Editor-approved drafts with source references
What you give it
Permitted documentsweb pagesvideo transcriptsbriefs
Build your own version of DeftGPT, Magai and more
One app with what these 3 AI tools do, yours to keep and change: DeftGPT, Magai, Capitol.ai.
Everything these tools do, in one app
- AI content generation Produces written content or creative material based on user input and context.Found in DeftGPT, Magai, Capitol.ai
- Chat interface Lets users interact with the AI through conversation.Found in Magai
- Multi-language support Allows users to interact with the AI in their preferred language.Found in DeftGPT
- Multiple AI models Provides access to various generative AI models for different content tasks.Found in Magai
- Save and reuse prompts Lets users save frequently used prompts and reuse them.Found in Magai
- Custom AI personas Allows creation of tailored AI personas for specific tasks or brand voices.Found in Magai
- Document upload and analysis Lets users upload documents for AI-driven analysis, insight extraction, and summarization.Found in DeftGPT, Magai
- Web page reading Reads and analyzes a web page by pasting its URL.Found in Magai
- YouTube transcript retrieval Automatically retrieves YouTube video transcripts.Found in Magai
- AI art generation Generates art using multiple sources such as DALL-E and Stability.ai.Found in DeftGPT
- Music composition Assists with creating music.Found in Capitol.ai
- Creative collaboration Acts as a digital muse to spark new ideas and refine or expand creative concepts.Found in Capitol.ai
- Rich media layouts Produces layouts that include charts, images, and data visualizations.Found in Capitol.ai
- Chat organization Uses chat folders, search, and filtering to organize work.Found in Magai
- Chat history retention Retains chat history even during interruptions.Found in Magai
- Private chat Offers secure chat.Found in DeftGPT
- API and SDK integration Provides advanced API and SDK solutions for integration into existing workflows.Found in Capitol.ai
How it works, step by step
- Generate written content from a brief and context
- Chat with the assistant in a conversation view
- Work in the writer's preferred language
- Route tasks across multiple AI models
- Save and reuse prompts
- Define custom AI personas for brand voice
- Upload documents for analysis and summarization
- Read and analyze a web page from its URL
- Retrieve YouTube video transcripts
- Generate art from multiple image sources
- Assist with music composition
- Act as a digital muse to expand concepts
- Produce layouts with charts, images and data visualizations
- Organize chats with folders, search and filters
- Retain chat history through interruptions
- Keep private chats secure
- Expose an API and SDK for existing workflows
- Compare the reviewed result with the recorded baseline and value assumptions
- Capture corrections and named-owner approval before consequential use
- Export a versioned editor-approved draft with source references and unresolved questions
Build it yourself with your AI system
Build this app yourself, no coding needed
Start with a quick version you can try in a few minutes. Like it? Then build the full app by copying and pasting our step-by-step instructions: everything is prepared for you.
Sign in to see how to build it yourself
Build a quick version to try, or get the full app pack for Source-based writing and editorial delivery workspace with the step-by-step building instructions. You don't need any technical skills: you copy, paste and answer a few questions. Both are included in the membership.
4 Have it built for you days to a few weeks
Rather not do it yourself, or want it fully tailored to your data, your way of working and your brand? Nexibeo builds Source-based writing and editorial delivery workspace with you.
What's in the app pack
Included in the Complete AI Training membership.
- The building instructions your AI follows, step by step
- The questions your AI will ask you about your business before it starts
- A clickable demo you can open in your browser, to see how it should work
- A detailed blueprint of the screens, the information it keeps and the checks it runs
Become a member to get the app packAlready a member? Sign in
The files, for the technically curious
- START-HERE.mdHow to build it with your own AI (read first)3 KB
- README.mdOverview and links3 KB
- questions.mdQuestions to answer before you build2 KB
- prompt-cloudflare.mdThe full build prompt, hosted on Cloudflare26 KB
- prompt-vps.mdThe same build on your own server (Docker)26 KB
- spec.jsonData model, API, AI pipeline, acceptance criteria12 KB
- demo/index.htmlThe working demo on sample data200 KB
Questions
Do I need to know how to code?
No. You copy and paste the prompts on this page into ChatGPT or Claude, and the AI does the building. When it asks you something, you answer in your own words.
What does it cost?
The quick version, the app pack and the step-by-step instructions are for members: you pay the membership price, not a price per app (see the plans). Building the full app uses your own ChatGPT or Claude subscription. Putting it online is often cheap or no cost at the start, and your AI tells you before anything costs money.
How long does it take?
The quick version: about two minutes. The real app: an afternoon for a first version you can use, longer if you want every feature.
Can I change it to fit my business?
Yes. Tell your AI what to change in plain words, like “add a column for the price” or “use our logo and colours”. Or have Nexibeo build and customise it for you.
More detailsHow the AI works, safeguards and what to build first
Reduce tool switching while keeping sources, drafts and approvals in one owned workspace. For writers, editors and content teams producing source-based articles, briefs and creative material, convert permitted documents, web pages, video transcripts and briefs into editor-approved drafts with source references. The benefit is a testable hypothesis, measured through accepted drafts per editorial hour and corrections after editorial approval; do not assume that AI output alone produces business value.
Confirm the buyer's problem and scope, collect permitted documents, web pages, video transcripts and briefs, then follow this sequence: 1. Generate written content from a brief and context. 2. Chat with the assistant in a conversation view. 3. Work in the writer's preferred language. 4. Route tasks across multiple AI models. 5. Save and reuse prompts. 6. Define custom AI personas for brand voice. 7. Upload documents for analysis and summarization. 8. Read and analyze a web page from its URL. 9. Retrieve YouTube video transcripts. 10. Generate art from multiple image sources. 11. Assist with music composition. 12. Act as a digital muse to expand concepts. 13. Produce layouts with charts, images and data visualizations. 14. Organize chats with folders, search and filters. 15. Retain chat history through interruptions. 16. Keep private chats secure. 17. Expose an API and SDK for existing workflows. Resolve uncertain cases with qualified reviewers, approve editor-approved drafts with source references, and measure accepted drafts per editorial hour and corrections after editorial approval against a documented baseline.
How the AI works
Use AI to interpret permitted inputs, suggest structured mappings and generate candidate outputs for the stated task modules. Use deterministic code for arithmetic, schema validation, hard constraints and reproducible tests. Review source-linked explanations and uncertainty before accepting results. One approved source set and brand voice guide; final fact, rights and editorial checks remain human. A model suggestion is never a verified fact, professional decision or authorization to act.
Safeguards
Preserve author voice, source attribution, quotation accuracy and usage permissions. Authors approve substantive changes and publication scope. One approved source set and brand voice guide; final fact, rights and editorial checks remain human. Keep all consequential actions under authorized human control and do not fabricate missing inputs, permissions, professional judgments or market evidence.
What to build first
Pilot scope: One approved source set and brand voice guide; final fact, rights and editorial checks remain human. Implement one approved input format, a bounded representative case set and the first two task modules: generate written content from a brief and context; chat with the assistant in a conversation view. Support the remaining modules with operator review: work in the writer's preferred language; route tasks across multiple AI models; save and reuse prompts; define custom AI personas for brand voice; upload documents for analysis and summarization; read and analyze a web page from its URL; retrieve YouTube video transcripts; generate art from multiple image sources; assist with music composition; act as a digital muse to expand concepts; produce layouts with charts, images and data visualizations; organize chats with folders, search and filters; retain chat history through interruptions; keep private chats secure; expose an API and SDK for existing workflows. Include source references, corrections, basic organization access, approval states, export and value measurement. Use managed operator assistance for unresolved exceptions. The cost estimate covers this narrow prototype, not unrestricted multi-tenant scale, complex production integrations, specialist certification or physical operations.
What it can connect to
Author-owned documents, permitted web pages and authorized video transcripts. Cloud file storage, design-file import/export and publishing destinations. Start with file exchange and validate destination specifications before promising direct publishing. Start with authorized file exchange. Validate current provider access, usage rights and schema behavior before promising a connector.
The screens in detail
Primary screens: Source intake and brief, Editable draft workspace, Editorial review and delivery. Use a thumbnail gallery for projects, a large central editing canvas, and a right-hand panel for sources, prompts, personas and comments. Let users compare versions side by side. Display draft, changes requested and approved states. Provide a client preview link with comments anchored to the relevant passage. Make the task-specific outcome editor-approved drafts with source references visible beside its evidence, review state and value baseline.
