Connect your stack once. Every agent can use it.
Agents read from and write to the tools your team already uses. Most connect in a few clicks. Anything else, the integration builder agent connects for you, from any data source you can describe.
Salesforce
Gong
Slack

Google Workspace
Notion
HubSpot
Outreach
Add an MCP server
Every tool agents can use today.
Grouped by what Taizen does with them. Each one is available to the chat, to every agent and to the background agents they start.
CRM
Read the deal, write it back.
Calls and meetings
What was said, and by whom.
Email and calendar
Threads for context, drafts that wait for approval, meetings that trigger prep.
Google WorkspaceTeam messaging
Where briefs, flags and approvals land.
Social and messaging
Search prospects and reach them where they answer.
Sales engagement
Sequences, campaigns and approved content.
LemlistKnowledge and docs
Playbooks and documents agents can read and cite.
Product and customer data
Usage and conversations for renewal and expansion work.
Projects and data imports
Work boards, forms and spreadsheets brought into Taizen.
Not on the list? An agent builds it.
The integration builder is an agent that connects any data source. Name a tool or paste a link to any API, including your own. It researches the API, asks for the access it needs, works out what to fetch, writes the importer and test-runs it before anything goes live. If a run fails later, it shows up under Needs you with a diagnosis.
Any MCP server
Server URL
Available to the chat and every agent, in safe mode until you say otherwise.
You decide who uses each connection.
Keep a connection to yourself, share it with a team, or open it to the whole org. Shares wait for an admin's approval, and write access is chosen when you connect.
Salesforce
Connected by Dana Whitfield · read and write
Who can use it
Just meTeamsWhole orgSecure by default.
Connections use OAuth, credentials are stored encrypted, and you choose read-only or write access per tool. With read-only credentials an agent says it couldn't write rather than pretending it did.
How long does it take to get running?
Connections are OAuth and take a few minutes. Most teams have their first agent live the same day, usually the CRM update, because it removes work reps are doing by hand right now.
Can it write back to our CRM, or is it read-only?
You decide when you connect it. Read-only for analysis, or write scopes for fields, notes, next steps and close dates. With read-only credentials a run tells you it couldn't write rather than pretending it did.
Can we connect our own internal systems?
Yes. If the system has an MCP server, connect it over OAuth and every agent can use it. If not, name it or paste a link to its API: the integration builder agent researches it, asks for access, writes the importer and test-runs it before it goes live on a schedule.
What if an integration stops working?
It moves to Needs you with what went wrong, and Diagnose looks into it from the same screen. Nothing fails silently: you see each integration's last run and its schedule at a glance.