For this release, we wanted to give you a small Christmas gift 🎄
We are introducing image generation, expanding Magnity’s ability to use external knowledge via web search, and improving how you collaborate, organize, and work with content. The team has worked very hard to get this update out before Christmas and we all hope you enjoy it.

🔎 Web search in Magnity chat
Magnity chat can now search the web.

If you ask Magnity something it cannot answer based on the sources you have provided, or if you explicitly ask it to look something up, it will automatically search the web and include external information in its response.

This currently happens automatically when needed or when you explicitly ask for it. We are considering adding this as a toggle you can turn on and off.

Why this is useful
Web search significantly expands the context you can work with in Magnity. For example, you can now:
• Put your email or landing page into the context of the latest news or developments
• Ask the Content Agent to compare your solution pages to competitors and create a gap analysis
• Find external videos or articles to include in your communication

The possibilities are extensive. Personally, we find the gap analysis use cases particularly exciting.

🖼 Image generation in Magnity
Magnity can now generate images.

You can generate images:
• Directly in chat
• Inside the image cropper

This means you can take an existing image in Magnity and ask Magnity to adjust it, or generate a completely new image either from scratch or based on a reference image from your library.

As part of this, we have redesigned the image cropper.

🎨 Redesigned image cropper
The image cropper has been rebuilt to support AI-powered image workflows.

You can now:
• Enter an exact aspect ratio manually
• Choose between three image actions:
– Upload a new image
– Generate a new image
– Edit image with AI

Why this matters
This makes it much easier to do subtle image adjustments, for example to better fit a local market or specific campaign context.

Note
At the moment, image generation uses the existing ChatGPT image API. The new image chat API is expected shortly and will replace this as soon as it becomes available.

🔔 Notifications when sharing projects
When someone shares a project with you, you will now receive an email notification with a direct link to the project.

Even if you are not logged in, you can click the link, log in, and be taken directly to the shared project.
This is the first step toward a more structured and user-friendly content review environment.

📬 Onboarding newsletter launched
We have launched an onboarding newsletter flow built entirely with Magnity.

The newsletter will mix:
• Training sessions
• FAQ and knowledge base articles
• Tips and tricks for getting the most out of Magnity

We hope you find it both useful and inspiring.

🏷 Custom tags
You can now create custom tags when:
• Adding content manually
• Editing existing tiles

This makes it easier to categorize and find content when working in Magnity, especially in larger libraries.

🛠 Adjustments and refinements

Source type changes removed
We have removed the ability to change the source type of a tile. This caused issues when switching between document types and webpages or videos, since documents are stored page by page.

We may reintroduce this later if there is strong demand.

Rich text editor improvements
We have made several improvements to how the rich text editor behaves when switching between the canvas and the editor in the Content Agent. This should make editing more stable and predictable.

🎯 Why This Matters
These updates are all part of enabling a much more contextual and intelligent use of Magnity.

With web search, image generation, improved collaboration, and better content organization, Magnity is now better equipped to:
• Analyze your content in a broader context
• Compare it to external information
• Help you build more engaging content and more elaborate plans

Especially in the Content Agent, these changes open up entirely new ways of working.

We hope you enjoy these new features and wish you a great holiday season 🎄

Questions or feedback?
Our support team is here to help:
✉️ ulsa@magnity.ai | 📞 +45 29 35 25 78

Thank you for using Magnity.
— The Magnity Development Team

5th January – 2026 release notes: New Quick Prompt Library and Advanced Crawling

Ulrik Sandholt
Shared by Ulrik • just now

This release focuses on improving how you interact with content and prompts in Magnity. It is the first step in a broader redesign that reflects the fact that Magnity can now search the internet and perform far more advanced content analysis, planning, and creation.

📚 New Quick Prompt Library design
We have released a redesigned Quick Prompt Library.

The new design introduces:
• A top-level category selector
• A search field to filter quick prompts
• Quick prompts displayed as cards
• Clear actions to use a prompt or see details

When viewing details, you can now see the full prompt itself, making it easier to understand exactly what it does and how it works.

This redesign makes quick prompts far more accessible, especially longer or more advanced prompts. The previous design struggled with discoverability and clarity once the library grew beyond a small set.

🧠 What’s coming next for Quick Prompts
This release is step one.

Next steps already planned include:
• Adding your own custom quick prompts
• Editing existing quick prompts
• Adding descriptions explaining what a prompt does
• Showing example outputs for more complex prompts

These features are not released yet, but the new design is built to support them.

🌍 Advanced crawling for localized pages
Magnity’s crawler has been upgraded to better handle localized page variants that do not share similar URLs.

Many global websites use HTML metadata to indicate that multiple pages are language or regional variants of the same core content. This is typically done using hreflang annotations, which tell search engines that different URLs represent localized versions of the same page.

Magnity can now detect and interpret these localization signals and correctly identify such pages as related variants, even when the URLs themselves look completely different.

This improves:
• Content deduplication
• Localization handling
• Accuracy when crawling large international sites

🛠 Minor fixes
No minor bug fixes were applied in this release.

🔮 Long-term development
We are actively preparing the backend to support flow building.

This requires changes to our data model and experimentation with new internal tools, made possible by our recent upgrade to the Responses API. This API allows Magnity to use structured tools as part of its reasoning process, which is a key requirement for building automation flows.

🎯 Why This Matters
To build a solid Flow Builder, we first need a solid Flow Plan Builder.
And to build that, we need a strong and flexible Quick Prompt interface.

This release lays the foundation for that journey. Combined with advanced crawling and richer content understanding, it moves Magnity closer to being a system that does not just write content, but helps plan, reason, and orchestrate it.

We hope you enjoy the update.

Questions or feedback?
Our support team is here to help:
✉️ ulsa@magnity.ai | 📞 +45 29 35 25 78

Thank you for using Magnity.
— The Magnity Development Team

This release introduces better control while working with Magnity, new ways to manage tiles, improved PDF exports, and an early alpha step toward retrieval-based intelligence.

⏹ Stop generating
You can now stop Magnity while it is generating a response.

A new Stop generating button lets you interrupt the output at any time. This is especially useful in the Content Agent when working with long texts and realizing mid-generation that the prompt or direction needs adjustment. You no longer have to wait for the full response to complete.

🧩 Edit and delete tiles
All tiles now include a small edit icon in the top-right corner. This means you can edit any tile you added or that has been added automatically. You can also delete unwanted tiles.
​

Clicking it allows you to:
• Change the image
• Change tags
• Add new tags (this will be rolled out to all add-content features soon)
• Change tile type
• Change the URL
• Edit the text content
​

After editing, the tile can be saved directly.

When deleting a tile, you can now also choose to delete all language versions of that tile at once.

We are currently looking into supporting image editing across all language versions as well.

🧠 RAG alpha (backend configuration)
We have added a RAG configuration for all customers in the back end. It allows us to add a simple Pinecone based RAG to a customer.
​
​What is a RAG?

A RAG can be thought of as a database with ChatGPT 5.2 on top. While ChatGPT understands a lot about language and brands in general, it does not know your full content library by heart. With a RAG, the model can reason over everything you have added to Magnity and answer questions based on your actual content.

This is an alpha feature, and we are not onboarding customers to it yet.

Why?
Our current RAG setup is intentionally simple. A high-quality RAG requires slicing, enrichment, metadata strategy, and tuning. Without that, we cannot guarantee precision. Making it truly valuable requires custom configuration per customer.

That said, this is a very important step toward our long-term ambition of building an autonomous marketing agent and a flow builder.

Imagine being able to ask Magnity to:
• Build an onboarding or engagement flow for a specific persona using real URLs
• Identify the most relevant content to reuse for marketing in 2026
• Find where a specific specification or claim appears across your content
• Locate all content related to a given topic
• Apply large compliance rule sets and automatically detect which rules apply to which content

The list goes on.
​

If you are curious, we are happy to show a demo of the RAG in action and discuss what it could become for you.

📄 Improved PDF file naming
When downloading emails or Content Agent projects as PDFs, filenames are no longer generic.

Files are now saved using:
• Project name
• Language (if applicable)
• Persona (if applicable)

This makes it much easier to keep track of multiple exported PDFs.

🛠 Minor bug fixes and improvements
• Fixed an issue where bullets added in the persona rich text editor could become invisible when using the persona in emails
• Improved scrolling behavior across the interface for better stability and usability
• On smaller screens, the content library now collapses automatically when opening the chat
• Fixed a bug where adding a PDF to an existing email chat could fail after selecting pages

🔍 Known bugs

Attachments when translating
When translating content, attachments from the original version are currently not transferred to the translated version. This can be inconvenient if you were referencing plans or sources from the original content. Attachments can be re-added manually. We are working on a fix.

No editing of PDF text
When editing a tile that is a PDF, no text is shown. PDF text is stored page by page, which we did not initially account for in tile editing.
If you edit and save a PDF tile right now, the text will be saved as empty. Please do not edit PDF tiles until this is fixed.

Changing a tile to a PDF
If you change a tile from a webpage or video to a PDF, the tile may fail to load. If this happens, simply change it back to a webpage or video. We are investigating the issue.

🔮 Upcoming features planned
• Early work on a Flow Builder. This is a major feature and will take time. Please be patient
• Ability to change the LLM used specifically for the Content Agent
• Support for changing background colors in templates
• Exploration of a module-based template builder for emails and landing pages, instead of fixed templates

If any of these are particularly important to you, feel free to reach out and let us know.
​
​Questions or feedback?
Our support team is here to help:
✉️ ulsa@magnity.ai

| 📞 +45 29 35 25 78

Today's release brings several major upgrades to the way you work with Magnity across all builders. Streaming chat has now been rolled out everywhere, the rich text editor has new color options, and the SoMe builder now includes a brand-new carousel template.

💬 Streaming Chat in All Builders
Magnity’s streaming chat experience is now live in:
• Content Agent
• Email Builder
• Landing Page Builder
• SoMe Post Builder

This means Magnity now writes responses in real time, allowing you to read content as it is produced rather than waiting for the final output.

You can also now see when Magnity is thinking, even though you cannot see what it is thinking.
This makes long responses, complex reasoning, and larger tasks far easier to follow and work with.

​🧱 Long-form HTML Structured Output
When generating long responses — such as flow plans, rewrites, or multi-section content — Magnity now returns clean, structured HTML formatted output by default.

This includes:
• Headings
• Bullets and numbered lists
• Highlights and bold text
• Clear sections and sub-sections

This provides a much better overview and reduces the need for manual formatting after generation.

🎨 Rich Text Editor: Text Colour and Background Colour
The rich text editor now supports:
• Text colour
• Text background colour

This gives you more control when formatting content, especially for social media posts, visual templates, or branded elements.
These additions also enable the new SoMe carousel template.

🖼️ New SoMe Carousel Template
The SoMe builder now includes a carousel template.
You can build multi-slide social posts directly in Magnity and use the new text colour and background colour features to highlight key elements per slide.

This opens up new creative possibilities for campaign storytelling, product sequences, step-by-step explainers, and multi-part announcements.

⏱ Chat Timeout Increased
The chat timeout has been increased from 1 minute to 10 minutes, giving Magnity more room to complete long or reasoning-heavy tasks without interruption.

🧹 Automatic Cache Refresh
Magnity now performs a full cache refresh automatically after each deployment.
This means you always load the newest version without manually refreshing or using CTRL + SHIFT + R.

🔗 Content Agent Source Handling Improved
When adding multiple sources to the Content Agent, URLs and text are now always added correctly.
All known issues in this area have been resolved.

You can still drag in tiles, reapply sources, and use the top attachment bar for complete source control.

🎯 Why This Matters
This release dramatically improves the speed, clarity, and flexibility of the Magnity experience.
Streaming chat across all builders, combined with structured HTML output and enhanced formatting tools, makes it easier than ever to work with long content, build complex assets, and create visual social posts.

The new carousel template and richer text formatting options also move Magnity closer to supporting fully branded content experiences, while the improved chat workflow lays more groundwork for the upcoming Journey Agent.

Questions or Feedback?
Our support team is here to help:
✉️ ulsa@magnity.ai 📞 +45 29 35 25 78
Thank you for using Magnity!
— The Magnity Development Team

Today’s release introduces several key upgrades to how you interact with Magnity. These improvements roll out first to the Content Agent, since it handles the longest and most complex outputs, but will soon extend to the email, landing page, and SoMe builders as well.

💬 Streaming Chat
Magnity’s chat is now fully streaming, meaning you’ll see Magnity write in real time as it generates content — instead of staring at the green circle of death in the lower left corner.

You can also now see when Magnity is thinking.
You cannot see what it is thinking, but you can see that Magnity is actively processing your request before the writing begins.

This makes long responses much easier to follow, since you can read as the content is being produced rather than waiting for the full response to load.

Streaming chat is live in the Content Agent today and will roll out to the email, landing page, and SoMe builders during the weekend (pending final tests).

🧱 Long-form HTML Formatted Responses
When you ask Magnity to generate very long responses — such as rewriting 30 pages of text or building a detailed engagement flow plan — it will now return the output as structured HTML-formatted text.

This includes:

• Headings and subheadings
• Bullets and numbered lists
• Bold text for clarity
• Clean sectioning for readability

This gives you a far clearer overview and drastically reduces the need for manual formatting afterward.

🐞 Known Bug: HTML Formatting and Editing
We’ve identified a bug affecting this new HTML formatting. If you add formatted text from the chat to the canvas and then edit it, the formatting may disappear when it is reinserted into the chat or rich text editor.

We expect to release a fix within the next 48 hours. Thank you for your patience.

🔗 URLs in Content Agent
We fixed an issue where adding multiple sources sometimes added the text but not the URLs to the chat. When you add any number of tiles to the canvas or chat it now also accurately remember each and every URL.

⏱ Chat Length and Timeout Increased
We’ve increased the chat timeout from 1 minute to 10 minutes.

This significantly reduces the chance of timeouts when generating long or complex responses, especially when using a reasoning model.

🧹 Cache Busting
Magnity now automatically clears outdated cache after new deployments.
You should no longer need to manually refresh or use CTRL + SHIFT + R to load the newest version.

🎯 Why This Matters
This update improves transparency, performance, and reliability across long-form work.
You can now:

• See Magnity think and write in real time
• Receive cleaner, structured HTML for long outputs
• Avoid premature timeouts on heavy tasks
• Rely on automatic cache updates

These improvements make the entire content creation and reasoning experience smoother and more predictable — especially when working with large or complex projects.

Questions or Feedback?
Our support team is here to help:
✉️ ulsa@magnity.ai

| 📞 +45 29 35 25 78

Thank you for using Magnity!
— The Magnity Development Team

This release expands the Content Agent chat functionality (contextual chat) to the email, landing page, and SoMe post builders.
​
You can now drag and drop tiles directly into the chat of any element — giving you full context for what you’re writing and allowing Magnity to understand the intent and background of your content.

💬 Chat Functionality in All Builders
The same intuitive chat experience from the Content Agent is now available across all builders.
When editing an email, landing page, or SoMe post, you can:

• Drag and drop any number of tiles into the chat to create instant context.
• Reapply sources from the top attachment bar or from individual chat bubbles.
• Select specific tiles or reapply all at once to quickly bring context back into the conversation.

This makes it easy to continue work, refine outputs, and reuse existing content without searching for tiles again.

📚 Why It Matters
Adding context directly in the builder unlocks a new level of precision and speed.
Since you can build tiles in the Content Agent, you can now use virtually any type of tile as context when writing:

• Engagement Flow Plans
• Industry Descriptions
• News Articles
• Related Pages
• White Papers
• Videos for Webinar Landing Pages

You can even reapply a specific source to refocus Magnity’s attention.
For example, if you’ve added a Flow Plan and want to discuss how one page has been implemented, you no longer need to locate the tile again — simply reapply it from the list of previously used tiles.

This gives users the flexibility to test, adjust, and iterate content with precision — all within the builder environment.

🖼️ Image Hosting Options: Now Available for Pardot (Salesforce Marketing Cloud Account Engagement)
Following last month’s update, where you could choose to host images either on Magnity’s Bytescale CDN or send them directly to Marketo, the same functionality is now also available for Pardot (Salesforce Marketing Cloud Account Engagement).

This gives you the same flexibility when working with Pardot campaigns ensuring consistent link tracking and full compatibility when sending emails to recipients in organizations with strict email security configurations.
By aligning image hosting with your platform domain, this feature helps maintain consistent link tracking and minimizes link adaptations caused by differing domains.

🧩 Minor Improvements
Fixed a few minor issues:

• The Send button in the Export SoMe Posts modal was misaligned.
• No other known interface issues at this time.

🔍 Known Issues
When requesting very large output texts (for example, long rewrites or translations), the interface may become unresponsive if the chat reaches its output token limit.
We’re working on a fix that will allow large outputs to be handled in multiple stitched responses.
Until then, try splitting large tasks into smaller chunks if you experience a timeout.

🎯 Why This Matters
This release is a step toward making Magnity fully context-aware across all content types.
By extending the Content Agent’s chat capabilities to every builder, you can now create smarter, faster, and more connected content experiences — powered by the same reasoning layer used in the Content Agent.

It also marks an important milestone toward the Journey Agent, a system that will automatically build complete automation flows from your existing content, combining reasoning, sequencing, and personalization.
We’re excited to move closer to that goal with this release.

Questions or Feedback?
Our support team is here to help:
✉️ ulsa@magnity.ai | 📞 +45 29 35 25 78

Thank you for using Magnity!
— The Magnity Development Team

This release focuses on three major improvements to make Magnity even smoother to work with:

You can now reuse sources directly from the chat history in the Content Agent.

You can save emails as PDFs with full control over what variants to include.

And you can now choose where images are hosted, improving link tracking consistency for corporate recipients.

💬 Content Agent: Reuse Sources from Chat History
You can now easily reapply any source previously used in your Content Agent project.

At the top of the chat, you’ll now find a full overview of all sources used in your project’s history, organized by type (webpage, video, or document). You can expand each list and reapply sources one by one or reapply all at once.

This makes it much easier to refine complex projects built from many different sources. For instance, if you’re reviewing a flow proposal from Magnity and want to adjust it, you can now reapply the sources directly and ask:

​“I don’t think this should be left out.”
or
​“Are we sure this source is used correctly?”

This is the first step towards a unified chat experience across all of Magnity. The same functionality will soon extend to the email, landing page, and SoMe builders, with adjustments to match how those modules apply content.

📄 Emails: Save as PDF (Three Export Options)
You can now save emails as PDF documents, offering full flexibility for sharing and review.

There are three export options available:
a) Save all variants in one combined PDF
b) Save each variant as an individual PDF
c) Save each variant together with its default version in one PDF

This makes it easier to compare localized content, share campaigns with stakeholders, or archive versions for documentation.

You’ll find the new “Save as PDF” button in the top menu, right next to the Duplicate Project button.

🖼️ Image Hosting Options: Magnity CDN or in your Automation Platform
Magnity now allows you to choose where your images are hosted either on Magnity’s Bytescale CDN or directly in your automation platform upon export.

This added flexibility ensures optimal compatibility when sending emails to recipients in large organizations with strict email security configurations. By aligning image hosting with your platform domain, this feature helps maintain consistent link tracking across recipients’ environments.
​
Contact your admin or us directly (f you are an admin for turning this on.

🧩 Minor Improvements

• Expanded CTA name and URL fields, so full URLs and tracking parameters are always visible and editable.
• Minor UI and performance refinements across builders for a smoother experience.

🔍 Known Issues
When requesting very large output texts from the Content Agent, you may experience the interface becoming unresponsive. This typically happens when rewriting or translating large volumes of content (for example, 30+ pages at once).

The issue occurs because the chat currently reaches its output token limit, causing the interface to time out.
We’re actively working on a fix that will allow the chat to stream large outputs in multiple stitched responses, ensuring stability even for extensive requests.

In the meantime, we recommend splitting large tasks into smaller chunks if you encounter an unresponsive interface when generating long outputs.

🎯 Why This Matters
These updates make Magnity more powerful, reliable, and enterprise-ready. You can now reuse sources more intuitively, export complete project PDFs, and ensure consistent link tracking for corporate recipients with enhanced email security setups.

Questions or Feedback?
Our support team is here to help:
✉️ ulsa@magnity.ai 📞 +45 29 35 25 78
Thank you for using Magnity!
— The Magnity Development Team

🧱 Content Agent: Custom Tiles
You can now combine multiple content sources into a single tile using the new Custom Tiles feature in Content Agent.

When you drag content into the Content Agent canvas, you’ll now see a small “Create Custom Tile” button in the top-left corner. Clicking it opens a modal window where you can mix and match the tiles you’ve added to the canvas.

Inside the modal, you can:

• Select which URL should act as the main link for the tile
• Choose or change the main image
• Add a custom URL if none of the existing ones fit
• Define whether it’s a webpage, video, or document tile (each follows its own rules when used elsewhere)

This means you can build rich, context-specific tiles, for example:

• Combine a video and its webpage into a single interactive tile
• Bundle campaign briefs and supporting materials into one shareable unit
• Merge translated documents with their original sources for reuse across languages

Every custom tile is automatically tagged “Custom Tile”, making them easy to find and manage in your library.

🔜 Coming Soon:
You’ll soon be able to drag custom tiles directly into the chat inside the email, SoMe, or landing page builders — allowing you to use a tile as context, for instance:
“This email should be the first in this engagement flow plan.” → drag tile into chat.

🛠 Bug Fixes & Improvements

• Minor UI adjustments for better visual alignment in the Content Agent canvas

🔍 Known Issues
When dragging a mizxed tile into the Content Agent Canvas, it will add the URL and source name again, so itr might appear it says source 1 twice. It has no impact on performance.

🎯 Why This Matters
Custom Tiles introduce a new way to organize, combine, and reuse content inside Magnity. It gives you creative flexibility to build campaign-ready assets directly in the Content Agent — bridging pages, videos, and documents into one unified element.

Questions or Feedback?
Our support team is here to help:
✉️ ulsa@magnity.ai | 📞 +45 29 35 25 78

Thank you for using Magnity!
— The Magnity Development Team

📄 PDFs now work properly with Content Agent

We had a few issues with adding PDFs to the Content Agent. This is now fixed. When adding multiple PDFs in one go, you will be asked about what pages you want to add for each PDF in a row.

💬 Chat updates

You can now use Shift + Enter in chat to change lines and if you enter more text the chat window will expand upwards to give you more space to work with. This should make it easier to enter in larger prompts, especially useful in the Content Agent.

🪶 Canvas visibility

In the Content Agent the canvas now has a vivible text field where you can just copy paste in any text you want to get going. This was there previously, but just not very visible.

🗂️ Content Agent: Duplicate Project

In the Content Agent you can now duplicate the project, so you can create new versions of the same project. This is especially helpful if you want to share an idea with someone but dont want them to edit your version.

Find the duplicate button in the black top bar, just as with e-mails, SoMe posts and landing pages.

🛠 Bug Fixes & Improvements

• Fixed an issue where the filters in Content Agent did not affect the content in the content library.
• Fixed an issue that caused the content library to not render all tiles for some markets.
• Cleaned up some minor UI issues.

🔍 Known Issues

• Right now all responses are in plain text. We have discovered a bug in our Chat API that cause long HTML strings to deform, and are replacing the API method within the nexct week as well, so you can get well formatted responses.

🎯 Why This Matters

The minor fixes are supposed to make the content agent easier to use as well as the email, SoMe and landing pages builder. It is also a preparation for the ability to add context to emails, landing pages and SoMe posts. We would like to offer you the opportunity to use the output PDF in the content agent to build content in the other builders. For instance flow plans.

This also works well with out plan to soon introduce mixed tiles, where you can mix tiles of various nature to use in any builder.

Questions or Feedback?

Questions or Concerns?
Our support team is here to help:
✉️ ulsa@amagnity.ai | 📞 +45 29 35 25 78

Thank you for using Magnity!

— The Magnity Development Team

🧪 Meet the Content Agent

We’re excited to introduce a powerful new feature inside Magnity: the Content Agent.

The Content Agent gives you a flexible space to experiment, strategize, and create — using your own content as the foundation. Whether you're working with web pages, documents, or videos, you can now ask your Content Agent anything, test messaging ideas, build automation flows, campaign briefs or translate content on the fly. Basically anything you can think of asking your content about.

🧩 What You Can Do

Just drag and drop any number of webpages, PDFs, or videos into the Content Agent canvas or into the chat. The Content Agent will instantly parse and understand your content — and you’re ready to go. Either you can modify the content or mix the content by dragging it into the chat or you can chat with the content only, by dragging it into the chat. You can even drag any content element or group of elements into the chat at any time, to add context to your conversartion.

From there, you can:

• 🤖 Ask questions and get insights from your own material, like: "Can you build an FAQ of 20 questions based on these videos?"
• ✉️Crearte campaign briefs, plans and even analyze your current content and identify gaps in messaging.
• 📈 Build plans for onboarding, engagement, nurturing, ABM or any other type of flow you can image. You can get anything from flows with funnel phases, start/end states, relevant URLs, and email breakdowns. You think it, we build it.
• 🌐 Translate any asset into any supported language in seconds and export it as a PDF.
• 🔍 Test prompts, messaging angles, and strategies — instantly
• 💬Drag content into the chat after having chatted about a topic for a while to add context to your conversation.

Magnity currently supports dragging in content parsing up to 60.000 tokens via ChatGPT, but we can expand that if you need to. We want to start off leaving a little space for conversation since the upper limit is 128.000 tokens. That’s enough to work with hundreds of pages at once — and we’re just getting started.

If you are curious about how tokens are counted, test it out here: Tokenizer - OpenAI API

Here are some examples of simple tasks:

1. “Generate a one-pager PDF outline from this video transcript.”
2. “Turn these product pages into comparison charts and FAQs for a landing page.”
3. Write a LinkedIn carousel outline with 5 slides highlighting insights from these pages.”
4. “Map these 20 pages to decision-journey phases (Aware, Consider, Decide).”
5. “Cluster these docs into themes with recommended campaign angles.”
6. “Extract pain points and value drivers for "persona a" based on these sources.”

We are going to overflood the new Content Agent Quick Prompt library with options and help, so you can get inspired on how to apply AI to your content library.

And yes, we will add the new drag content into chat for the emails, landing pages and SoMe posts as well, but it will be in the coming 1-2 weeks.

🔧 Pro Tips

• The Content Agent has rules consisiting of Writing rules and Tone of Voice guidelines. You can use these to form your responses.
• You can manully copy paste any text into the canvas that you want to work with.
• You can now add a tile to the chat by clicking a small button in the lower right corner of it.
• You can mark all the visible tiles in the content library and drag them all into the canvas or chat in one go.
• When you add one or more tiles to the chat, you can view the source content by clicking the small blob above the chat box. Here you can also remove them all or one by one.

🛠 Bug Fixes & Improvements

• Fixed an issue where the subject line would default to the master language if it contained a '%' sign when exporting to Marketo.
• Fixed an issue that caused the headline and image text in a 4 element lwebpage module to ignore the tag in the prompt, thereby doing generic headlines
• Cleaned up some minor UI issues.

🔍 Known Issues

• PDF documents has a bug that prevents you from adding them with all text to the canvas. We are fixing this within one week. We could have waited on releasing the rest, but thought we wanted you to try it out while we did some small fixes.
• If you want to add a document to the content library, do it from the email composer and not the content agent. When you add it ffrom the content agent, it does not show up in the library. We are fixcing this asap.
• Right now all responses are in plain text. We have discovered a bug in our Chat API that cause long HTML strings to deform, and are replacing the API method within the nexct week as well, so you can get well formatted responses.

🎯 Why This Matters

The Content Agent is a key step in evolving Magnity into a fully autonomous AI co-pilot — not just for content generation, but for decision-making, strategy, and campaign orchestration. Whether you're testing ideas or building production-ready flows, the Playground gives you creative control with AI-powered speed. We are researching how to expand the content agent to understsnd your entire information library from the get go, so you dont have to drsg anything in, but can just have an open conversation. Stay tuned and reach out to us, if you are an admin and we can tell you more.

Questions or Feedback?

Questions or Concerns?
Our support team is here to help:
✉️ ulsa@amagnity.ai | 📞 +45 29 35 25 78

Thank you for using Magnity!

— The Magnity Development Team