Changelog

Three focused improvements that cut through the noise: better visibility into what your agents are doing, smarter knowledge organization, and faster agent discovery. Everything you need to work with confidence.

Watch your agent work in real-time

Interpretability in Chat shows you exactly what your agent is doing as it happens. See the workflow, skill chains, API calls, and how inputs flow through each step. No more waiting for the agent to finish, you watch the progress unfold.

• View agent workflow and skill execution step-by-step

• See how inputs are processed and used

• Watch API calls and data flow in real-time

• Understand what your agent is doing at each moment

This gives you better visibility and confidence in your agents' decisions, without waiting for completion.

Add shared knowledge to your projects

You can now attach knowledge sources directly to projects. Every chat within that project automatically has access to the same centralized knowledge, giving everyone context without duplication.

• Attach knowledge sources to projects

• All project chats access shared knowledge automatically

• Better context for team collaboration

• No need to manually add knowledge to each chat

Find it at: Project settings → Knowledge → Add knowledge sources

Pin your best agents for the whole team

Workspace admins can now pin agents to the Chat home screen. Your team sees your most-used agents right away : no searching, no hunting.

• Pin agents to Chat home for easy discovery

• Help your team find the right agent instantly

• Organize your enterprise agent shelf

• Available to all workspace members

Find it at: Admin settings → Pin agents to Chat home

Improvements

LLM configuration now has its own dedicated menu. No more digging through mixed settings, everything related to your model is in one place.

Find it at: Agent configuration → LLM settings

Get started now

Start by pinning your most-used agents, then explore the Chat selector to see how fast you can switch between AI models. Watch the interpretability panel next time you run a complex task, you'll see exactly how your agent thinks.

We've shipped five powerful tools to help you scale AI safely. Whether you're managing a fleet of agents across your organization, keeping your brand consistent, or making sure nothing breaks in production—this update gives you the control you need.

Your brand identity, now everywhere

Branding kit lets you define your brand once and apply it automatically to every agent. Upload your logo, colors, fonts, tone guidelines, and brand rules to your workspace, then attach or remove them per agent with a single click. When you update a brand resource, it updates everywhere—no manual reconfiguration needed.

• Create brand resources once at the workspace level (logos, colors, fonts, voice guidelines, photos, rules)

• Attach or remove resources per agent instantly

• Changes propagate to agent system prompts within 5 minutes

• Requires WORKSPACE_MANAGE_BRANDING_KIT permission

• Available on all plans

Find it at: Workspace settings → Brand identity

How to test it: Create a workspace branding resource (e.g., add your company logo), attach it to an agent, and ask the agent to create a slide or document. You'll see your brand applied automatically.

See exactly what your team is doing

Admin workspace – 360° user usage view gives you complete visibility into every team member's activity, agents, and credit consumption in one place. No more hunting through logs or asking "who created that agent?" or "which LLMs is this person using?"—it's all there.

For each member, you can instantly see:

• Join date, last login, credit limit, group memberships, and all permissions

• Every agent they've created and the LLMs they're using

• Real-time credit consumption and activity history

• Associated projects and roles

Find it at: Workspace settings → Members → click the eye icon on any member

Availability: Team Starter, Team Growth, and Tailored/Enterprise plans (admins only)

How to test it: Go to your Members section and click the eye icon next to a team member's name. Explore their profile, agent list, and usage data.

Stop agents before they drain your budget

Agent credit monitoring lets you set a custom credit threshold for each agent and get notified in-app when usage approaches that limit. Perfect for production agents, public widgets, or any agent you want to keep under control.

• Set any credit limit per agent

• Get in-app alerts as usage approaches your threshold

• Monitor each agent independently

• Available on all plans

How to test it: Open an agent, go to its monitoring settings, set a credit limit, and simulate usage to trigger an alert.

Lock your agents so they don't break

Lock agent is a one-click way to protect production agents from accidental changes. When locked, only owners and admins can modify the agent's prompt, skills, data sources, sharing, or any other configuration—but everyone can still use the agent in chat.

• Toggle lock on or off at the top of any agent page

• Only owners and admins can unlock

• All settings are protected: prompt, skills, data sources, sharing, duplication, and more

• No impact on usage, credits, or performance

• Available on all plans

Find it at: Agent page → top section → "Lock agent" toggle (next to Share and "Use this agent")

How to test it: Open an agent you own, turn on the Lock agent toggle, then try to edit it as a regular user—you'll see a message asking you to contact the owner.

Your team's credentials stay with your team

Require user's own account is a toggle on external agent skills that ensures each person uses their own Gmail, Slack, Google Drive, or calendar account instead of sharing yours. No more credential sharing, full audit trails, and complete privacy.

When you enable this toggle:

• Each user authenticates with their own account the first time they use the agent

• Personal data (emails, files, calendar events) stays on their account

• Every action is traceable to the person who performed it

• Users can only access what their own account permissions allow

Find it at: Agent → Skills → Edit any external skill → "Require user's own account" toggle

Works with: Gmail, Google Drive, Slack, Outlook, Microsoft Teams, Google Calendar, Outlook Calendar, and all external service integrations. Available on all plans.

How to test it: Create an agent with a Gmail skill, enable the toggle, share it with a colleague, and have them authenticate with their own Gmail account. Send a test email through the agent and verify it came from their account, not yours.

What's next

These five features work together to give you governance, visibility, and control at scale:

• Use branding kit to keep all agents consistent

• Use admin visibility to monitor who's building what

• Use credit alerts to prevent runaway costs

• Use agent lock to protect production configurations

• Use per-user auth to maintain security and accountability

All available on all plans. No surprises, no lock-in.

Tips & best practices

For brand consistency: Start with a core set of resources (1 logo, 2–3 colors, 1 voice description, 1 key guideline). You can always add more. Remember to name resources clearly ("Main logo," "Brand blue #0066CC") so they're easy to find.

For admin oversight: Review your members list quarterly. Check credit usage weekly to spot unusual patterns. Keep at least two admins to prevent lockout.

For production safety: Lock agents after major updates. Communicate with your team that locked agents require owner approval for changes. Unlock temporarily when broad edits are needed, then re-lock when stable.

For security: Always require user's own account when sharing agents with external integrations. This prevents credential sprawl and keeps your audit trail clean.

Known details

• Branding kit changes to agent system prompts are cached for up to 5 minutes. After attaching or removing a resource, allow this delay before fully testing the agent's response.

• The "Require user's own account" toggle applies uniformly to all recipients. If you need different behaviors, create separate agent versions.

• Agent locking can be triggered programmatically via the setBotLocked mutation (API). Only owners and admins should call it.

• Admin 360° view is available only on Team plans and above; Free and Pro plan workspaces have basic member management only.

Ready to lock down your governance? Start with branding kit to unify your agents, then use admin visibility to track activity, credit alerts to manage costs, agent lock to protect production, and per-user auth to keep security tight. Your fleet is now under control.

Your SSO credentials now work on mobile.

We're excited to announce that enterprise teams can now authenticate using SSO directly from the Swiftask mobile app. If your organization uses Single Sign-On (SAML via Azure AD, Okta, or other identity providers), you can now sign in from iOS with your corporate credentials—no workarounds, no separate passwords.

SSO login now available on iOS

Enterprise users with SSO-enabled workspaces can authenticate using their organization's identity provider directly from the mobile app. The mobile app now respects your workspace's SSO configuration, giving you the same seamless, secure login experience you have on the web.

• Supported identity providers: Azure AD, Okta, and any SAML 2.0-compliant identity provider

• Seamless integration: Uses your existing workspace SSO setup—no additional configuration needed

• Available on: All Swiftask plans

• Find it: Login screen → Sign in with SSO option (appears automatically if your workspace has SSO enabled)

Smoother, faster authentication flow

We've redesigned the entire login experience to be quicker and more intuitive. Whether you're signing in with email, OAuth (Google/Microsoft), or SSO, the process is now streamlined for speed and reliability.

Bug fixes and performance improvements

• Improved stability and performance across the mobile app

• Fixed minor issues affecting login reliability

• Enhanced overall app responsiveness on iOS

How to get started

1. Update to iOS v1.0.24 from the App Store

2. Open Swiftask on your iPhone

3. At the login screen, if your workspace has SSO enabled, you'll see a "Sign in with SSO" option

4. Tap it and authenticate with your corporate credentials

5. You're in — no additional setup required

For workspace admins

SSO configuration is managed at the workspace level. If your organization isn't using SSO yet and you'd like to enable it, visit Workspace administration → SAML Configuration to get started. Once configured, all team members can authenticate via SSO on both web and mobile.

For detailed setup instructions, see the SSO/SAML documentation.

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

Good news: analyzing your Excel, CSV, or JSON files now costs a lot less. We've optimized the Python skill to use fewer credits while keeping all its power. More analyses, fewer expenses.

Your Analyses Cost Less

Every time you upload a file and request an analysis, the AI uses fewer credits. It's straightforward: you get more analyses with the same budget.

• Reduced consumption across all data analyses

• No limits: analyze as many files as you want

• Same results: charts, stats, insights — nothing changes except the price

Generate Excel Files Directly

You can now ask the AI to create Excel files right away — perfect for exporting analyses, building reports, or sharing processed data.

• Just say: "Create an Excel file with a summary by region and a chart"

• Grab the file instantly in the chat with a download link

• No more copy-pasting or manual data wrangling

Errors Get Fixed Faster

If something goes wrong, the AI fixes the issue without regenerating the whole code. Result: fewer wasted credits, more speed.

How to Use It

1. Open a chat with an agent

2. Click the + icon to add the Python: Code + Upload + Visualization skill

3. Upload your file (Excel, CSV, JSON, etc.)

4. Request an analysis: "Analyze this file and give me the key figures"

5. Or ask for an export: "Create an Excel with the summary by category"

The generated file shows up right away — download it in one click.

Common Use Cases

• Analyze sales data → get a chart + an Excel with totals by region

• Process a contact list → generate a cleaned and sorted Excel file

• Summarize results → create a report with tables and charts

• Compare periods → get visualizations and ready-to-share export files

Availability: All plans (Pro, Team Starter, Team Growth, Custom)

Tip: With this optimization, now's the perfect time to automate your regular data analyses. Save time and cut costs on credits.

We're excited to announce two powerful new tools for working with PDFs: a dedicated PDF Search & Replace skill and a ready-to-use Brad - PDF anonymization agent template. Together, they make it easy to find and replace text while protecting sensitive data.

PDF Search & Replace skill

Find and replace text in PDF files while keeping your original formatting intact. Whether you're updating placeholders, correcting information, or preparing documents for distribution, this skill handles the work automatically.

Provide the PDF URL, specify the strings to search for and their replacements, and the processed PDF is uploaded to cloud storage with a download link returned instantly.

• Available on all plans

• No file size limits

• Processed PDFs uploaded to S3 with instant download links

• Preserves original PDF formatting during replacements

Where to find it: Skills → Search "pdf" → PDF Search & Replace

How to test it: Add the skill to any agent, then ask it to search and replace text in a sample PDF. For example: "Search for [PLACEHOLDER] in this PDF and replace it with [ACTUAL_VALUE], then give me the download link."

Brad - PDF anonymization agent template

Protect sensitive information automatically. Brad is a pre-configured agent template that detects and removes all personally identifiable information (PII) from PDF documents in seconds.

Upload a PDF containing names, contact details, financial information, or any other sensitive data. Brad analyzes the document, identifies all PII, removes it, and returns a clean, anonymized PDF ready to share or archive.

• Detects all types of PII (names, emails, phone numbers, addresses, financial data, and more)

• Available on all plans

• No file size limits

• Returns anonymized PDF as a downloadable file

• Ready-to-use template — no configuration needed

Where to find it: Agents → Create Agent → From Template → Brad - PDF Anonymization

How to test it:

1. Go to Agents and click "Create Agent"

2. Select "From Template"

3. Search for and select "Brad - PDF Anonymization"

4. Choose "Clone and test" to use it immediately

5. Upload a PDF with sensitive information

6. Brad will process it and return the anonymized version as a download

Why this matters

These tools solve a real problem: managing sensitive documents at scale. Whether you're preparing contracts for external review, sharing reports while protecting privacy, or automating document workflows, you now have enterprise-grade PDF handling built into your agent fleet.

Available now on all Swiftask plans. No additional setup or configuration required.

Ready to try it? Create a new agent from the Brad template or add the PDF Search & Replace skill to your existing agents. Both are available immediately in your workspace.

Looking for the perfect model for your AI agents? We've just added two new Claude models via AWS Bedrock: a champion of value for money, and a beast of raw power.

Claude Sonnet 4.6 — Advanced intelligence without compromising your costs

You get near-Opus power at the same price as Sonnet 4.5. Perfect for agents that demand serious reasoning without breaking the bank.

• Pricing: 3/3 /3/15 per million tokens (input / output)

• Capabilities: Extended thinking, web automation (computer use), image analysis, up to 1M token context

• Ideal for: Complex autonomous agents, full code generation, strategic analysis of large documents

• Key benefit: Cut your AI infrastructure costs by 40% compared to Opus, without sacrificing quality

Claude Opus 4.6 — When you need the best

Anthropic's most powerful model. Use it when reasoning quality is non-negotiable and you're tackling critical or highly complex tasks.

• Capabilities: Maximum reasoning, ultra-precise instruction following, handling complex edge cases

• Ideal for: Critical tasks, multi-step problems, analyses where precision makes the difference

• Key benefit: Zero compromise on quality — Anthropic's most capable model

How to use these models

In your agents:

1. Go to Agents → Select your agent → Edit

2. Open the Objectives & Instructions section (or Model selection)

3. Click the LLM Model dropdown

4. Search for and select Bedrock – Claude Sonnet 4.6 or Bedrock – Claude Opus 4.6

5. Save

In Chat:

1. Open Chat

2. Click the model selector (top left of the input field)

3. Search for the model by name

4. Start chatting

Availability

• ✅ Available on all Swiftask plans (Pro, Team Starter, Team Growth, Tailored)

• ✅ No upgrade required

• ✅ All your existing agents, skills, and automations work immediately

Our advice

Start with Sonnet 4.6 for your standard agent workflows — it's the best balance of power and cost. Reserve Opus 4.6 for your critical tasks where maximum reasoning precision makes the difference. This way, you optimize your budget while keeping the power where it matters most.

How to test

Claude Sonnet 4.6:

• Create an agent with a complex task: code analysis, strategic synthesis, or architecture generation

• Example: "Analyze this full financial report and extract the 10 most important insights"

• Test multimodal capabilities: Upload an image and request a detailed analysis

Claude Opus 4.6:

• Use it on a critical task where reasoning quality is essential

• Example: "Identify all edge cases and error scenarios in this process flow"

• Compare results with Sonnet 4.6 to see the difference in precision

Ready to deploy your agents with the best models? Open your agents now, select Claude Sonnet 4.6 or Opus 4.6, and test the power. 🎯

We've added a powerful new way to keep data private and accountability clear when sharing agents with your team. Meet the "Require user's own account" toggle—a simple but important security feature for external integrations.

Agents now respect user credentials for external services

When you share an agent that uses external integrations (Gmail, Google Drive, Slack, Outlook, Microsoft Teams, or any calendar service), you can now require users to authenticate with their own accounts instead of using yours.

Here's what changes:

• Each user's data stays on their account – When someone uses a Gmail skill, they use their Gmail account, not yours. Their emails, files, and actions are completely separate.

• Clear accountability – Every action is traceable to the person who performed it, not to the agent owner.

• Automatic permission respect – Users can only access what their own account permissions allow. No surprises, no over-sharing.

• One-time setup – Users configure their account once when they first access the agent, then everything works seamlessly.

How to set it up

1. Navigate to Agents → select your agent → click the edit icon (✏️)

2. Go to Skills in the left panel

3. Click Add a skill or edit an existing external skill (Gmail, Google Drive, Slack, Outlook, Calendar, etc.)

4. Fill in the skill configuration form

5. At the bottom of the form, toggle "Require user's own account" on

6. Save and share your agent normally

That's it. When recipients access the agent, they'll see a "Configuration required" banner and can authenticate with one click.

Available on: All Swiftask plans
Works with: Gmail, Google Drive, Slack, Outlook, Microsoft Teams, Google Calendar, Outlook Calendar, and all external service integrations
Does not apply to: Internal Swiftask skills (only external integrations)

What your users will see

1. They open a shared agent that has this toggle enabled

2. A blue "Configuration required" banner appears

3. They click "Configure" and authenticate with their own account

4. They're done—the agent now uses their credentials for all external actions

Why this matters

• Privacy first – Personal data (emails, files, calendar events) stays on the user's account

• Compliance ready – Perfect for regulated industries where audit trails and individual accountability are essential

• No credential sharing – You never have to share your Gmail, Slack, or calendar access with teammates

• Respects existing access – If someone doesn't have permission to a resource in their own account, they can't access it through the agent either

Test it now

1. Create or edit an agent with an external skill (try Gmail or Google Drive)

2. Enable the "Require user's own account" toggle

3. Share the agent with a test user (different account)

4. Log in as the test user and open the shared agent

5. Look for the "Configuration required" banner

6. Click "Configure" and authenticate

7. Send a test message that triggers the skill

8. Verify the action used the test user's credentials, not yours

Ready to share securely? Open any agent, add an external skill, enable the toggle, and share with confidence. Your team's data stays where it belongs—with them. 🔒

We've added agent locking so you can protect your production agents from accidental changes. Once locked, only owners and admins can modify agent settings—everyone else can still use the agent, but they'll see a clear message if they try to edit it.

Lock agent in production

You can now lock any agent you own or administer to prevent unauthorized changes. Perfect for production agents, shared templates, or any agent you want to keep stable. When locked, all configuration changes are blocked for regular users—they'll see a helpful error message asking them to contact the owner or admin.

• Turn the lock on or off with a single toggle

• Only owners and admins can lock or unlock agents

• Locked agents remain fully usable in chat for everyone with access

• All agent settings are protected: prompt, skills, data sources, sharing, duplication, and more

• No impact on usage, credits, or performance

Find it: Agent page → top section → "Lock agent" toggle (next to Share and "Use this agent" buttons)

Testing the feature:

1. Open any agent you own or administer

2. Click the "Lock agent" toggle at the top of the page (it will turn on and stay highlighted)

3. Try to edit the agent settings as a regular user—you'll see a message asking to contact the owner/admin

4. As owner/admin, click the toggle again to unlock and make changes