Someone asks about a ticket. Instead of switching tabs, you ask Sayli, and it reads the ticket and answers from what is actually there. That is the difference between a copilot and a chatbot.
Tools, in the moment
MCP connections let Sayli call external tools during a call and after it. A read tool pulls a real ticket or a real doc into the answer. A write tool drafts an update for you to send. The work stays inside the conversation.
You connect a tool once per organization. Everyone on your team shares it after that.
The presets
Eight presets ship today. Some connect with a pasted token. The rest connect with OAuth.
| Tool | Connect with |
|---|---|
| Linear | Token |
| Notion | OAuth |
| GitHub | Token |
| Jira | OAuth |
| Confluence | OAuth |
| Gmail | OAuth |
| HubSpot | OAuth |
| Salesforce | OAuth |
Read now, write on confirm
Read tools run while Sayli answers. They ground a reply in a real ticket or a real doc, so the answer reflects what your tools hold, not a guess.
Write tools work differently. Sayli proposes them in the brief, with the change spelled out. They run only after you confirm.
A write tool is always a proposal first. You read it, then you decide. Sayli never posts, edits, or sends on its own.
Connect one
Find the preset you want in the list of eight.
Linear and GitHub take a pasted token. The rest send you through an OAuth sign-in with the provider.
Review what Sayli can read and write, then approve. The connection now belongs to your whole organization.