Frequently Asked Questions

In May 2025, Ymnig AI rebranded to Abundly AI.

The transition

Ymnig AI officially became Abundly AI in May 2025. This was a complete rebrand of the company while maintaining all the same services, team, and technology.

What this means

• Same company: All the expertise and people remain unchanged
• Same platform: Your AI agents and data continue to work seamlessly
• Same location: Still based in Stockholm, Sweden
• New identity: Now operating under the Abundly AI brand, more internationally recognizable and pronounceable but still aligned with our vision of creating abundance through AI technology

For existing customers

Nothing changes for your day-to-day experience. All accounts, agents, and services continue without interruption.

The rebrand was announced on May 28, 2025, and you can read more about it on our blog.

Abundly AI helps organizations build effective human-AI teams — where people and AI agents collaborate to boost productivity, insight, and decision-making.

Unlike basic automation tools, Abundly AI focuses on augmentation, not replacement. It enables your workforce to create, train, and work alongside AI agents that handle repetitive or data-intensive tasks, freeing humans to focus on strategy and creativity.

How Abundly AI works

Build AI agents easily: Create your first agent in minutes using plain language — no coding required. See agents

Train your team: Abundly AI helps your employees learn to design and manage their own AI-powered workflows. See courses.

Scale responsibly: From pilot projects to enterprise transformation, the platform supports both experimentation and organizational change. See transformation

Why it matters

Abundly AI turns AI from a technical challenge into a practical business capability. Organizations use it to streamline operations, enhance decision-making, and develop lasting in-house expertise in human-AI collaboration.

Learn more about how to build your first AI agent at https://app.abundly.ai

Getting started takes just a few minutes:

1. Sign up at app.abundly.ai/signup — free trial, no credit card required
2. Create an agent from scratch or clone one from our Use Cases
3. Configure and test — tell it what to do, enable capabilities, and refine until you're happy

For a complete walkthrough, see our Getting Started Guide.

There are two ways to pause an agent:

1. From Agent Management: Go to Agent Management → Agents tab, find your agent, and use the On/Off toggle in the Status column
2. From the agent itself: Go to Settings → Main Settings → Actions and toggle the agent off

While paused, the agent stops processing triggers, scheduled tasks, and incoming messages — but stays fully configured and ready to resume anytime.

For more details, see our Agent Management documentation.

Agent instructions are like a job description - they define what your agent should do, how it should behave, and provide necessary context. Here's how to write effective instructions.

Two Ways to Create Instructions

1. Direct editing - Click "Instructions" in the agent navbar to write and edit directly
2. Conversational configuration - Chat with the agent and ask it to update its own instructions based on the conversation

The Recommended Workflow

1. Start a conversation - Describe what you want in plain language, like onboarding a new team member
2. Agent asks for what it needs - It will request capabilities, documents, or clarification
3. Agent drafts instructions - Writes its own instructions from the conversation for your review
4. Review and tweak - Read the draft, make adjustments, and approve
5. Iterate over time - Return anytime to improve

Best Practices

Do:

• Be specific about the expected outcome
• Explain the "why" behind important rules
• Provide examples of good and bad behavior
• Define escalation paths for edge cases

Don't:

• Write novel-length instructions upfront
• Assume the agent will infer unstated requirements
• Include irrelevant context
• Forget to update instructions as needs change

The Intern Analogy

Think of setting up an agent like onboarding a new intern:

1. Explain the job and the goal
2. Provide context and resources
3. Set boundaries - what should they never do?
4. Start supervised and monitor their work
5. Gradually expand responsibility as trust is earned

Version Control

Agent instructions are automatically versioned, so you can:

• Track changes over time
• Revert to previous versions if needed
• Compare versions side-by-side

Learn More

• Agent Instructions Documentation
• Agent Design Best Practices
• Prompt Engineering Guide

As of now, we do not support external embedding of the agent chat widget, but it is on our roadmap.

Current alternatives

If you want external users to communicate with your agent today, you have these options:

Email integration

• Enable Send Email and Receive Email capabilities on your agent
• External users can interact with your agent via email
• The agent can receive emails and respond automatically

Custom API solution

• Use the agent's API for a custom integration
• Go to Agent Settings → API Access to get started
• Build your own interface that communicates with the agent

Future availability

We're actively working on chat widget embedding functionality. We'll notify customers when this feature becomes available.

Need help?

If you'd like to discuss alternative solutions for your specific use case, contact us at support@abundly.ai.

Yes! Multiple users can access the same agents — we even recommend it when collaborating on processes.

Access is controlled per agent with four levels: Admin (full control), Edit (modify agent), Use (chat only), or None (hidden). You can set a default for the whole team and override for specific users.

For details on organization roles, groups, and agent-to-agent access, see our Access Control documentation.

To create an agent: click New Agent in your dashboard and give it a name, or clone a pre-configured agent from our Use Cases. Then define what it should do, add capabilities (email, Slack, etc.), and test it. For detailed steps, see the Getting Started guide.

The AI model sometimes guesses the wrong language during auto-detection.

Solution: Go to your user settings and configure voice transcription to always use a specific language instead of auto-detect.

For more about voice input, text-to-speech, Walk & Talk mode, and phone calls, see our Voice Communication documentation.

There are two ways to give team members access:

1. Team-level: Go to Members in the main menu to add people to your organization
2. Agent-specific: Go to the agent's Settings → Team Access to control who can access that specific agent

Each agent has four access levels: Admin, Edit, Use, or None. You can set a default for all team members and override for specific users.

For details on roles, groups, and permissions, see our Access Control documentation.

Integrations connect your agent to external services like Slack, Google Drive, GitHub, etc. Toggle them on in the Capabilities section of your agent.

• Some work out of the box (e.g., web search, email) using platform-provided credentials
• Others require your authorization (e.g., Slack, Notion) via OAuth or API token
• On-demand: If your agent needs a capability it doesn't have, it will ask for it during the conversation

Credentials are stored securely and encrypted. For setup guides, authentication details, and extending with MCP servers, see our Integrations documentation.

The recommended approach is iterative refinement:

1. Chat with your agent and update instructions with more specific details
2. Be explicit about requirements (companies, time periods, formats, etc.)
3. Test and tweak — try 1-2 iterations before escalating

If you don't see improvement after a couple of attempts, contact support@abundly.ai with specific examples of the problems.

For tips on reducing costs and improving performance, see our Agent Optimization guide.

Abundly has comprehensive documentation available at docs.abundly.ai.

Documentation Sections

The documentation site covers:

• Introduction - Platform overview and getting started guides
• Features - Detailed information about agent capabilities, instructions, and communication
• Integrations - How to connect agents to external services
• Best Practices - Guidance on designing effective agents
• Use Cases - Real-world examples and applications
• Security - Enterprise security features and compliance
• API Reference - Technical API documentation
• Changelog - Platform updates and new features

Quick Links

• New to Abundly? Start with the Welcome page
• Want to build your first agent? See Getting Started
• Need help with integrations? Check the Integrations Overview

Video Tutorial

A 9-minute video walkthrough by Henrik Kniberg demonstrates the platform in action.

Still need help?

If you can't find what you're looking for in the documentation, contact us at support@abundly.ai.

To let your agent communicate on your Slack server, you need to

Step 1: Create a Slack app

Here is a simple quick-start guide. For more comprehensive info, see api.slack.com/docs.

The easiest way to create a Slack app is to use a manifest file as a template. Copy the template below,

{
   "display_information":{
      "name":"YOUR_APP_NAME",
      "description":"YOUR_APP_DESCRIPTION",
      "background_color":"#000000"
   },
   "features":{
      "app_home":{
         "messages_tab_enabled":true,
         "messages_tab_read_only_enabled":false
      },
      "bot_user":{
         "display_name":"YOUR_BOT_DISPLAY_NAME",
         "always_online":true
      }
   },
   "oauth_config":{
      "scopes":{
         "bot":[
            "app_mentions:read",
            "channels:read",
            "chat:write",
            "groups:read",
            "im:read",
            "users:read",
            "channels:history",
            "groups:history",
            "im:history",
            "channels:join",
            "im:write",
            "mpim:history"
         ]
      }
   },
   "settings":{
      "event_subscriptions":{
         "request_url":"https://agent-service-339911427090.europe-north2.run.app/api/slack/webhook",
         "bot_events":[
            "app_mention"
         ]
      },
      "org_deploy_enabled":false,
      "socket_mode_enabled":false,
      "token_rotation_enabled":false
   }
}

1. Visit api.slack.com/apps
2. Click "Create New App"
3. Choose "From a manifest"
4. Paste the above manifest
5. Replace YOUR_APP_NAME, YOUR_APP_DESCRIPTION, and YOUR_BOT_DISPLAY_NAME with your own info.
6. Click "Next" and "Create". Your app is now installed!
7. Copy the App ID.
8. Go to "OAuth & Permissions" and press the installation button under "OAuth Tokens". After doing so you should see "Bot User OAuth Token". Copy that value as well.

Understanding bot_events (Optional Customization)

The manifest above configures your agent to only respond when @-mentioned in channels. This prevents the agent from interfering in all conversations.

• app_mention - Agent responds when @-mentioned (✅ RECOMMENDED to prevent interference)

If you want different behavior, you can modify the bot_events section:

• Add message.im - Agent responds to every direct message (1-on-1 conversations)
• Add message.mpim - Agent responds to every message in multi-person DMs
• Add message.channels and message.groups - Agent responds to ALL messages in channels it's a member of (⚠️ WARNING: This can cause the agent to interfere in conversations)

For more information:

• The scopes define what the agent can do in Slack. See the full list of scopes.
• The bot_events define which events trigger the agent. See the full list of events.

Step 2. Configure the Slack capability in Abundly

Go to Settings -> Capabilities, enable Slack, and paste in the bot token and app ID.

Step 3. Add the App in Slack

Before you can use your agent, you need to add it to your Slack workspace:

1. In Slack, look at the bottom of your left sidebar for the Apps section
2. Click Add apps
3. Search for your app by name (the YOUR_APP_NAME you used in the manifest)
4. Click to add it
5. This enables you to chat directly with your agent and use it in channels

Step 4. Invite the Agent to Channels

Your agent must be invited to any channels where you want it to respond:

1. In Slack, open each channel where you want the agent to work
2. Type /invite @AgentName (where AgentName is the name of your bot)
3. The agent can now receive and respond to @-mentions in these channels

Troubleshooting: If the manifest approach didn't work

If you created your Slack app manually (without using the manifest), you may need to configure these settings:

Event Subscriptions:

1. In Slack app settings, click "Event Subscriptions"
2. Set "Request URL" to: https://agent-service-339911427090.europe-north2.run.app/api/slack/webhook
3. Ensure "Enable Events" is ON
4. Under "Subscribe to bot events", add app_mention

OAuth Scopes:

1. In Slack app settings, click "OAuth & Permissions"
2. Under "Bot Token Scopes", ensure these are present:
   • channels:read - To see public channels
   • groups:read - To see private channels
   • chat:write - To send messages
   • app_mentions:read - To receive mentions
3. If you added new scopes, reinstall the app and update the Bot Token in Abundly

Setting up Google Drive integration allows your agent to access and create Google Drive documents. Here's the complete setup process:

Step 1: Enable the capability

1. Go to your agent's Settings → Capabilities page
2. Find "Google Drive" in the capabilities list
3. Click "Create connection" and continue in the popup window

Step 2: Google approval flow

1. You'll be directed to Google's authorization page
2. Sign in to your Google account if prompted
3. Important: Accept this specific scope when prompted:
   • "See, edit, create, and delete only the specific Google Drive files you use with this app"
4. Click "Allow" to grant permissions

Step 3: Verify connection

After authorization, your Google Drive capability should show:

• Status: Connected
• Your connected token information
• Token owner details

Step 4: Start using Google Drive

Once connected, your agent can:

• Create documents: Ask your agent to create new Google Drive documents
• Access shared files: Add existing files using the document picker under "Docs"
• File management: Work with files you've explicitly shared with the agent

Important notes

• No service account needed: You should not need to use a service account for this integration
• Personal access only: The integration uses your personal Google account
• Selective access: The agent only has access to files you explicitly share or that it creates

Troubleshooting

If you encounter issues during setup:

1. Clear browser cache: Try clearing your browser cache and cookies
2. Different browser: Test the setup process in a different browser or incognito mode
3. Check permissions: Ensure you're using a Google account with appropriate permissions
4. Contact support: If you get stuck at any step, email support@abundly.ai with:
   • Which step you're stuck on
   • Screenshots of any error messages
   • Description of what you expected vs. what happened

What the agent can do once connected

• Create new Google Drive documents
• Read and edit documents you've shared
• Generate reports and save them to Drive
• Access files through the document picker interface

Abundly has limited Microsoft integration (Outlook and SharePoint available on request). We don't use Microsoft's LLM selection—we independently choose AI models based on performance for autonomous agent tasks. See our Integrations documentation for details.

Overview

The GitHub integration enables AI agents to interact with GitHub repositories for pull request management and repository monitoring. This capability streamlines development workflows by automating common GitHub tasks.

What the GitHub Integration Can Do

Pull Request Management:

• Merge pull requests with different merge methods (merge, squash, rebase)
• List and filter pull requests by status
• Get detailed pull request information including file changes and diffs

Repository Access:

• Browse repository files and directories
• Read file contents from any branch or commit
• List repository branches
• Track recent commits and changes

Monitoring:

• Monitor repository activity
• Track changes since specific commits or dates
• Access all repositories you have permissions for

GitHub Projects Support

The GitHub integration does not currently support GitHub Projects. It focuses on repository-level operations like pull requests, commits, and file management.

Common Use Cases

• Automatically merge approved pull requests
• Generate release notes from commit history
• Monitor repository activity and send notifications
• Support code review workflows
• Track changes for release management

Getting Started

1. Enable the Capability: Go to Settings → Capabilities and enable "GitHub"

2. Create a GitHub Token:

   • Visit GitHub Settings → Personal access tokens
   • Click "Generate new token (classic)"
   • Select these scopes: repo, read:org, and workflow (if needed)
   • Copy the token immediately

3. Configure:

   • Paste your token in the "token" field
   • Optionally specify repositories in "watchedRepositories" (e.g., yourorg/project1)
   • Click "Save github Credential"

Your data is encrypted (AES-256 at rest, TLS 1.2+ in transit) and stored in GDPR-compliant EU data centers. Credentials and API keys are never exposed to the LLM. We use multi-layer security including a separate security agent and code-level guardrails that can't be bypassed via prompts. All actions are logged for audit trails. For full details, see our Security Overview.

Abundly is built with enterprise-grade security, using a multi-layer "onion" model for comprehensive protection.

Multi-Layer Security Architecture

Key Security Features

• Security Agent - A dedicated background agent that reviews plans and can veto unsafe actions, protecting against prompt injection attacks
• Access Controls - Role-based permissions for users and agents
• Guardrails - Technical constraints enforced by the platform
• Audit Trails - Complete logging of all agent activities
• Credential Security - Encrypted storage of secrets and API keys
• Data Encryption - AES-256 at rest, TLS 1.2+ in transit

Compliance

Learn More

For detailed security documentation, see:

• Security Overview
• Access Control
• Guardrails
• Credentials
• Compliance

Questions?

For security-specific inquiries, contact us at support@abundly.ai.

our list of subprocessors

Yes, Tier 1 subscribers can purchase additional credits when they exceed their monthly allowance.

Available credit packages

Extra Credit Package for Tier 1:

• 2,000 additional credits for $15 USD
• Perfect for months when you need more than your base allocation
• Credits are added immediately to your account balance

When to consider extra credits

• You're approaching your monthly credit limit
• You have a temporary project requiring more agent usage
• You want to avoid upgrading to Tier 2 permanently
• You need flexibility for seasonal usage spikes

How to purchase

1. Log into your account at app.abundly.ai
2. Navigate to Billing in your account settings
3. Look for "Extra Credits" section
4. Select the 2,000 credit package ($15 USD)
5. Complete the purchase through the payment system
6. Credits are added immediately to your available balance

Cost comparison

• Tier 1 + Extra Credits: Base plan + $15 for 2,000 credits
• Tier 2 upgrade: Higher monthly cost but includes more base credits
• Best for: Occasional extra usage without permanent plan change

Questions?

If you need help purchasing extra credits or want to discuss upgrading your plan, contact us at support@abundly.ai.

Yes, you need an active subscription or sufficient credit balance to keep your agents running. If credits run out, agents pause automatically but no data is lost—they resume immediately once you add credits or choose a plan. See our Pricing documentation for full details.

You cannot top up credits while on trial—you must first activate a paid subscription. Go to Billing → Plans, choose a tier, and activate. You'll receive subscription credits immediately and can then purchase more in Billing → Credits.

For full details, see our Pricing documentation.

Here are the key ways to reduce your AI agent costs:

• Run less frequently – Schedule tasks hourly instead of every few minutes when possible
• Minimize context size – Only include essential information for the task
• Use agent documents wisely – Store reference info with "Summary" visibility so it's retrieved only when needed
• Simplify instructions – Keep them clear and concise; simpler often works better
• Choose a cheaper model – Switch from Claude Sonnet to a more economical option if your use case allows

For detailed optimization strategies, see our Agent Optimization Guide.

Yes! Go to your account settings, navigate to subscriptions, choose a plan, and complete the upgrade. Your subscription starts immediately, all data remains intact, and you can then purchase additional credits.

For full details on plans and pricing, see our Pricing documentation.

Go to Billing in your dashboard, then click the Credits tab to top up. Note: You must have an active paid subscription (credit top-up is disabled during trials). For full details, see our Pricing documentation.

Credit usage varies based on task complexity, context size, and the LLM model used. For example, a simple news check might use ~50 credits, while analyzing a meeting transcript and drafting follow-ups could use ~175 credits. For detailed examples and optimization tips, see our Agent Optimization Guide.

Abundly uses a credit-based pricing system—you pay for credits consumed when agents perform actions like sending emails, analyzing documents, or making API calls. Costs vary based on task complexity, from ~50 credits for simple tasks to ~5,000 for complex operations. All plans include unlimited agents and team members, with unused credits rolling over. For full details on plans and pricing, see our Agent Optimization Guide.

Abundly uses credit-based pricing with no per-seat costs:

• Unlimited agents and unlimited team members included
• You only pay for credits consumed when agents perform actions
• Three tiers: Small, Business, and Enterprise

View current pricing at app.abundly.ai/prices.

For details on how credits work, billing, and managing costs, see our Pricing documentation.

When your credits reach zero, your agents will automatically pause—but don't worry, all your configurations and data remain safe. Simply add more credits through your dashboard to resume service immediately. For full details on credits and pricing, see our Pricing documentation.

This is expected—credit top-up is disabled during trials, even if you've selected a paid plan. Once your trial ends, the top-up button becomes available. Contact support@abundly.ai if you urgently need more credits before trial ends.

For full details on credits and billing, see our Pricing documentation.

The 'Overloaded' error means the LLM provider (e.g., Anthropic/Claude) is experiencing high traffic. Wait 5-10 minutes and try again—it usually resolves on its own. You can also try switching to a different model temporarily.

For more troubleshooting tips, see our Troubleshooting guide.

Email support@abundly.ai for technical support. Include a clear description, steps tried, and any error messages. We typically respond within 24 hours on business days.

For common issues and self-service solutions, see our Troubleshooting guide.

Each new verification code invalidates all previous ones. Check your email for the most recent code (look at timestamps) and use that one. Codes expire after 30 minutes. Don't request multiple codes in a row—each request invalidates the previous one.

For more help, see our Troubleshooting guide.

Yes! You can select which language model powers each agent in Abundly.

To configure: Go to your Agent settings and choose from providers like Anthropic Claude, OpenAI GPT, or Google Gemini.

Quick tips:

• Use (no preference) to let Abundly auto-select the best model for you
• Choose model aliases (e.g., "Claude Sonnet Latest") for automatic upgrades
• Pick specific versions when you need full control and consistency

For the full list of available models, thinking token options, and use-case recommendations, see our Model Selection documentation.

Yes! As of June 2025, the Abundly team has implemented significant improvements that reduce credit consumption by 25-50% across all agent interactions.

What changed

• Reduced credit consumption for all agent activities (chat, autonomous tasks, scheduled operations)
• The exact reduction varies based on how interactions take place, but most users see 25-50% savings
• This improvement affects all types of agent usage regardless of context

When it took effect

• The changes have been live on the platform for several days as of June 26, 2025
• You do not need to take any action to benefit from these improvements
• All existing agents automatically benefit from the reduced credit consumption

User action required

None - This improvement is automatic and applies to all agents immediately. No configuration changes or updates are needed.

When planning to run large batch operations (processing hundreds or thousands of items), proper preparation can prevent interruptions and ensure successful completion.

Credit Requirements

Cost per item:

• Typically 25-50 credits per item processed
• Cost varies depending on whether "thinking" is enabled and complexity of processing
• For example: 3,500 items would require approximately 87,500-175,000 credits

Pre-operation Checklist

1. Calculate credit needs:

• Estimate total items × 25-50 credits per item
• Add a buffer for unexpected complexity or retries
• Check your current credit balance in your dashboard

2. Top up credits before starting:

• Purchase sufficient credits to complete the entire batch
• Avoid running out mid-operation, which could require restarting
• Better to over-estimate than to run short

3. Identify completed vs. incomplete items:

• If an operation is interrupted, you'll need to identify which items were not processed
• Consider organizing your batch data to track progress
• Plan how you'll resume or restart if needed

Why This Matters

• Avoid interrupted operations: Running out of credits mid-batch means stopping and restarting
• Save time: Completing operations in one go is more efficient
• Reduce complexity: Fewer manual interventions needed to track progress

Getting Help

If you need help estimating exact credit requirements based on your specific settings and data, contact us at support@abundly.ai. We can help you calculate more precise estimates for your use case.

Chat conversations are stored in our MongoDB database hosted in Stockholm, Sweden (EU). You have full control—delete a conversation anytime and it's permanently removed.

For details on data residency, encryption, and compliance, see our Infrastructure documentation.

It depends on the source. Agent documents (created in Abundly) are stored in EU data centers in Stockholm. External documents (Google Drive, SharePoint, etc.) remain on their original provider's servers—the agent accesses them through your permission but doesn't copy them.

For more details, see our Documents documentation.

All customer data is stored in EU data centers in Stockholm, Sweden (database on AWS eu-north-1, services on GCP europe-north2). Static files are served via CDN. Data does not leave the EU.

For full details on infrastructure, encryption, and compliance, see our Infrastructure documentation.

Absolutely! You'll be very positively surprised. The concepts, strategies, and workflows you learn in our agent courses are valuable regardless of the specific AI platform you're using. While the implementation details may differ, the foundational knowledge about agent design, automation patterns, and AI integration principles applies broadly.