Magnity News Center

Today, we are releasing one of the largest Magnity updates so far: a complete redesign of our frontend and all our content builders.

The new frontend has been rebuilt in React.js. This has significantly reduced the size and complexity of our codebase, making it easier for us to improve the platform and develop new functionality going forward.

The release also introduces a broad range of improvements and new capabilities across the interface, content library, canvas, text editing, and chat.

This is more than a visual redesign. It creates the technical and interaction foundation for the next generation of Magnity.

🧭 A new menu and navigation experience

The redesign introduces a new burger menu across the Magnity application.

Inside each agent, the burger menu appears as a compact icon-based navigation menu that you can expand or collapse depending on how much working space you need.

The menu uses our new Magnity iconography and creates a more consistent experience across the platform.

💾 Protection against unsaved changes

Buttons and menu items that take you away from the current interface will now warn you if you have unsaved changes.

This reduces the risk of accidentally leaving an agent and losing work that has not yet been saved.

The warning also applies when navigating through the new burger menu.

📚 A redesigned content library

The content library has received a substantial redesign to make it easier to browse, manage, and work with content.

↔️ Expand, collapse, and resize the library

You can now expand or collapse the content library by clicking the button in its top-left corner.

You can also manually resize the library by dragging its border left or right.

This allows you to decide exactly how much space the content library and canvas should occupy, depending on what you are working on.

🖼 Redesigned content tiles

Content tiles have been redesigned to display more information while remaining easier to scan.

The image and content information are now separated using a vertical split, giving both the image and the associated information more room.

Each tile also includes a three-dot menu where you can:

• Edit the content
• Delete the content

🏷 Easier tag management

The interface for editing content tiles has also been updated.

It is now substantially easier to add and remove tags, particularly when a tile contains several tags or needs to be reorganized.

The previous plus button has also been renamed:

+ Add content

This should make its purpose much clearer, particularly for new Magnity users.

Filters have also been adjusted to make them easier to identify and use.

🎨 A more flexible canvas

We have made several important changes to how you work inside the canvas.

👤 Redesigned persona selection

Personas are now left-aligned, creating room for more personas to be displayed across the canvas.

They are also shown as rounded squares, making it clearer that they represent selectable personas rather than ordinary buttons or content fields.

✍️ Rich text editing directly above the template

Rich text formatting has been moved from the chat and into a new formatting bar positioned directly above the template.

This allows you to format text where you are already working, making manual editing more natural and direct.

You can use the formatting bar to adjust the text inside the selected template field without moving between the canvas and chat.

In the Content Agent, rich text formatting is still located inside the chat. This will also be moved in an upcoming release.

🔍 Compare two variants side by side

We have introduced a new comparison view for reviewing content variants.

When you activate the comparison slider, Magnity opens a second view to the right of the original template.

The second view mirrors the existing template structure, allowing you to compare two variants directly.

You can use this to compare:

• An original version and a personalized variant
• Two different persona variants
• A source version and a localized version
• Different language versions

This should make reviewing localized and personalized content significantly easier, as differences can now be evaluated directly rather than by switching between versions.

💬 Minimize the chat while editing

The chat will still open automatically when you select an element in the canvas.

However, you can now minimize the chat by clicking the button in the top-left corner of the chat panel.

Once minimized, you can move between different fields in the template and edit them manually without the chat reopening every time you select a new field.

When you need the chat again, simply click the same button to reopen it.

This provides a cleaner manual editing workflow while keeping the chat immediately available when needed.

🤖 A completely redesigned chat

The chat interface has been redesigned to feel more familiar to users of tools such as ChatGPT and Claude.

Your messages now appear inside chat bubbles, while Magnity’s responses are displayed as clean text responses.

The previous large action buttons have been replaced with smaller icons below each message and response.

Current actions include:

• Add
• Copy
• Regenerate
• Delete

The new icon-based design gives us more space to introduce additional actions and tools over time.

➕ Add or append content to the canvas

In the Content Agent, you can now decide how a response should be added to the canvas.

Add to canvas
Replaces the existing content on the canvas with the generated response.

Append to canvas
Adds the generated response to the end of the existing canvas content.

We are also developing an Add at cursor option, which will allow you to insert generated content at a specific location inside the canvas.

⏹ Stop generating directly from the chat button

The stop-generating action is now built into the chat button.

While Magnity is generating a response, you can click the chat button to stop the generation.

This replaces the previous separate stop-generating control and keeps the main chat actions in one place.

📊 Generate charts from your content

You can now ask Magnity to turn information in the chat into a chart.

For example, you can ask Magnity to create:

• A bar chart
• A line chart
• A chart comparing different values
• A visual representation of performance data
• Other chart formats relevant to the information provided

Magnity will interpret the information and select or create an appropriate visual format.

Charts cannot yet be added directly to the canvas. We are adding this functionality in the next release.

📋 Create formatted tables (coming soon)

You can also ask Magnity to turn content or data into a formatted table.

Rather than returning a basic text table, Magnity can now present the information in a more structured and visually readable format.

This can be used for comparisons, performance overviews, content inventories, research findings, plans, and many other types of structured information.

Formatted tables cannot yet be transferred directly to the canvas. This will be added alongside chart support in an upcoming release.

🔗 Agents can now work with other agents

Magnity’s agents can now communicate with the Rules Agent and other agents.

This introduces the foundation for workflows where one agent can use the capabilities, context, or output of another agent.

For example, you can add 30 pages of content to the Content Agent and ask Magnity to update a market language ruleset with vocabulary identified across the material.

The Content Agent can analyze the content and work with the Rules Agent to produce the updated vocabulary.

This is an early version of a much broader cross-agent architecture. We will add more functionality around agent collaboration during the coming weeks and months.

🧰 External tools and data connections

We have also opened Magnity up for external tools and data sources.

Current connection options include:

• Google Search Console
• Google Analytics
• DataForSEO
• Other SEO tools where relevant

Once a connection has been configured, Magnity can use the connected data inside the Content Agent.

You can, for example, ask Magnity to:

• Show the performance of specific content
• Analyze traffic and search performance
• Conduct SEO analysis
• Conduct GEO analysis
• Identify content opportunities
• Combine content analysis with performance data
• Create charts and tables based on connected data

These capabilities are currently available through the Content Agent and will soon also become available in the Webpage Agent and moire.

Please contact your Magnity administrator if you are interested in enabling one or more of these connections. We can help you do that initally. Soon you admin will be able to do so themselves.

🌐 Start chatting without selecting a content tile

Previously, you needed to add a tile from the content library before starting a conversation with Magnity.

You can now open the chat and begin a conversation without first selecting or adding content.

You can use the open chat to ask Magnity questions about:

• Magnity functionality
• How to perform a task
• How different agents work
• The content already available in your project
• The tools and capabilities available to you

You cannot yet ask this chat to build a complete email, webpage, or social media post from scratch.

However, this is the next logical step in its development.

💬 Introducing the foundation for All Chat

The open chat will soon be referred to as All Chat.

Today, most Magnity chats relate to a specific element, such as a headline, body text, module, or template field.

All Chat is designed to become the place where you communicate with the complete asset or project.

Instead of only talking to an individual element, you will be able to talk to the entire webpage, email, flow, or collection of content.

This could allow you to ask Magnity to:

“Add two more modules about topic A.”

“Make all the articles in this email feel more connected.”

“Adjust the entire webpage for a specific persona.”

“Create a set of webpages and emails based on this brief.”

“Review the complete email and identify what is missing.”

“Use the Content Agent plan to build the required assets.”

All Chat will gradually become a central interaction layer across Magnity, allowing you to coordinate work across content, templates, agents, tools, and data sources.

⚠️ Current limitations

This is a major frontend release, but some parts of the new experience are still being completed.

Known limitations in this release:

• Charts cannot yet be added directly to the canvas
• Formatted tables cannot yet be added directly to the canvas
• Add at cursor is still under development
• The open chat cannot yet build complete assets from scratch
• Rich text formatting is still located in the chat inside the Content Agent
• Some older areas, including the Flow Blueprint and Control Panel, have not yet received the complete redesign
• The burger menu may look or behave slightly differently when moving between the new interfaces and older parts of Magnity

These areas will be updated during the coming releases.

🛠 The remaining interface is being redesigned

We know there are still smaller parts of Magnity that need a visual and interaction update, particularly the Flow Blueprint and areas inside the Control Panel.

We are actively redesigning these areas.

During the next few weeks, you may therefore notice that the burger menu looks slightly different when you move between the newly redesigned agents and the Control Panel, where parts of the previous interface are still implemented.

The platform should remain fully usable throughout this transition.

🎯 Why this matters

The new frontend is not only intended to make Magnity look better.

Moving the application to React.js has reduced the size and complexity of the frontend codebase and gives us a much stronger foundation for future development.

The new interaction model also brings the canvas, chat, agents, tools, and content library closer together.

This lays the groundwork for capabilities such as:

• More tools directly inside the chat
• Charts and tables that can be added to content
• All Chat across complete assets and projects
• Deeper collaboration between agents
• Content creation based on live performance data
• More advanced SEO and GEO workflows
• Complete emails and webpages built directly from a conversation
• Coordinated creation of multiple assets from a single brief

We hope the new interface feels smoother, clearer, and easier to use.

We are excited to complete the remaining areas and continue building on the new foundation.

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 a new Adoption area in the Control Panel, improves how findings are handled in the Compliance Agent, and adds more flexibility to compliance rules through asset type selection and verification-focused findings.

We are also still working on the broader front-end redesign and expect to be done with that within the coming two weeks.
​
📈 New “Adoption” menu in the Control Panel

There is now a new Adoption menu item in the Control Panel.

This is the first version of a new area designed to help customers drive onboarding, adoption, and shared project workflows in a more structured way.

In Adoption, you can now:

• View onboarding project status as a new customer
• See adoption metrics related to usage of the platform
• Manage projects you are doing together with us
• Create projects
• Add stages
• Add tasks
• Assign tasks to team members
• Add files to stages
• Comment on stages

Team members will also receive reminders and updates via email when something changes or when milestones are close to being exceeded.

Why this matters

The purpose of this feature is to build an interface where adoption of the platform can be supported through workflow management.

Right now, everything is manual. But over time, this lays the groundwork for a more agentic setup.

For example, in the future you could imagine Magnity creating a project for you automatically, such as Newsletter 34, and then assigning users to tasks based on roles and responsibilities.

This first version is the beginning of that direction.

✅ Compliance Agent: grouped findings as the default view

We have adjusted the interface of the Compliance Agent so that findings are now shown grouped together by default when analysing an asset.

Grouping can be toggled on or off.

When grouping is turned on, findings are grouped by things such as:

• Categorization
• Topic
• Rule ID
• Related issue type

This is meant to make the interface easier to work with, especially when many findings relate to the same kind of issue.

Example

If there are 5 findings related to an unapproved use of a hyphen, these findings can now be shown as one grouped issue containing 5 findings.

This helps in two ways:

• It makes the interface easier to understand
• It allows you to work more efficiently with bulk remediation of the same type of issue

🏷 Asset type selection in the Compliance Agent

When you upload an asset into the Compliance Agent, you must now select the asset type from a dropdown.

Examples include:

• Landing page
• Email
• White paper
• Video
• Article
• Other document types

The reason for this is that we have now added the value of this field as a merge field in the rules.

This means you can now make parts of your rules conditional on the type of asset being analysed.

Example

You could write a rule such as:
If the asset type is video, do not run any boilerplate analysis.”

This makes the Compliance Agent much more flexible and allows your rules to become more context-aware.

🔎 Verification is now a dedicated skill option

We have also added verification as a specific option in the agent skills.

This means that when a finding recommends that something should be verified rather than changed, it will no longer show up as a “change this into that” type of recommendation.

This is important because not every issue is a direct rewrite problem. Some findings are better handled as checks, confirmations, or validation tasks.

The result is a more precise and more helpful review experience.

🎯 Why this matters

This release is about making Magnity easier to use in practice while also making the underlying system smarter.

The new Adoption area helps structure platform rollout and shared work.

Grouped findings reduce noise in Compliance Agent reviews.
Asset type selection makes rules more context-aware.
And verification as a separate skill improves the quality of recommendations.

All of this supports our broader ambition to make Magnity a more intelligent and operationally useful agentic system.

🔮 Upcoming features

We are continuing work in two important areas.

New front-end redesign

We are releasing a new and redesigned front-end interface with many improvements.

The reason is simple: it will make development of features such as review, collaboration, agents, and other advanced capabilities much easier to implement.

Rebuilt crawler

We are also rebuilding the crawler so it becomes:

• Better at handling corner cases when identifying URLs across markets
• Better at understanding localized page relationships
• Better at formatting scraped text so it is immediately more readable

This will improve both the quality of collected source material and the overall usefulness of content inside Magnity.

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 improving two important workflows in Magnity: planning and scheduling social media posts, and collaborating around compliance findings.

We are also continuing our larger UX and design overhaul of the application, but those changes are not ready to release just yet. More on that soon.

📅 Calendar view in the Social Media Agent

We have added calendar functionality to the Social Media Agent.

When scheduling posts, you can now choose between:

• List view
• Calendar view

This makes it easier to see what is planned, when posts are scheduled, and how your social media activity is distributed over time.

You can also click a scheduled post directly from the calendar and return to working on that post.

In addition, you can now select geographic targeting when scheduling social media posts.

💬 Comments in the Compliance Agent

You can now add comments to findings in the Compliance Agent.

This enables simple collaboration around compliance findings, especially when several people need to review, clarify, or discuss an issue before it is resolved.

Comments can be used to:

• Add context to a finding
• Explain why a finding should be changed, resolved, or dismissed
• Leave notes for colleagues or reviewers
• Support a more practical review workflow

This is one of the next steps in making the Compliance Agent more useful as a collaborative review environment.

✍️ Add findings manually in the Compliance Agent

You can now manually add findings in the Compliance Agent.

When reviewing the preview text, you can highlight a piece of text and click Add finding manually.

This opens a new finding where you can add:

• Description
• Suggested change
• Severity level

This is useful when you spot something that Magnity has not flagged automatically, or when you want to add a human review point to the compliance report.

It also makes the Compliance Agent more flexible, because findings can now come from both AI analysis and manual reviewer input.

🎨 Larger UX and design overhaul underway

We are currently working on a major UX and design overhaul of Magnity.

This work is not ready to release yet, but it is progressing and will shape how Magnity becomes easier, faster, and more intuitive to use across agents and builders.

Please stand by. We will share more when the first parts are ready.

🎯 Why this matters

This release improves both planning and review.

The Social Media Agent now gives you a clearer overview of scheduled content, while the Compliance Agent becomes more collaborative and flexible.

Together, these changes support our broader direction: making Magnity a more complete agentic operating system for B2B marketing, where content can be planned, built, checked, reviewed, and improved in one connected workflow.

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 improves the depth and quality of the Compliance Agent, expands what you can upload directly in agent chat, and adds a few important upgrades to the Persona Agent and Rules Agent.

🛡️ Compliance Agent: new 3-step analysis cycle

We have upgraded the Compliance Agent analysis cycle so each report now runs through three analysis steps instead of one.

The new flow works like this:

1. Initial analysis run
   Magnity performs the first standard analysis of the selected content.
2. Second analysis run with memory
   Magnity then performs a second run while keeping the first run in memory. This helps it identify additional findings and reconsider edge cases with more context.
3. Third review and merge run
   Finally, Magnity performs a third pass where it merges the two previous analysis runs, removes duplicates, and distributes ownership of findings into the right reports.

This means the Compliance Agent is now better at:
• Catching more relevant findings
• Reducing duplicate findings
• Assigning findings to the right analysis report
• Producing a cleaner and more trustworthy result set

📎 Upload files and images directly in chat

We are now offering the ability to upload files directly into agent chat using the plus icon.

Supported formats currently include:
• PDF
• Word
• PowerPoint
• TXT
• Images

Magnity can now read these formats when they are uploaded through chat, which also means that Magnity can now read images.

This is currently available in:
• The Rules Agent
• The Persona Agent

We will be adding this capability to all chats soon.

👤 Persona Agent: create industry descriptions

We have upgraded the Persona Agent so it can now also create industry descriptions for you.

This makes it easier to build stronger persona setups where personas and industries work together as part of your personalization, planning, and flow logic.

🧠 Rules Agent improvements

We have upgraded the Rules Agent and fixed a few smaller issues related to changing multiple rules at once.

Most importantly, we fixed an issue where changing multiple rules could sometimes result in a greyed-out Action Block button, preventing you from proceeding properly.

This is now working as intended.

🔮 Upcoming features

We are working on several important upgrades behind the scenes.

A rebuilt crawler

We are rebuilding our crawler so it becomes more advanced in how it identifies localized URLs.

The goal is to improve:
• Local variant detection
• International URL matching
• Content consistency across markets

We also want the crawler to format the text it collects before saving it, using an open source model operating locally.

Folders in Projects view

As part of our redesign efforts, we are adding folders to the Projects view.

This will make it much easier to organize work at scale.

Proactive rule intelligence

We are also working on proactive rule intelligence.

This means Magnity will begin learning from your rule-related interactions and will be able to suggest rule changes on an ongoing basis through the Rules Agent.

Front-end redesign and structured React library

We are redesigning the general interface and adding a more structured React component library to the front end.

This will:
• Make the interface more user friendly
• Make Magnity easier to develop further
• Support the broader transition toward a more agent-ready experience

🎯 Why this matters

This release improves two of the things that matter most when building an agentic operating system:

• Better reasoning quality
• Better contextual input

The Compliance Agent now performs a much more robust review cycle, and the ability to upload richer file types directly into chat gives agents more ways to understand what you are working on.

Together with the upgrades to the Persona Agent and Rules Agent, this is another step toward making Magnity more intelligent, more flexible, and easier to work with.

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 week’s release focuses on three major improvements.

First, you can now add files and images to all remaining chats in Magnity.
Second, we are releasing folders for projects.
Third, we have significantly reduced the initial information load in the Compliance Agent to make review easier and faster.

📎 Add files and images to any chat

Last week we released the ability to add files to chat in the Rules Agent and Persona Agent using the small + icon on the left side of the chat.

That release went well, and we are now rolling out the same capability to all remaining chats in:

• Email
• Webpage
• SoMe
• Content Agent

Compliance Agent will follow as well, but we still need to implement a few agentic pieces there first.

You can now upload:

• PPT
• DOCX
• TXT
• PDF
• Images

This means you can feed a chat with much richer context.

Examples:
• Add an image of a webpage and ask Magnity to extract the content and give you a conversion optimization analysis
• Add campaign plans as screenshots or images and ask Magnity to build from them
• Upload visual concepts you want to discuss or improve
• Use uploaded images as the starting point for image editing or re-use

You can also choose Add content manually, which opens a field where you can simply paste in text as a manual source.

This makes chat much more flexible and much better suited for real work, where your input is rarely just one tile or one page.

📁 Folders for projects

We are also releasing folders for projects.

While this sounds simple, it is a meaningful improvement to how you organize work in Magnity.

You can now:

• Create folders
• Delete folders
• Create nested folders
• Drag and drop projects into folders
• Move a project into a folder using the ... menu
• Select what folder to save a project in directly from one of the agents

This should make it much easier to keep your projects organized and manageable over time.

✅ Compliance Agent: reduced information load and easier review

We have made a significant update to the Compliance Agent interface to reduce the amount of information shown at once and make findings easier to work with.

What has changed

Removed left-side finding details panel
We have removed the entire left tab that previously showed finding details.
Instead, details now live directly under each finding card in the Analysis tab and can be expanded by clicking See details.

Replaced explanatory text under category headlines
We removed the explanatory text below the findings section headlines and replaced it with pills showing the severity level distribution for the category findings.

Redesigned finding cards
We have redesigned how each finding card works.

First, we now show the suggestion by default instead of the description.

Suggestions contain two fields:

• Replace this
• With this

“Replace this” is tinted red/coral, and “With this” is tinted green. This makes the key action much easier to understand immediately.

Second, we removed the subcategories called Resolved and Dismissed as separate movement states in the interface. Previously, cards moved around when state changed, which created confusion. Now cards stay in place regardless of whether they are:

• Finding
• Fixed
• Resolved
• Dismissed

You can still filter by these states if needed.

Third, each card now has a very clear color and matching pill/tag based on state:

• Yellow = Finding
• Purple = Fixed
• Green = Resolved
• Coral / Red = Dismissed

The matching text in the raw source is highlighted accordingly, making it much easier to understand the status of each issue.

⏭ Coming very soon to Compliance Agent

We are already working on the next set of additions, likely for early next week.

Comments on findings

Each finding will be commentable by users, so you can add extra information for reviewers or coworkers.

Add finding manually

You will be able to highlight text and add a finding manually.
When text is highlighted, a small hover button will appear and open a new finding card you can edit.

Feedback when dismissing

When dismissing a finding, you will be asked to give feedback. This will not be mandatory, but it will help teach the system where it fails and support future proactive rule updates.

Select document type

We will add the ability to define a document type, such as:

• Email
• Article
• Press release
• Webpage

This will become available as a merge field in rules, so you can write rules specific to document type.
For example, for email analysis you may not want to review the header and footer.

We do not have a release date yet, but we hope as soon as next week.

🛠 Other fixes and updates

Word upload fix in Compliance Agent

We fixed an issue where Word documents with many nested tables were not read correctly.
They are now handled properly in the Compliance Agent.

Flow Builder improvement

We adjusted the Flow Builder so that subject line and preheader are now built in sequence.

This means the preheader now knows what the subject line is before it is created, just like in the ordinary email builder.

Email exporter safeguard

We adjusted the email exporter so unsaved email projects can no longer be exported.

This prevents several potential file-related issues.

🤖 Agentic backend preparations across all builders

We have now made preparations so that all builders have an agentic backend.

For the more technical among you, this means we can begin introducing inter-agent connectivity.

Examples of what this could enable:
• Invoke the Rules Agent from the Email Agent
• Invoke the upcoming SEO/GEO Agent, or Findability Agent, from the Webpage Agent
• Invoke the Compliance Agent from the Content Agent

This opens up many possible concepts and workflows.

It is also an important path toward a stronger review and collaboration setup around content creation. There is still work to do before this is fully connected, but the groundwork is now in place.

🧠 Learning from first draft and final export states

We are also beginning to store emails, webpages, and SoMe posts in both:

• First draft mode
• Final export mode

Over time, this can be fed into the Rules Agent.

The purpose is to move toward self-correcting agentic networks that learn from your interactions and suggest rule changes as a consequence.

This is not finished yet, but development is underway.

🔮 Looking ahead

We have more things underway that we believe will continue pushing the marketing space forward, and we will share more as we get closer.

The long-term goal remains the same:

To build an Agentic OS for B2B marketing that behaves like an autonomous marketing agent.

These releases are all steps in that direction.

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 we are releasing another agent as part of our redesign and our effort to make Magnity more functional, more helpful, and easier to use: the Persona Agent.

The Persona Agent adds AI directly to persona work in Magnity, making it much easier to create, improve, evaluate, and manage personas as part of a more agent-driven workflow.

👤 Introducing the Persona Agent

The Persona Agent is an AI agent built specifically for persona creation and optimization.

Just like the Rules Agent, it allows you to chat directly with your personas and ask Magnity to help with persona-related work across multiple levels.

You can now use the Persona Agent to:

• Edit existing personas
• Evaluate whether personas are strong enough
• Research new information relevant to personas
• Create new personas from scratch
• Add images or edit persona avatars using OpenAI Image 2.0
• Compare personas and identify overlaps or gaps
• Work more intelligently with industries and persona context

This gives you a much more flexible and intelligent way to work with personas than simple manual editing.

🧠 What the Persona Agent understands

The Persona Agent is built with a broad set of persona-related skills. We will not list them all here, but in practice it means you now have an agent that can help with much more than just editing a persona field.

It can help you:

• Judge whether a persona is too weak, vague, or overlapping
• Improve persona structure and clarity
• Turn research into better persona definitions
• Understand how industries influence personas
• Evaluate how personas and personalization rules fit together
• Create personas that are more operational and useful in actual content generation

This is especially important if you are working seriously with personalization and want personas to be something more than just static descriptions.

🖼 Avatar editing and generation with OpenAI Image 2.0

The Persona Agent can also help generate or update persona avatars using OpenAI Image 2.0.

This means you can create a new persona and add a fitting avatar, or improve and update the avatar of an existing persona, directly as part of your persona workflow.

🗂 Updated persona interface

Alongside the Persona Agent, we have also slightly updated the persona interface.

The interface is now more contemporary and easier to work with.
You can now more easily:

• Edit personas
• Duplicate personas
• Delete personas
• Disable personas

These actions are now available from icons at the top of the avatar image, making persona management faster and more intuitive.

📄 Backup PDF export agent

We have also added a backup PDF export agent.

This means Magnity now has a fallback mechanism for PDF export, so you are less likely to experience downtime if one of our external suppliers has issues.

This happens automatically in the background.

🧾 HTML-friendly rules formatting

We have also made our rules HTML formatting friendly.

This means that if you ask the Rules Agent to format your rules more nicely, it can now save them in a more readable format using:

• Bold text
• Bullets
• Better visual structure

This makes longer rulesets easier to read, review, and maintain.

🔮 What’s next

We are currently looking at the crawler next, along with further items in the Magnity redesign.

There is more to come as we continue evolving Magnity toward a more agentic and easier-to-use system.

Stay tuned.

🎯 Why this matters

The Persona Agent is another important step toward turning Magnity into an agentic operating system for B2B marketing.

Personas are central to personalization, planning, flow creation, and content relevance. By adding an agent directly to persona work, we make it easier to improve the quality of personas and ensure they are actually useful in the rest of Magnity.

Together with the Rules Agent and the ongoing redesign, this pushes Magnity further toward a much more intelligent, connected, and usable system.

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 we are releasing a major stepping stone toward a multi-agent network that can operate as part of a B2B marketing operating system: the Rules Agent.

Magnity has always offered a huge degree of freedom and flexibility through its layered rule system. That flexibility is powerful, but it also comes with complexity and responsibility. So we decided to build an agent specifically to help you understand, navigate, optimize, and safely update your rules.

This release also includes updates to the Content Agent, the Compliance Agent, a new home page, and a few important fixes.

🧠 Introducing the Rules Agent

The Rules Agent is an AI reasoning agent attached to your rules.

It understands:
• How your rules are structured
• How they relate to each other
• How merge fields work
• How rules affect content generation across Magnity
• How to safely suggest and apply updates

It comes with:
• A general chat for all rules
• A dedicated chat for each individual rule

You can use it to:
• Ask questions about your rules
• Optimize all rules at once
• Optimize a category of rules
• Optimize a single rule
• Ask for recommendations
• Discuss changes before applying them
• Get suggested edits
• Let the agent perform the changes for you
​

🧰 The 7 skills of the Rules Agent

The Rules Agent uses a set of specialized skills to reason about your rules and decide what to do.

From the current setup, these skills include:

• How rules are organised
Helps explain the overall structure of the rule system and how the different rule layers fit together.

• Key relationships
Explains how rules influence each other and what dependencies exist between them.

• Proposing rule updates
Helps draft improvements, rewrites, or optimizations to rules based on your intent.

• Reviewing rule quality
Evaluates whether a rule is clear, useful, redundant, too vague, or potentially conflicting.

• Using merge fields
Explains and helps update merge fields correctly so rules use the right dynamic inputs.

• Version history and rollback
Understands how rule versions, snapshots, and rollback work so experimentation stays safe.

• Element generation order and dependencies
Explains how rules affect content generation order and how certain rules depend on output from others.

• External research and inspiration
Helps reason about outside inspiration and how to translate intent into better rules without breaking your existing setup.
​

🗂 A redesigned rules interface

We have redesigned the rules interface to make it much easier to understand, use, and navigate.

When you open your rules, you now land in the All rules view, and the chat on the right tells you that you are currently chatting with all rules.

You can:
• Filter by source and medium
• Search rules
• Sort rules alphabetically
• Sort by latest updated

This makes it much easier to find the rules you just changed, or the rules you want to review next.

🏷 Updated rule category names

We have updated the names of rule categories to better reflect their purpose and context.

The changes are:

• Global rules → Brand rules
• Local rules → Market rules
• Base prompts → Element rules and Element prompts

You can now also work with:

• Task rules

This is where personalization and translation rules now live.

• Flow rules
These now live under Element rules.

🔎 Better visibility into rules and merge fields

When you expand a rule, you can now see:
• A short description of what it does
• The rule itself

For element, market, and task rules and prompts, you can also see the merge fields used by the rule.

Merge fields are the dynamic pieces of text Magnity inserts during generation, such as:
• The URL of the tile you used
• The selected language
• The scraped source text
• Other runtime context

If you are unsure what they do, the Rules Agent can explain them to you.

🧱 Rule Stack view

When you click a specific rule, the chat for that rule opens.

Next to the chat, you will now find a new tab: Rule Stack.

This shows you what other rules influence the rule you are working with. That matters when making changes, because rules rarely live in isolation.

The Rules Agent understands the Rule Stack as well, so when it suggests or applies changes, it takes the surrounding rule context into account.

🕘 Version history, snapshots, and rollback

In the top right corner you can now access Rules History and see the changes that have happened.

You can also click a new function called Snapshot, which lets you save a snapshot of all your rules before experimenting.

This is especially helpful before making changes across multiple rules.

In addition, each individual rule still supports rollback to its five latest versions, so if you only want to undo one rule change, you can do that quickly.

🧾 Diff view and action block

When the Rules Agent suggests an update, it will always offer to show you a diff.

The diff makes the change transparent by showing:
• Removed text in red and struck through
• New text in green
• The changes side by side

It will also offer an Action Block, where you can see the full updated rule and either:

• Accept
• Dismiss

If you accept, a new rule version is created and saved automatically.

This gives you a much safer and more flexible way to optimize rules and experiment with rule sets.

🎥 More to come on the Rules Agent

There are more details to the Rules Agent than we can reasonably cover here. We will go through those in an upcoming training video.

If you would like a more detailed walkthrough, we are also happy to offer a full 1-hour presentation free of charge.

Please reach out to your admin.

The next step for the Rules Agent is to allow it to make proactive rule suggestions. We are working toward that now, but there are a few things we need to build first.

This is one of many steps toward an agentic OS for B2B marketing.

✍️ Content Agent updates

We have made a few useful additions to the Content Agent.

Copy text from the canvas

You can now copy text directly from the Content Agent canvas using a small copy icon in the top right corner.

Replace or Add to canvas

In the chat, you can now choose between:

• Replace
This replaces the text in the canvas with the selected chat response.

• Add to canvas
This adds the selected text to the bottom of the canvas.

This is especially helpful when building campaign plans or other structured documents that expand as you work.

✅ Compliance Agent updates

We have made two important improvements to the Compliance Agent.

Export multiple analysis runs into one document

You can now run multiple analyses and choose which analysis you want to export findings and remediations from as comments.

This means you can analyze a PDF in multiple steps and still get all suggestions collected into one exported document.

Easier manual editing

A new Manual edit button makes it easier to manually replace a found issue directly. This is a fast and practical way to edit content when you know exactly what needs changing.

Compliance chat can now apply debated fixes

We have also fixed the chat in the Compliance Agent so that it can now apply the fixes you reach through discussion in the chat itself.

🖼 OpenAI Image Model 2.0 is now live

We are very happy to announce that Magnity is now using OpenAI’s new Image Model 2.0 for both image creation and editing.

You can use it:
• In the Content Agent
• In the image cropper

If you have not tried the new image capabilities yet, give them a spin.

For example:
“Give me an image of my brand’s top product as a blueprint infographic. Search for product details.”

Here is ours :D

​

🏠 New home page

You will also notice that the start page has been redesigned.

The new home page now allows you to:
• See the last four projects you worked on
• Pick between the available agent builders you have access to
• Read the latest news

This, together with the Rules Agent, is an early look at the broader redesign we need to undertake as we move toward an agentic OS.

🔮 Upcoming features

We are currently making backend updates so that more of Magnity can be transformed into agents.

This new approach also demands a new design direction, which we have wanted for a long time. We are now actively working on that.

A larger Magnity redesign

We are going to redesign Magnity. As part of that redesign, several smaller but highly useful features will arrive, including:

• Folders
• Comparison views
• Review features
• Other quality-of-life improvements

This will take a few weeks, but it should make the interface significantly better, more helpful, more intuitive, and more flexible.

Stay tuned for more.

🛠 Minor fixes

We have fixed a couple of important issues:

• Previously, if you used a high thinking model on a very large task, Magnity could appear not to respond. This happened because the underlying Umbraco backend timed out if no response was returned within four minutes. This is no longer a problem, and the model can now think as long as needed before responding.
This means you can now use high thinking models for tasks such as translating large volumes of text.

• We have also fixed the chat in the Compliance Agent so that it can now apply any fixes you discuss your way toward in the chat.

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 an entirely new agent in Magnity: the Compliance Agent.
​

The Compliance Agent is built to support our journey toward becoming an Agentic Operating System for Marketing, supporting all six links of the value chain:

• Research
• Plan
• Build
• Check
• Deploy
• Improve

This agent is also the first major step toward a much stronger review experience in Magnity. We wanted to take review beyond simple comments, so we built a full AI-powered compliance workflow that can review and remediate content based on your rules.

Right now, the Compliance Agent is a standalone agent. Over time, we aim to bring its functionality into all builders, so compliance becomes an integrated part of Magnity at every level.

🪜 How it works in 4 steps

The Compliance Agent works in four simple steps:

1. Add a content piece
2. Pick what analyses to run
3. Review findings and remediate them
4. Resolve or dismiss findings and export the desired file
   ​

🛡️ What the Compliance Agent does

The Compliance Agent can take any:

• Video
• Webpage
• Word document
• PDF
• PowerPoint document
​
​

It extracts the text, runs one or more analyses on it, and presents you with specific findings based on

your:

• Brand rules
• Legal rules
• Marketing claims rules
• Other compliance requirements
​
​

Each finding is:

• Categorized
• Rated by criticality
• Supported with description, suggestion, and evidence

You can then:

• Chat with any finding
• Let Magnity fix the finding
• Fix the finding manually
• Resolve or dismiss the finding
​

🔎 A more serious review workflow

This is not just an AI checker. It is a proper review workflow.
​

Every fix includes a before and after, and every remediation is stored in a dedicated Remediation View. This makes it possible to:
​

• Review all changes made
• Export suggestions to colleagues
• See exactly what was changed and why

Magnity also keeps an Audit Log, so you can track every finding, remediation, and action taken across multiple analyses of the same content.

In addition, each analysis run generates a report, which can be exported and shared if needed.
​
​

🔧 Exporting remediated content

The Compliance Agent lets you export reviewed content in several ways.

You can export PDF, Word, and PowerPoint files with findings and before/after text inserted as comments.

You can also export fully edited Word and PowerPoint files if you want the remediations already applied.
​

We are working on doing the same for PDFs. PDFs are simply a more difficult format to work with, and we need more time to perfect that functionality.
​

⚖️ Why this matters

For companies with legal review, strong MLR processes, or strict brand guidelines, this can save months of back and forth between legal and marketing.

The goal is not to eliminate legal review entirely. The goal is to get content approved orders of magnitude faster by letting Magnity perform a serious pre-check before content reaches legal or regulatory stakeholders.
​

📚 Marketing claims analysis

You can also set up a marketing claims analysis.

In that scenario, Magnity can:

• Identify claim-like statements
• Flag them
• Check them against your marketing claims library
• Determine whether they are approved or disapproved

This is especially useful for teams working in regulated or highly controlled environments.
​

🧠 Setting up the Compliance Agent

To use the Compliance Agent well, we need to set up your compliance rules.
​

There are different ways to do this.

If you already have documented compliance or legal rules, we can use those.
​

If you do not, we can help construct them from existing content. For example, we can load a large set of pages into Magnity and ask it to identify coherent expressions, naming patterns, phrasing conventions, or legal patterns. We can then refine and extend the ruleset with more content.
​

The point is not to create a “perfect” compliant document that skips review. The point is to dramatically improve the quality of content before it reaches final review.
​

✉️ Smaller Magnity improvements in this release

Alongside the Compliance Agent, we have also made a few improvements across Magnity.
​

Empty module warning on export

When exporting an email or webpage, Magnity will now tell you if you have any empty modules in the project. A link appears in the export view so you can click directly back to the empty content.
​

Smarter TXT and PDF export from Content Agent

If you export more than five TXT or PDF files from the Content Agent, Magnity will now package them into a ZIP file. This prevents browsers from being flooded with downloads and avoids browser limitations.
​

🛠 Bug fixes

We have fixed several bugs:

• Fixed a bug where certain video files added to the Content Agent were missing the first two timestamps
• Fixed a bug where the Flow Builder sometimes did not use local language rules correctly
• Fixed a bug where filters in the content library could reduce the visible content count incorrectly
​

🔮 Other work in progress

Apart from the Compliance Agent, we have been working hard on several major initiatives.
​

Interface redesign

We are redesigning the overall Magnity interface, making it more contemporary, more functional, and more agent-ready. We are not abandoning the tab system, but we are making it much more engaging.
​

Review functionality

The Compliance Agent is only the first step in a broader rethink of review in Magnity. We will continue building in this direction.
​

Multi-layered multi-agent network

We have been conceptualizing a multi-layered, multi-agent network that we will share more about in the coming weeks.
​

SEO / GEO Agent

We have built an SEO / GEO agent that we plan to release in the not too distant future. We are excited about it, but not ready to share more just yet.
​

Rules Agent

We have almost completed a Rules Agent.

At the same time, the entire Control Panel and rule interface are getting a major overhaul. The Rules Agent will allow you to chat directly with your rules.

You will be able to:
​

• Ask what should be changed
• Explain what seems wrong
• Let the agent identify which rules are relevant
• Get suggestions for how to update them
• Let the agent apply multiple rule changes for you
​

This is a major step toward making Magnity much easier to control and optimize over time. Expect v1 to release within the next 7 days.
​

Broader upcoming features

Several previously mentioned features are part of this larger backend and product work, including:

• Project folders
• Better support for PPTX and Word documents
• More flexible model selection
• Better control over which models are available across features

We are building these carefully because we want them to work properly across the platform.
​

🎯 Why this release is important

The Compliance Agent is not just another feature. It is a major expansion of what Magnity is.

It brings serious review, remediation, auditability, and structured compliance workflows into the platform, and it moves us much closer to our long-term vision of an Agentic OS for B2B marketing and, ultimately, an autonomous B2B marketing agent.

We thank you for your patience and are excited to release much more in the immediate future.
​

Questions or feedback?

Please direct any questions about the above to your administrator.
​

Thank you for using Magnity.
— The Magnity Development Team

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

This release focuses on making day-to-day work in Magnity faster and easier. It includes more flexible export options in the Content Agent, better visibility into tile availability across markets, faster sharing with reviewers, and a small but useful upgrade to YouTube video tiles.

📄 Content Agent: Save as TXT and choose what variants to export

Just as you can already export emails into PDF files and choose how variants should be grouped, you can now do the same from the Content Agent.

You can now:

• Export all variants in one file
• Export one variant in each file
• Export one variant plus the master version in each file

We have also added the ability to save content as a TXT file.

This opens up a practical new use case for video localization and subtitle workflows.

Example:

• Drag in a video as a source
• Or paste in subtitle text manually
• Translate it into as many languages as needed
• Export each language as its own TXT file

This is especially useful when working with SRT and subtitle production, where fast translation and clean text export matter more than visual formatting.

In short, Magnity can now help you go from one source transcript to multiple language-ready subtitle files much faster.

🌍 See what markets a tile is available in

If you click the small pencil icon to edit a tile, you can now see what markets that tile is available in.

There are now three views:

• Total overview of availability
• Markets where the tile is available
• Markets where the tile is unavailable

This makes it much easier to evaluate whether a page or source is available in the markets you need before you begin creating an email or other content.

👥 Share project with reviewers

We have been working to make reviews faster.

You can now choose Share with reviewers from the Share menu under projects.

If a user is tagged as a reviewer in our back end for a market included in the project, that user will automatically be shared on the project.

This means you no longer need to pick reviewers one by one, which can otherwise take quite a while when many markets are involved.

▶️ YouTube video tiles now show video title

YouTube video tiles have had a small but useful upgrade.

Previously, tiles showed the video URL in the left content library tab.

They now show the YouTube video title instead.

This should make it much easier to identify which video is which when browsing the content library.

If you click the title, it will still take you to the original video.

🛠 Known issues

We are currently working through a few bugs.

One known issue is that when saving a project in the Content Agent, Magnity may sometimes forget attachments added to the chat.

The attachments are still visible in the chat and can be re-added, but we know this is annoying and are working to fix it.

🔮 Upcoming releases

We have more improvements on the way as mentioned in our last release notews and will share more soon. These updates are partily delivering on that.

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 week’s release is a smaller feature update following the recent custom template release. It introduces self-service YouTube crawling, new options for automatic channel ingestion, further improvements to custom templates, and a few upcoming features already in progress.

▶️ YouTube videos can now be added as sources directly in Magnity

You can now add YouTube videos as sources in Magnity yourselves.

Up until now, if you wanted to use a YouTube video as a source, you had to send it to us and we would add it through the back end. That is no longer necessary. You can now do this directly inside the interface.

If you click the little + icon next to Filters, where you usually upload new sources, you will now find a fifth tab called Crawl YouTube.

Here, you can:

• Paste in any YouTube video link
• Press Crawl
• Add the video directly to your source library

If the YouTube video already has an existing transcription on the YouTube page, Magnity will crawl the video almost instantly.

If it does not have a transcription, we will generate the transcription as part of the crawl.

This makes it much easier to use video content as a source for planning, analysis, and content creation.

📺 Automatic YouTube channel crawling by market

We can now also set up automatic crawling of YouTube channels per market in the back end.

This means a market can have its own assigned YouTube channel, but it can also inherit channels from another market where relevant.

Example:
If you have both a Global and a UK YouTube channel in English, we can set Magnity up so:

• The Global market crawls the Global channel
• The UK market crawls the UK channel
• The UK market can also inherit the Global channel
• Or vice versa, depending on how you want your source structure to work

This allows multiple relevant channels to update automatically in the same market library.
​

If you would like your YouTube channel or channels added to automatic crawling, please reach out to us and we can help you add that in 10 minutes.

🧩 Custom template export upgrade

We have added further functionality to the custom template feature.

When exporting, Magnity can now handle modules where background colours are selected through a drop-down field.

This required a significant rethink of the export functionality, and that work is now completed across all customers.

If you do not currently have configurable background colours in your templates or modules and would like that added, please reach out.

Important note

Because of this export issue, which is now fixed, not all customers are yet live with custom templates.

We are working on getting everyone fully enabled as quickly as possible.

Thank you for your patience while we complete the rollout.

🛠 Known issue

We are currently looking into a known issue where, in rare cases, creating an email can result in two variants of the same email being created at once, making the email appear empty.

When this happens, we need to unpublish one of the variants to return the email to normal.

🔮 Upcoming features

We are currently building a compliance agent that will allow marketers and other relevant employees to upload and review:

• PowerPoint documents
• PDF documents
• Word documents
• Videos
• Web pages
• Emails

This feature is expected to be in beta within the next 1 to 2 weeks. This does not equal to a fully fledged production ready agent, but a funcitonal brand compliance agent, that can be used within a limited use case.

We are also focusing on improving a number of areas over the coming weeks. Not because anything is fundamentally wrong, but because we have several loose ends we want to make better.

Automatic reviewer identification upon sharing
When sharing a project, we plan to add a button that allows you to share directly with the relevant reviewers.

If a user is tagged as a reviewer for a local market, and that market has a version of the content you are building, they will automatically be added to the share list.

Change LLM from within the interface
We are exploring the option to let each user have their own preferred LLM inside the interface.

This would let you switch model only for your own work, instead of changing it for everyone.

For example:

• ChatGPT 5.4 High works very well for translation
• But it can feel unnecessarily slow for standard copywriting tasks

Content review mode with comments
We are looking at adding a review mode where a project can be marked for review and approval.

A reviewer would then be able to:

• Approve the project
• Add comments directly to the project

Project folders
We are looking at adding a folder system for projects, to make it easier to manage larger portfolios of work.

Custom QuickPrompts
We are looking at adding custom QuickPrompts as a feature.

This would allow you to explain to Magnity what you want to achieve, after which it would build the necessary QuickPrompt for you to test and add to your setup.

Additional channels
We are also looking into adding more fixed output channels, such as WhatsApp.

Timing is still uncertain.

Content context
Just like we can add context when building a newsletter flow, we are aiming to do the same for web pages and emails.

This would allow each element in a web page or email to better understand what the other elements are doing, so the final output becomes more coherent and aligned.

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