Plug and AI

Description Features Permissions Security & Compliance

Plug and AI brings the world's best AI models directly into Slack. Your entire team gets instant access to ChatGPT, Claude, Gemini, and 300+ models through simple @-mentions—without managing individual subscriptions.Features:
- Multi-model access: Switch between GPT-5, Claude, Gemini instantly
- Image understanding & generation: Analyze screenshots, generate visuals
- Thread-aware conversations: AI maintains context in Slack threads
- Unified workspace billing: One shared credit pool, no per-seat feesProblems It Solves:
:money_with_wings: The $20/Seat Problem: Most employees use AI occasionally, yet subscriptions charge $20/user/month regardless. A team of 10 pays $200/month. With Plug and AI, the same team pays ~$35. 80%+ savings.
:lock: Vendor Lock-in: Don't get stuck with yesterday's best model. Switch from GPT to Claude to Gemini mid-conversation—always use the newest, best model for your task.
:clipboard: Billing Chaos: One workspace balance, one Stripe checkout, one invoice. No more tracking multiple subscriptions or chasing reimbursements.Get started:
- Click "Add to Slack" → receive $1.00 free credit instantly
- Talk to @AI on any channel, ask questions like:
@ai What's the best approach for......
@ai gpt-5.1 Analyze this chart [attach screenshot]Choose models:
/ai set premium — highest quality (GPT-5.1, Gemini 3 Pro, etc.)
/ai set free — free-tier models for experimentation
Or specify inline: @ai gemini-3-pro Write a tech spec......Manage credits:
- View balance in the App Home tab
- Click ":credit_card: Buy More Credits" to add funds via Stripe
- $0/month base cost
- Pay-per-use: Wholesale API rates + 10%Add to Slack today. $1.00 free credit. No credit card required.:warning: Important Information:
Slack Plan Requirement: The AI agent experience in Slack's app container requires a paid Slack plan. However, @mentions, direct messages, and /ai commands work on all Slack plans, including free.
AI Accuracy Disclaimer: Plug and AI provides access to third-party Large Language Models (LLMs) including ChatGPT, Claude, Gemini and other. These AI models may occasionally generate inaccurate, incomplete, or outdated information. Always verify important information independently. AI responses should not be relied upon for critical decisions without human review.

Plug and AI will be able to view:

Plug and AI will be able to do:

Review the details to better understand this app’s security practices. To learn more about assessing apps for your workspace visit our Help Center.

General

Privacy & data governance

Data retention policy

Conversation history is stored only in memory and automatically deleted after inactivity. Billing metadata (usage counts, costs, balances) is stored indefinitely in our database (until the user requests deletion), but actual message content and AI responses are never persisted. Users can enable Zero Data Retention (ZDR) mode to ensure AI providers also don't store their prompts or responses.

Data archiving and removal policy

In-memory data (conversations, caches) is automatically purged on a rolling basis—conversations after 24 hours, caches after 1 hour. OAuth installation data is automatically deleted when a workspace uninstalls the app. Users can clear their preferences via /ai clear; bulk data export and GDPR deletion requests are handled manually upon request.

Data storage policy

We store only billing metadata (user IDs, token counts, costs, transactions) in Cloudflare D1—no message content, images, or conversation transcripts are persisted. All data is stored in Cloudflare's infrastructure with encryption at rest. User-uploaded images and AI-generated images are passed through to Slack and never stored on our servers.

App/service has sub-processors

yes

Guidelines for sub-processors

https://plugand.ai/privacy.html

App/service uses large language models (LLM)

yes

LLM model(s) used

Users can choose from 300+ models including GPT-5, Claude, Gemini, Llama, and Mistral via OpenRouter; the default is an auto-routing chain that selects the optimal model per request.

LLM retention settings

Zero Data Retention (ZDR) is enabled by default, instructing providers not to store prompts or responses; users can disable ZDR in settings if they need access to models that don't support it.

LLM data tenancy policy

We use OpenRouter as our API gateway with Zero Data Retention (ZDR) enabled by default; individual model providers (OpenAI, Anthropic, Google) maintain their own tenancy policies which users should review.

LLM data residency policy

Data residency varies by model provider—requests may be processed in the US, EU, or other regions depending on which model the user selects; we do not control or guarantee specific data residency.

Certifications & compliance

Security