To make this easier, a user must go to their personal settings to toggle on the option to turn on their browser default scroll bar under Accessibility. This is the only option available in this section of settings.

My idea or question to the Wrike Product team - can this be made a default setting for all users across an account? I think it would be valuable to all users regardless as there is a barrier here for the user experience and this seems like the solve.

Hey Community! 👋

Welcome to Wrike Agent News!

This monthly digest features updates, learnings, and how-tos from the Wrike R&D team.

This month’s theme is precision: every new feature is focused on giving you finer control over what agents do, where they operate, and how you track everything that happens.

📍 New Action: Location Change 

Agents can now move tasks between folders or add them to additional folders based on content, status, or whatever logic you put in the prompt.

There are two modes:

• Move to location pulls the task out of its current folder and places it exclusively in the target.
• Add to location keeps it where it is and adds it to another folder, which is useful when you want visibility across teams without losing the original context.

When writing the agent’s instructions, you embed location chips (structured references to specific folders or projects) directly in the prompt text. The agent reads the task, reasons about which destination fits, and picks from those chips. You control where things can land; the agent decides which one.

Why this matters: Imagine a setup with more than 15 automation rules just to route tasks to the right folder, each rule covering a single condition. With location change, a single agent can read the task, reason about where it belongs, and move it. One agent replaces the whole rule set because the LLM handles the combinatorial logic that static if‑then rules cannot.

📆 New Action: Start and Due Date Change 

Agents can now modify start dates and due dates based on workflow conditions.

Use case: A project kickoff agent can read the project start date, calculate milestone dates based on the project type, and set due dates on key deliverables. Or a simpler pattern: when a task moves to “In Progress,” set the start date to today if it’s empty.

Why this matters: Date management has been one of the most requested agent capabilities, and it is an area where agents add clear value over basic automations. An automation can set a fixed date, but an agent can read the task context and reason about what the right date should be.

🔎 Expanded Context: Parent Fields, Siblings, and Cross-Folder Lookup 

Agents just got significantly smarter about what they can see.

Parent item custom fields

Agents acting on a sub-task can now read custom field values from the parent item. Use case: a task inherits its priority from the project it belongs to, so the agent reads the project’s “Client Tier” field and uses it to decide how to handle the sub-task.

Sibling awareness

Agents can now see other sub-tasks under the same parent. This enables duplicate detection (is there already a task like this one?), workload balancing (how many open tasks does this folder have?), and comparative reasoning (is this the only overdue item, or are all of them late?).

Cross-folder lookup

Agents can read items from other folders in the same space, not just the folder they are appointed to. Example: a new project request comes into an intake folder, and the agent scans a “Forecasted Projects” folder to check if a matching project already exists before creating a duplicate.

Together, these upgrades let agents reason about context beyond the individual task they were triggered on, shifting from “react to one item” to “understand the situation.”

🔗 Agents Now Fire on API Changes 

Agents now trigger when items are created or modified via the Wrike API. Previously, only UI-driven changes fired triggers.

Why this matters: If you use Wrike Integrate, Zapier, or any custom integration that creates or updates tasks via API, your agents will now pick those changes up automatically.

🏷️ Easier Agent Discovery: Comment Icon 

There’s a new icon in the comment editor toolbar for finding and appointing agents. Instead of navigating to the agent management panel, you can discover available agents directly from the comment area of any work item.

This also improves the chat experience: selecting an already appointed agent from the comment bar starts a conversation with it right there in the thread.

🛠️ Action Work Items Filtering 

Each action now has its own filter picker, using the same filter experience you know from Wrike’s standard filters. You can filter by item type, status, assignee, custom fields, importance, name, or any combination.

Filters are applied before the LLM runs, so filtered-out items do not consume credits.

This solves cases where a triaging agent on a project folder was acting on every sub-item (projects, milestones, everything). Now you can add a filter for “tasks only” and it ignores the rest. Or get more specific with “tasks in status New, assigned to nobody.” Each action in a multi-action agent can have different filters, so one action targets open tasks while another targets completed ones.

☑️ New Custom Field Type: Checkboxes 

Agents now read and write checkbox custom fields.

Example use case: A “Reconciliation Complete” checkbox. Instead of someone manually checking the box after filling in all reporting fields, an agent can read those fields, decide whether the data is complete, and then check it, applying judgment, not just flipping a toggle.

The same pattern works for “Triaged,” “Assets Received,” “NDA Signed,” “Brief Approved,” or any binary state that currently requires someone to look at the task and decide.

🔤 Action Naming 

You can now name individual actions inside multi-action agents. Instead of “Action 1,” “Action 2,” and “Action 3” in your activity logs, you’ll see labels like “Set Priority,” “Route to Team,” or “Post Summary.”

Why this matters: It’s a small change that makes a big difference when you’re debugging a five-action agent and trying to figure out which action misfired.

📖 Formula Field Reading 

Agents can now read formulas and calculated custom field values during reasoning. If you have a field that computes a risk score, aggregates sub-item progress, or mirrors a native field value, agents can see it and use it in their decisions.

This is read-only (formula fields are computed, not editable), but it lets agents reason about derived metrics without you having to duplicate the data into a regular field.

Pro tip: If there’s a field type that agents can’t read yet, create a formula field that references it. The formula output becomes visible to the agent and works as a bridge for any unsupported field type. Point a formula at it, and the agent sees the value.

Under the Hood 👇

• Hard limits on sub-item processing: When an agent is configured to run on "all sub-items", you now get a warning at appointment time showing how many items will be affected. This prevents accidental action spikes on large folders.
  
  
• Improved date handling: The LLM layer now correctly interprets relative dates, date ranges, and timezone-aware scheduling.

Agent of the Month: Intake Deduplication Agent 💯

Teams that receive incoming work requests such as support tickets, project intake forms, or creative briefs deal with duplicates constantly. The same request comes in twice, or a new request describes something that already exists under a different name. Catching these manually requires someone to remember what’s already in the pipeline or to search before acting. Most teams don’t.

Why automations can’t do this: An automation can check exact field matches like “if Client Name equals X, do Y.” But incoming requests rarely use the exact same words. “Acme Corp” might come in as “Acme Corporation,” “ACME,” or “the Acme project from last quarter.” Matching requires reading the description, understanding intent, and judging similarity. That’s LLM territory.

The solution: A two-action agent that uses three of this month’s new features, cross-folder lookup, location change, and action filtering, to scan your existing projects, detect duplicates by meaning (not just keywords), and route new requests automatically.

How it works:

1. A new request lands in your intake folder.
   
   
2. The agent reads the request, then scans a reference folder (for example “Active Projects”) for items with similar names, descriptions, or scope using fuzzy matching, not exact matches.
   
   
3. Action 1 posts a comment: duplicate found, no match, or uncertain.
   
   
4. Action 2 routes the request to Active Projects if it’s new, or leaves it in intake for manual review if a duplicate was flagged.

The pattern adapts to any domain: support tickets against known issues, bug reports against existing bugs, RFPs against past proposals. New item arrives → the agent scans a reference folder → judges similarity → then routes or flags.

Click the link below for the complete configuration, prompts, and customization guide.

👉 Solution and configuration

Combining This Month's Features

Location change plus action filtering is a powerful combination. Imagine a project intake folder where new requests land:

• Action 1 (filtered to tasks in status “New” with no assignee): The agent reads the request, classifies the project type, and moves it to the correct team folder using location chips.
  
  
• Action 2 (filtered to tasks in status “New”): The agent sets the due date based on the project type and the urgency described in the brief.
  
  
• Action 3: The agent posts a summary comment tagging the team lead (list the team leads and their folders in the general instruction, since the agent has no access to user data on its own).

You end up with three named actions, “Route Request,” “Set Timeline,” and “Notify Team,” each with its own filter. The activity log shows exactly which action did what.

Questions?

Want help setting up any of these features? Reach out to us in the comments.

Need a different agent type? Contact your Customer Success Manager.

Found a bug or have feedback? Use the feedback link in the product or let us know in the comments.

On Our Radar

Areas we're actively exploring:

• Context filtering: Expanding what agents can see beyond the 3-level hierarchy limit.
• Sub-item trigger scope: Agents that trigger on changes to sub-items of a specific parent.
• Approval flow actions: Agents that start approval workflows and manage approvers.
• Sequential action dependencies: Actions where Step B uses the result of Step A.

Your feedback shapes our roadmap. Keep testing, keep sharing what works (and what doesn't).

Hello Community! 👋

Today we’re sharing a guide to set up an Intake Deduplication Agent that scans new incoming requests, compares them against items in your folder using meaning-based matching, and helps prevent duplicate work from entering your pipeline.

Below, you’ll find the full configuration, prompts, setup instructions, and customization ideas so you can plug this into your intake workflow ✔️

Agent Goal / Use Case

Your intake folder receives more than 50 requests each week, and about 15% are duplicates or near-duplicates of work already in your pipeline. They are often the same project described in different words. By the time someone notices, a kickoff meeting may already be scheduled for work that already exists.

A standard automation rule can match exact field values, but it cannot recognize that “Acme Corp website redesign” and “ACME - redesign of corporate site” refer to the same project.

How It Works

The Intake Deduplication Agent is a multi-action agent that:

1. When a new request lands in your intake folder.
   
2. Reads the new request’s title and description.
   
3. It scans a reference folder (e.g. "Active Projects") for items with similar names, descriptions, or scope, fuzzy matching by meaning.
   
4. Action 1 posts a comment: duplicate found, no match, or uncertain.
   
5. Action 2 routes the request to Active Projects if it's new, or leaves it in intake for manual review if a duplicate was flagged.

Features Used

• Cross-folder lookup — agent reads items from a different folder than where it's appointed
  
• Location change — agent moves/adds items to the correct folder
  
• Action filtering — actions only apply to tasks in Status = New
  
• Action naming — actions are labeled "Check for Duplicates" and "Route Request" in the activity log

Prerequisites

Before setting this up, make sure you have:

1. An Intake Folder

This is where new requests are created.

2. An Active Projects Folder

This folder will act as the reference source the agent checks against.

3. A clear request structure

At minimum, incoming items should have:

• Title
• Description

The better the request details, the better the duplicate detection quality.

Prompt

General Instructions

Action 1 — Post a Comment

Action name: Check for Duplicates

Copy-paste the following into Action 1:

Action 2 — Location Change (Add to location)

Action name: Route Request

Copy-paste the following into Action 2:

Setup Steps

Step 1: Create the Agent

• Go to Space Settings → AI Agents → Create Custom AI Agent
• Name the agent “Intake Deduplication Agent”
• Set the Trigger to “New item created”
• Paste the General Instructions into the instructions field. Replace the location chip placeholder with your actual "Active Projects" folder — type @ or use the folder picker to embed the chip .

Step 2: Configure Action 1

• Add Action 1
• Select Post a comment
• Name it “Check for Duplicates”
• Paste the Action 1 prompt
• Add the filter: Item type = Task, Status = New

Step 3: Configure Action 2

• Add Action 2
• Select Location change (Add to location)
• Name it “Route Request”
• Paste the Action 2 prompt 
• Select your "Active Projects" folder as the target location
• Add the same filter: Item type = Task, Status = New

Step 4: Appoint the Agent

• Appoint the agent to your intake/requests folder.

Step 5: Test in Playground

• Before rolling it out broadly, test with a few examples:

Customization 

1. Different matching criteria

Adjust the "REFERENCE DATA" section in the general instruction to match your domain:

Examples:

• Support tickets: Match on error messages, affected product/module, and customer name
  
• Bug reports: Match on reproduction steps, error codes, and affected component
  
• RFPs / proposals: Match on client name, industry, and requested services
  
• Creative briefs: Match on campaign name, brand, and target audience

2. Stricter or looser matching

• To reduce false positives: Add "Only flag a match if at least two criteria match simultaneously."
  
• To catch more duplicates: Add "Also consider partial matches , if the client name matches but the project description is different, flag as uncertain."

3. Different routing behavior

• Move instead of add: Change Action 2 from "Add to location" to "Move to location" if you want the item removed from intake entirely.
  
• Route to different folders based on type: Add more location chips and adjust the Action 2 prompt: "If no duplicate and the request mentions 'design', add to the Creative Projects folder. If it mentions 'engineering', add it to the Engineering Backlog folder."

4. Adding a status change

If you want the agent to also update the request's status after routing, add a third action:

• Action 3 name: "Update Status"
• Action 3 type: Change status
• Prompt: "If this item was moved to Active Projects, change its status to 'In Review.' If it was flagged as a duplicate, change its status to 'Needs Review.”

Tips

• Start small. Appoint to one intake folder with 10-20 items in the reference folder. Verify the matching quality before scaling.
  
• Check the activity log. The agent's reasoning shows exactly why it flagged (or didn't flag) a match. Use action names "Check for Duplicates" and "Route Request" to quickly find what you're looking for.
  
• Reference folder size matters. Cross-folder lookup works well up to a few hundred items. If your Active Projects folder has thousands of items, consider narrowing with a filter or using a more specific reference folder.
  
• The uncertain category is your friend. It's better to flag an uncertain match for human review than to miss a duplicate or incorrectly block a new request.

Hi Community! 👋

It’s time for another Wrike-Up Wednesday! 🥳

How do you usually start your day? Are you a “coffee first, everything else later” person ☕, someone who jumps straight into planning and priorities 📋, or do you ease in with a quiet moment, a walk, or a quick scroll through updates? 📲

For this week’s Wrike-Up Wednesday, we’d love to hear:

What does your morning ritual in 3 steps look like? It can be as simple, fun, or detailed as you like – just keep it to three steps.

Share your 3-step ritual in the comments and tell us how it helps you start the day on the right note ✨

My Morning Ritual in 3 Steps:

1. Make a cup of coffee or tea, and water my plants ☕🌿
2. Do a quick scan of my Wrike to-do list for the day 📅
3. Put on some background music to get into “work mode” 🎧

Now it’s your turn! ⬇️

I am not familiar with what CORS is, so I don't rreally know where to start looking for solutions. Is it an Auth issue? Aconnection issue? A call issue?

I am using this url to send my requests per the docs
https://www.wrike.com/app/wrike_v2_web/public/api/v1/

But I also tried app-us2.wrike.com with no luck

thanks for any help

A person receiving this email notification isn't sure what project the update is for or what action is requested of them, causing confusion and behaviors like ignoring the email all together or flagging for additional follow up.

Updating the task name was an option we considered as a work around. However, it wasn't a sufficient solution to customize each task's name when working within templates/blueprints, where tasks follow organized naming conventions.

Could email notifications for tagged recipients be more user friendly - with customizable subject lines and/or project number/name included?

Updates to this feature would improve our team's Wrike user adaption and engagement levels.

Similar posts:

/hc/en-us/community/posts/360003159073-Email-notifications-and-project-names

/hc/en-us/community/posts/115003230429-Additional-information-in-email-notifications

/hc/en-us/community/posts/115003990869-Email-notifications-subject-format-improvement

Context: We are trying to streamline a processes in Wrike to collect external requests and love the fact that we can email back the requesters directly through Wrike. 

The only issue or setback that we are experiencing is that we cannot add other email recipients, either directly or in CC. This is causing folks to rely on Outlook to reach out to multiple people, which is unfortunate because these communications cannot be tracked in Wrike.

Suggestion: Allow us to include other email recipients in Wrike so that we can properly loop in folks who might need to be part of the conversation and so that we can truly and fully track all conversations in Wrike on the work item (task or project).

We’re excited to share that Wrike’s Gantt chart is getting a major upgrade 🎉 Based on your feedback, we’re rolling out a new version that brings speed, power, and a more seamless experience to your project planning.

✨ What’s new right now?

• One-click switch – Try out the new Gantt and switch back to the classic version anytime
  
• Performance boost – Faster loading, especially for large and complex projects
  
• Grouping & filters – Organize your data more effectively
  
• Fiscal year support – Plan your timelines with more flexibility
  

👉 You’ll see a “Try new Gantt chart” button directly in your classic Gantt view 

📅 Rollout plan & milestones

August 2025

• Switch option available (classic loads by default)
  
• Grouping + new filters
  
• Fiscal year support
  
• Significant performance improvements
  

Early October 2025 (Planned)

• New Gantt becomes default (switch back to classic is possible)
  
• Public links for sharing Gantt views
  
• Fresh UX updates for a modern look
  
• Improved critical path
  

Early 2026

• The new Gantt becomes the standard version
  
• The classic Gantt will be sunset (based on adoption & feedback)
  
• Snapshots & PDF export
  
• Baseline columns (compare planned vs. actual dates)
  
• Full screen mode
  

📝 What’s changing

A few smaller features from the current Gantt won’t be carried over:

• Manual sorting → will be replaced by grouping
  
• Item creation directly from canvas → simplified via the new Table
  

💬 We need your feedback!

This is just the beginning—we’ll continue improving the new Gantt with your input. Please share your thoughts here in the Community:

• What do you think of the new experience?
  
• Which upcoming features are most important for you?
  
• What’s missing that you’d like to see carried over?
  

Please try the new version and share your feedback below 👇

It would be great if any changes to custom fields on active work would be reflected in the work's activity stream. 

Right now, activity streams report changes in native fields (assignees, start dates, due dates, statuses, etc.) and comments. They don't however show what changes have been applied to any custom field value. This poses a gap in visibility to understand who made what changes - it would be helpful to have a trail of these changes. We have a number of custom fields that different types of work use, and when changes are made, it can often cause confusion - knowing who changed what would help us investigate if need be.

Thanks :) 

Has your team ever had a challenge working with naming conventions? Is manually adding prefixes or suffixes to new or existing items not an option for you? If so, we have great news… our new action in Wrike Automation has got you covered! 😁

Wrike has launched a new Change name action that allows you to change the item’s title in three ways: automatically categorize your items by adding prefixes, and suffixes or simply renaming them completely. 🤖

When creating a rule, you can find the three new options listed in the Change name action :

With this powerful enhancement, adding prefixes to new items is as simple as this:

1. Select the trigger “New item created”.
   
   
2. Select the condition “Change name” and choose the option “Add prefix”. Type the prefix you’d need to include in your item’s title.
   
   

Tip! Don’t forget to select a location where the rule applies to ensure that prefixes are set in the correct folder, like a specific Client folder or your Backlog.

And you’re done! 

And what about already existing items? Easy! 😎 You can create an automation rule to automatically add the relevant prefix (or suffix) when a custom field is ticked.

By ticking the custom field, the prefix will be added to the item’s title:

We know that the idea to add prefixes and suffixes automatically has been quite popular among many of you so please show your excitement in the comments! And please feel free to drop any questions you might have about this new addition 🔥

I'd love to share some feedback on collecting contact information on external request forms.

It would be amazing if we could update the Contact info page questions that appear when we check off Enable public link on a request form and select Require respondent's name and email.

I know the name and email questions are mandatory, but it would be great if we could:

• Add additional questions to this page, related to contact information (ie. phone number, address, etc.)
• Be able to split up the name question (or choose if we want to ask for full name in one question, or first name and/or last name in separate questions)

This piece of feedback sprung from a specific use case. We are trying to connect requester names to our CRM via an integration through mapping the questions to separate custom fields (first name and last name fields), but we cannot add another question to this page or split the name question. We can rename the Your name question to first name and later add last name in the field OR re-add first and last name questions later in the form, but we want to avoid a choppy experience and we don't want users to have to fill in the same questions twice, respectively.

Totally understand that the email question should be mandatory if we are requiring the respondent's name and email, as we want to ensure they get emailed a copy of their submission and so that we can email requesters directly from any give work item - not trying to change this aspect of the existing feature. We just want more control over how we capture name and other relevant contact information.

Thanks!

We have plently of projects that are created from the standard blueprint. The blueprint is set with "New Gantt Chart" view, however the users must always activate manually "New Gantt Chart" view when they're creating the project X from the Request Form (blueprint).

Can we enable by default the "New Gantt Chart" view automatically for the blueprints / all users to avoid this?

New Gantt Chart view is very powerful, we don't see any usage now for the old Ganttchart view.

Many thanks.

Ideally this data would feed into custom fields, but it would be ok if it appeared in the "Add a comment" area at the end of the project record.

https://www.wrike.com/api/v4/webhooks?hookUrl=https://******&secret=8q***

(full address and secret not shown for security)

I am making a GET request, but I'm getting this:

{
  "errorDescription": "Parameter 'hookUrl' is not allowed",
  "error": "invalid_request"
}

Your documentation seems clear on what steps to take and this in not working for me.  I've gone through the community board seeing if anyone else has had this issue.  Nothing looks close to this type of error.

Thanks

We’ve taken our first big step toward a better community experience and introduced a new look and structure for the Wrike Community.

This is just the beginning, and we’re excited to keep building on it based on your needs and feedback. ✨

We’d really appreciate your thoughts:

• What do you like about the new experience so far?
• What feels missing?
• What features or improvements would you like to see next?

Please share your feedback in the comments below (screenshots are welcome!). Your input will directly help us decide what to improve next.

Thank you for helping us make the Wrike Community better for everyone 💚

The workaround is to change the custom field to a number (not percent) and then have the team enter the value. While this works, it looks strange. These charts are graphed using numbers instead of percents. 

If I change the custom field to a percent, Wrike doesn't allow graphing, and this is what the widget edit screen shows: 

We are constantly adding people to the end of comments to make sure they are informed.

Is there a supported way to detect effort allocation changes (via Workato connector triggers or Wrike REST API/webhooks)? If not, is there a recommended workaround that doesn’t require polling all tasks?

Best regards,
Tim

We are currently tracking our equipment in a database (because having assets mixed with users is not implimented very well right now) and have a form for scheduling equipment use. When the task is created, some has to manually go into the database and first check to see if the equipment is available for the requested time, then change the record of that piece of equipment, then update the task appropriatelty. If we had access to the DD in automations it would make this process so much easier.

Also if there was some type of filtering based on a column in the db that would allow only certain items to appear in a custom/form field, that would be amazing!

Then imagine if a dashboard could access DB info):o

It would be helpful to have a setting to allow subtasks to drive the dates for the parent tasks.  Right now it's manual.  There are some who prefer it that way, and some who do not, so it would be nice to be able to set that on a per-project basis.

This log is VERY helpful but it is missing just one key piece of info. The date that it was entered for. It would be great if that was added so users can quickly see: if they made a mistake, already entered something, etcl.

Thanks to @Pietro Poli, I understand that access can be removed by restricting report access for a certain user type. However, the users still need access to dashboards within Reports. I am only referring to workload. If there is no way, is this planned as a future feature?

Hi Community! 😊

We’re excited to announce that pre-enrollment for the Wrike AI Elite Mastery Certification is officially open!

The elite standard is coming. Are you ready to architect the future?

This isn’t just another AI course. It’s a premium, mastery-level certification built for those who want to lead the future of work with confidence. If you’re ready to move beyond basic prompting and learn how to structure, deploy, and scale AI for real organizational impact, this program is for you.

Why pre-enroll in Wrike AI Elite Mastery?

This proctored certification ($299 MSRP) is designed for professionals who want to build elite-level skills in AI-powered work management.

What’s included?

🤖 Agentic Orchestration – Master the deployment of autonomous Wrike Agents to eliminate manual triage and reporting.

📊 Predictive Insights – Leverage AI to identify project slippage before it happens and drive data-driven leadership.

⚙️ The Methodology Bridge – Learn the “Why-To” strategy for structuring AI across complex, cross-functional work hierarchies.

Why it matters

Earning and sharing your Wrike AI Elite Mastery badge on LinkedIn shows more than familiarity with Wrike, it signals that you have the advanced skills needed to help drive a high-velocity, automated enterprise.

If you’re looking to sharpen your expertise, stand out in the market, and lead with AI in a more strategic way, this certification is a great next step.

Ready to get early access?

👉 Pre-enroll now 

🎉 Special community offer: The first 15 people to pre-enroll can use voucher code COMMUNITY100 at checkout for 100% off.

Don’t miss your chance to take the next step with Wrike AI Elite Mastery 💯