Changelog

Hello!

It's update time ! We are thrilled to share the latest improvements deployed on Swiftask this August 4, 2026. Our goal is to make your everyday work even simpler and more comfortable.

Here is a breakdown of what this update changes for you:

✍️ A modern text editor for your Branding Kit

• What’s changing: Say goodbye to plain, boring text! You can now format your Branding Kit texts just like a real document: add bold, italics, create bulleted lists, or insert line breaks.

• What it's for: The Branding Kit helps you define your company's identity (your tone of voice, key messages, words to use or avoid) so that your AI agents always speak with your brand's voice. With this new editor, writing and structuring these guidelines is a breeze, keeping them clear and easy to read for your teams.

• What it brings to your daily life: Pure writing comfort. Your editorial guidelines are clean and well-structured, and your agents continue to follow them to perfection.

• How to get started: Simply head over to your Workspace Settings → Branding Kit to start formatting your texts.

📊 Clearer and more readable Knowledge Bases (Knowledge Tables & Sources)

• What’s changing: Knowledge Tables (those structured data tables, very similar to CSV files embedded in Swiftask) and the detail pages of your information sources (files, websites, SharePoint...) are getting a major facelift with a completely redesigned layout.

• What it's for: These tools allow you to feed your agents with precise data (product catalogs, contact lists, FAQs...). Thanks to this visual redesign, navigating through this data and checking at a glance which information is powering your agents' responses is much easier.

• What it brings to your daily life: Less eye strain and total control over your agents' "memory". You instantly understand where the information comes from, and you can manage your data tables with much more fluidity.

💻 Your desktop app updates all by itself!

• What’s changing: The Swiftask desktop application now supports automatic updates.

• What it's for: No more downloading new versions manually from the website or wondering if you're running the latest build. Swiftask takes care of everything in the background.

• What it brings to your daily life: The peace of mind of always enjoying the very latest features, security patches, and stability improvements—without lifting a finger.

• How to get started: You don't have to do a thing! Just let the app do its magic next time you launch it.

🛠️ Stronger connections and smoother exchanges (Outlook, files, and chat)

• What’s changing: Our team has strengthened several elements behind the scenes:

  • The Outlook connector is now much more robust to prevent unexpected disconnections.

  • File processing by sub-agents (the specialized components working in the background to handle complex tasks) is now much more reliable.

  • The chat space with agents has been optimized to be more responsive.

• What it's for: These technical fixes are designed to make using Swiftask completely smooth and seamless.

• What it brings to your daily life:

  • Peace of mind: Your automations linked to your Outlook emails won't stop working due to an expired session. No more repetitive reconnection requests!

  • Efficiency: When you send documents to your agents, analysis is smoother, with a much lower risk of freezes or failures.

  • Speed: Your chat exchanges are more responsive and stable, even during long discussions.

💡 In short, what this update changes for you:

1. More comfort: Simplified brand guidelines editing and much more readable data tables (similar to CSV files).

2. More peace of mind: A desktop app that updates itself and an Outlook connection that stays active.

3. More fluidity: Faster, more reliable agents to analyze your documents and reply to your messages.

Hello,

We would like to follow up with you regarding the slowdown experienced on the Swiftask platform on July 23, 2026, between 2:00 PM and 9:00 PM (UTC), which affected all our users.

What happened

After a thorough investigation by our technical teams, we identified the source of the issue: in certain configurations within the multi-agent module, an agent and its sub-agents could trigger a loop by calling each other repeatedly. These repetitive executions gradually saturated our database connections, which slowed down the entire platform.

We want to reassure you: no data was compromised, lost, or exposed. This incident was strictly performance-related.

What we have done

As soon as the cause was identified, our teams worked to deploy fixes, which were put into production on July 23 at 9:00 PM (UTC). These improvements include:

• Implementing an anti-loop safeguard, which automatically detects and interrupts recursive calls between an agent and its sub-agents;

• Optimizing our caching system to reduce the load on our database;

• Patching our parallel processing management for better load distribution.

What we continue to do

We are actively continuing our work to strengthen the platform's reliability over the long term:

• At the application level: reinforcing early detection mechanisms for agent loops;

• At the infrastructure level: reinforcing our capacities and enhancing monitoring of database connections to detect such situations before they impact your experience.

We are fully committed to ensuring a stable and high-performance service, and we will keep you updated on the progress of these improvements.

Thank you for your trust and patience.

Sincerely,

The Swiftask Team

Hello,

We wanted to follow up with you regarding the recent incidents and slowdowns you may have experienced on the Swiftask platform.

What happened

After a thorough investigation by our technical teams, we identified that these incidents were caused by infrastructure issues triggered during peak load periods. These peaks are directly tied to the strong increase in platform adoption over the past few weeks, which put pressure on certain components of our architecture: application services, database, and computing resources.

What we've done

As soon as we detected these issues, our teams mobilized to diagnose the root cause and deploy fixes, which went into production last night. These improvements include:

• Optimization of the agent engine deployment to prevent interruptions during execution

• Increased database resources to better handle read/write load

• Expanded server capacity across our infrastructure after coordinating with Scaleway to increase our quotas

What we're continuing to do

We're actively pursuing optimization efforts at multiple levels:

• Application level: load management, processing optimization, and implementation of resilience mechanisms

• LLM support optimization: improving resilience for Scaleway and other LLM providers

• Infrastructure level: auto-scaling, enhanced monitoring, and resource management

Additionally, to ensure long-term platform reliability and performance, we've engaged an external infrastructure specialist to conduct a comprehensive audit of our systems and guide us through implementing improvements across the entire Swiftask platform.

We're committed to delivering a stable and high-performing service, and we'll keep you updated on our progress.

Thank you for your trust and patience.

Best regards,

The Swiftask team

Anthropic just shipped two new Claude models. Both are live in Swiftask right now, on every plan, at no extra cost.

Which one to pick?

Both share the same specs:

• 992,000 token context window, analyze entire codebases or 500-page documents in one shot

• 120,000 token output limit, long-form outputs without truncation

• Available on Pro, Team Starter, Team Growth, and Custom plans

Why upgrade from Sonnet 4.6 to Sonnet 5?

Sonnet 5 replaces Sonnet 4.6 as the recommended default for most tasks. Same price bracket, stronger reasoning, larger context (992K vs previous limits). If you're using Sonnet 4.6 today, you can freely switch to Sonnet 5 if you want it, that is a one-click win.

Sonnet 4.6 stays available: no forced migration, no breaking changes.

How to switch

In Chat:

1. Open Chat → click the model selector at the top of the input

2. Under "Anthropic - Claude", pick Sonnet 5 or Fable 5

3. Start typing

In Agents:

1. Open your agent → Agent Configuration → Model selection

2. Pick the new model → Save

As workspace default: Workspace administration → Settings → Advanced → Default Chat AI → select the model → Update.

How to test in 2 minutes

Sonnet 5: Drop a 50-page PDF and ask: "Extract the 10 most important insights with page references." Compare speed and accuracy vs. your current default.

Fable 5: Give it a complex reasoning task: "Analyze these three business scenarios and recommend the best one with tradeoffs." Compare output depth vs. Sonnet 5.

Our recommendation

Use Sonnet 5 for 80% of your workflows: chat, agents, automations. Reserve Fable 5 for tasks where output quality justifies the cost: legal analysis, strategic planning, technical audits.

Learn more about choosing the right model and credit consumption.

Open Chat now and try Sonnet 5 on your next task.

This thursday, join our webinar on building a fleet of cold-emailing agents to save time on your prospecting.

→ https://tinyurl.com/3hvr7x5f

We've made it easier to work together. You can now share any chat session with teammates or with anyone outside your workspace. Whether you need feedback from a colleague or want to show a completed analysis to a client, sharing is one click away.

Share conversations with teammates

Invite colleagues to view or edit any chat session. Each person gets the access they need: view-only to review your work, or read and write to jump in and add their own messages. Find it by clicking the Share button at the top of any conversation.

• Two permission levels: "Read only" (view only) or "Read & write" (view, reply, and edit own messages)

• Search teammates by name or email

• Manage access anytime by reopening the share dialog

Share conversations publicly via link

Need to share a chat with someone outside your workspace? Generate a unique public link anyone can open without logging in. Perfect for sharing analysis results with clients, getting external feedback, or archiving conversations for reference.

• Anyone with the link can view the conversation in read-only mode

• Public link format: https://www.app.swiftask.ai/public/chat/[slug]

• Revoke access anytime by disabling the public link

• Recipients see only the conversation thread — no sidebar, no other chats

  

Find shared conversations easily

A new "Shared chats" collection is now available in your chat session list, located at the bottom of your collections. It groups every conversation shared with you or accessible via public links. No more hunting through your chat history.

How to test it

1. Open any conversation and click the Share button (top right of the chat header)

   

2. In the "Users" tab: search for a colleague and assign "Read only" or "Read & write"

3. In the "Public" tab: toggle "Anyone with the link" to generate a shareable URL, then copy it

4. Send the public link to someone outside your workspace, they can open it immediately without signing up

5. Check your chat session list and go to the "Shared chat" collection at the bottom to see all your shared conversations.

Available on all Swiftask plans. Open any conversation and hit Share to try it.

Tomorrow, join our webinar on building a fleet of cold-emailing agents to save time on your prospecting.

→ https://tinyurl.com/3hvr7x5f

Until now, tracking your automatic knowledge syncs meant opening each source one by one. No overview. No central control. No easy way to know when your next sync would run.

Today, we're fixing that.

✨ New: Knowledge auto sync menu

A dedicated dashboard to view, monitor, and control every automatic sync across your knowledge sources, in one click.

Find it in Knowledge → Auto sync (left sidebar).

What you get:

• Full overview of every active sync: source, category, schedule, next run, and status

• Real-time status indicators: instantly see what's ACTIVE or PAUSED

• One-click actions: pause, resume, or delete any sync without leaving the dashboard

• Immediate propagation: changes on your synced sources reflect in your agents right away

• Flexible schedules: hourly, daily, weekly, monthly, with custom intervals

• Supported sources: Google Drive, SharePoint, Dropbox, websites, and document files

• Available on all plans: Pro, Team Starter, Team Growth, and Custom

💡 Why it matters

Your agents are only as good as the knowledge they have access to. When your docs, drives, and pricing pages update, your agents need to know instantly.

The Auto sync menu gives you the control layer that was missing: less time babysitting syncs, more time letting your AI work on fresh data.

🧪 Try it now

1. Open Knowledge in the left sidebar

2. Click Auto sync

3. Review your active syncs and their next scheduled runs

4. Pause, resume, or delete any sync in one click

👉 Open Knowledge auto sync

One dashboard. Every sync. Full control.

Join our webinar on building a fleet of cold-emailing agents to save time on your prospecting.

→ https://tinyurl.com/3hvr7x5f

Your agent fleet is growing. Some agents run every day, others only once a quarter, and some you no longer use at all. You can now archive inactive agents to keep your workspace clean, and restore them in one click whenever you need them back.

Archive and restore in seconds

• Archive any agent from the three-dot menu (⋮) on the agent card

  

• Access all archived agents in the new "Archived" tab in the Agents sidebar

• Restore an archived agent with one click; all its skills, knowledge sources, and settings come back untouched

• Delete permanently from the archived view when you're sure you don't need it anymore

Find it: Agents → [Agent card] → ⋮ → Archive Restore it: Agents → Archived tab → ⋮ → Restore

What happens when you archive an agent

• The agent disappears from all agent lists and search results, and moves to the Archived tab

• Existing conversations remain fully accessible in your chat history, nothing is lost

• Automation triggers stop running (scheduled tasks, email triggers, etc.) until the agent is restored

• Shared access is paused: users you shared the agent with can no longer access it

• When you restore the agent, sharing is automatically re-enabled for all previous users, no need to re-share manually

How to test it

1. Open Agents in the sidebar

2. Pick any agent you own

3. Click the three-dot menu (⋮) → Archive

4. Confirm the agent is gone from your main agent list

5. Scroll to the new Archived tab at the bottom of the sidebar

6. Click ⋮ on the archived agent → Restore

7. The agent is back in your main list, fully usable, with all sharing restored

Available on: All plans (Pro, Team Starter, Team Growth, Custom)

📖 Learn more about managing agents →

Join our webinar on building a fleet of cold-emailing agents to save time on your prospecting.

→ https://tinyurl.com/3hvr7x5f

GLM-5.2 was already available on Swiftask. We've now added a second version hosted on Scaleway, so you can use the same reasoning power with your data kept in Europe.

Same model, sovereign hosting

You now have two ways to use GLM-5.2 in Swiftask:

• GLM-5.2 (original)

• Scaleway - GLM-5.2 (new, hosted in Europe with Shield 3 protection)

Same capabilities, same reasoning quality. The difference is where your data is processed.

• Cost: 1.2 per word

• Hosting: Scaleway, in Europe

• Data protection: Shield 3, your data stays in Europe and is never used to train the model

• Availability: All plans, no extra cost

• Access: Already visible in the model selector, no configuration needed

When to use the Scaleway version

Pick Scaleway - GLM-5.2 when:

• You handle sensitive or regulated data (finance, healthcare, public sector)

• You need European data residency for compliance (GDPR, SecNumCloud)

• You want to keep your data flow within EU infrastructure

For everything else, the original GLM-5.2 works just as well.

How to use it

In Chat:

1. Open Chat

2. Click the model selector at the top left

3. Choose Scaleway - GLM-5.2

In Agents: Go to Agents → Configuration → Model Selection and assign Scaleway - GLM-5.2 to your agent.

Open Chat, pick Scaleway - GLM-5.2, put it to work on your longest, most complex task, and keep your data in Europe.

Join our webinar on building a fleet of cold-emailing agents to save time on your prospecting.

→ https://tinyurl.com/3hvr7x5f