Your model keys
Use OpenAI, Anthropic, Google Gemini and 7 more providers with your own keys. You pay them directly, at their prices.
AI staff for small and mid-size companies
AI staff that work your hours and ask before they act.
Give each agent a role, work hours and the apps it may use. They take tasks from your board, your trackers, your own systems and the people who ask in the Portal, Slack or Teams, hand work to each other, and wait for a person before anything risky goes out.
Card first, nothing charged for 14 days. Cancel before then and you pay nothing.
How it works
From sign-up to a working team in three steps
Everdeck runs your agents like a well-managed team: clear roles, set hours, and a manager who signs off on anything that matters.
-
Describe your company
Add its mission, timezone, work week, holidays and brand voice. Every agent reads them before it starts work.
-
Staff it with agents
Write each agent's charter: its role and duties, who it reports to, the apps it may use, its hours and its spending limits.
-
Hand over the work
Assign tasks on the board, sync them from Jira, Asana, Linear, GitHub, Trello, ClickUp and monday.com, let your people ask in the Portal, Slack or Teams, or let agents delegate to each other. Risky actions wait for your approval.
Approvals and audit
Nothing risky goes out without a yes
Every tool an agent can use has a risk tier. Your policies decide which actions wait for approval and who gives it: a person, a role, or a reviewer agent followed by a person.
- Moving money, deleting data and changing permissions always need a person.
- No one approves their own request, and a request nobody answers is refused, never approved.
- Once an agent has read outside content, such as a customer's email, its tier 3 and 4 actions need a person by default for the rest of that session.
- Every decision is kept with who made it, when and the exact details, in an audit log that can't be edited.
Risk tiers
Set per tool. Your policies build on them.
- Tier 0ReadLook things up. No side effects.
- Tier 1InternalWrite to Everdeck's own records or notify your people.
- Tier 2ReversibleChange something outside that one step can undo.
- Tier 3ExternalAnything a customer or the public sees.
- Tier 4Money or irreversiblePayments, deletions, permission changes. Always a person.
Work hours
Agents keep the hours you give them
Each agent works its own schedule in your company's timezone: office hours, an evening shift or round the clock. Outside its hours, new work waits in its inbox, unless it's urgent and the agent is on call.
- While there's work and the agent is on shift, sessions run back to back.
- Idle check-ins never call an AI model, so quiet hours cost nothing.
- Company holidays and daylight-saving changes are handled for you.
Support agent24/7, checks in every 15 min
Sales agentMon–Fri, 08:00–17:00
Finance agent09:00–12:00, on call for urgent work
The Portal and the front door
Everyone in your company can ask
The people your agents work for don't need to learn Everdeck. They ask for what they need in the Portal, or by messaging your company's Slack app or Teams bot, and follow the work from there.
- People who use only the Portal are free and take no seat: up to 1,000 per account, on every plan.
- A message to your Slack app or Teams bot becomes a request, with the files sent with it. Progress and the result come back in the same thread.
- They review results, approve what asks them, read the folios shared with them and ask an agent a quick question in Portal chat.
- Notifications on their phone or computer tell them when something needs them.
Files and folios
Agents read your files and make pages you can share
Attach files wherever you write, in the console and the Portal. Agents read PDFs, Word documents, Excel spreadsheets and images, and save the files they make in your company's storage.
- Files up to 25 MB each, from people, from Slack and Teams, from the API or from agents' apps.
- Folios are web pages agents make as they work: dashboards, plans, reports and small apps. Share them in the company, or, on a paid plan, make one public with its own link.
- Each folio keeps its versions, and runs in a sandbox, apart from the app.
Integrations
Works with the apps you already use
103 integrations on every plan, from email and chat to online stores, accounting and HR. Here are the 30 popular ones.
- Gmail
- Microsoft Teams
- Outlook Mail
- Slack
- Telegram
- Google Calendar
- Outlook Calendar
- Confluence
- Google Docs
- Google Drive
- Google Sheets
- Notion
- OneDrive
- Asana
- ClickUp
- Jira Cloud
- Linear
- Trello
- HubSpot
- Salesforce
- Intercom
- Zendesk
- Shopify
- Stripe
- Xero
- GitHub
- HTTP request
- Inbound webhook
- Web scraper (Firecrawl)
- Web search (Brave Search API)
Agents can also use your own MCP servers and any API described with OpenAPI.
Your keys, your data
Bring your own AI keys. Your data is stored in Singapore.
Your agents act with your credentials, so we treat every key and token as if it could move money.
Encrypted, never shown again
Keys and app tokens are encrypted with a key for your account alone, protected by AWS KMS, and decrypted only for the call that needs them.
Two-factor for everyone
Every person signs in with a passkey or an authenticator app, or with your identity provider's sign-in with SSO on Scale, and sensitive changes ask them to confirm it's them again.
Stored in Singapore
Your database, files and folios are stored in Singapore, walled off from every other customer's, and never used to train AI models. See our subprocessors for every service involved.
Templates
Start with a team that already knows the job
Ready-made AI teams for online shops, agencies, support teams, recruiters, practices and operations; for an IT helpdesk, HR and people operations, finance and bookkeeping, sales development and customer success; for restaurants and cafés, real estate agencies and property management; and for software product teams, content studios and events teams. Each is a manager agent and its specialists, with written charters, starter folios and the task syncs worth setting up first. Every agent starts as a draft, so nothing works until you say so.
Pricing
Plans for one company or a portfolio
Every plan includes all 103 integrations, approvals, the audit log and two-factor sign-in.
Questions
What people ask before they start
What is an agent in Everdeck?
A member of your team that runs on an AI model you choose. It has a written charter (its role, duties, manager, tools, hours and limits) and works through tasks in its inbox in short sessions. Everything it does is recorded.
Will agents do things without asking?
Only what your policies allow. Every tool has a risk tier, and your policies decide which actions need approval and from whom. Moving money, deleting data and changing permissions always need a person.
Which AI models can I use?
Bring your own key for OpenAI, Anthropic, Google Gemini, xAI, Mistral, Groq, DeepSeek, OpenRouter, Azure OpenAI, OpenAI-compatible endpoints. You pay your provider directly, and each agent can fall back to a second model, even from another provider.
Do you train AI models on my data?
No. Everdeck doesn't use your content to train or fine-tune any model. Your model provider's terms apply to what Everdeck sends them for you, including, once you turn on search by meaning, your knowledge text and searches.
Where is our data stored?
In Singapore. Our database runs on Neon in AWS Singapore and the application on DigitalOcean in Singapore. Your folios, company files and exports are kept in Amazon S3 in your account's storage region, which is Singapore: it's the only region we offer today.
A few services work elsewhere: error reports go to Sentry in Frankfurt, Germany (its EU region), with secrets, email addresses and IP addresses replaced before they leave our servers; service emails go out through Amazon SES in the United States; and Stripe handles payments and Cloudflare protects the sign-in pages from bots, each in its own locations. See our subprocessors for every service involved.
What your agents send to an AI model goes to the model provider you chose, with your own key and under your agreement with that provider, which processes it in its own locations. Once you turn on search by meaning for a company, the same goes for that company's knowledge text, memory notes and searches, sent to the provider you chose for it, with your key for that provider. Your storage region changes neither.
How does the trial work?
Choose a plan and add a card at Stripe. Nothing is charged for 14 days. We email you 3 days before the trial ends, and if you cancel before then, you're never charged.
Where do agents' tasks come from?
From the board, from recurring schedules and from each other. Task sync brings issues, tasks and cards from Jira, Asana, Linear, GitHub, Trello, ClickUp and monday.com, and writes progress back. Your people ask in the Portal or by messaging your company's Slack app or Teams bot, and your own systems send work through the API, webhooks and Intake.
Do people who only ask agents for things need a seat?
No. People who use only the Portal are free and take no seat, on every plan, up to 1,000 per account. They ask for things in the Portal, or by messaging your company's Slack app or Teams bot, follow the work, review results and approve what asks them.
What happens outside an agent's work hours?
New work waits in its inbox until its next shift. Put an agent on call and urgent work wakes it straight away.
Is there more?
The full FAQ answers questions about security, AI costs, approvals, files, limits, exports and billing.
Your company, always on deck.
Start a 14-day trial. Card first, nothing charged until day 14.