AI security & operations for MSPs

Zulip

Hal posts every alert into one Zulip channel, each in a topic of its own: every escalation with its full write-up, the morning digest, Platform Health changes, watch results and notices. He answers your team in any topic of that channel. Zulip is an addition: the portal’s Events page and email stay the channels of record.

Every alert, in a topic of its own

Each escalation opens a topic named for its report and the client, with the severity, the summary, the full write-up and a link to the report in the portal beneath it. The morning digest, each Platform Health change and each notice open their own topics too, so a reply is always about one thing. A watch’s results follow in the topic of the report it follows. A report too long for one message continues in the next, in the same topic.

Write in a topic and Hal answers there, with that topic’s alert in mind. He keeps quiet where people are talking among themselves. Zulip, Slack and Teams are independent, so a team that works in Zulip gets its alerts and its answers there, and one that uses several can connect any of them.

What Hal posts
Every escalation as it happens, with its full write-up and a link to the report in the portal; the morning digest, its ACTION items first; Platform Health changes; watch results; and notices, such as maintenance on your instance. Each alert opens a topic of its own.
What your team can do
Write in any topic of the channel, no @ needed, and he answers there. Each topic is one conversation, so a reply under an escalation reaches him with that whole investigation in mind. Resolving a topic keeps its conversation.
What it is not
The channel of record. The portal’s Events page and email are: a Zulip outage, or a Zulip you never connect, changes nothing about what Hal delivers there.
How it connects
A Generic bot you create in Zulip, subscribed to Hal’s channel. Zulip Cloud and your own server both work.
Who belongs in it
Everyone in the channel reads what Hal posts there, client names included, so invite only staff you would give portal access.
Setup
The bot, the channel, who Hal can tell is asking and the test: in the docs →
The Hal portal Settings page on the Zulip section: what Hal posts there, the Enable Zulip switch, the four steps for creating the bot, the Site, Bot email, API key and Channel fields, Save and Send test buttons, and notes on checking the bot, on each person's email address setting and on private channels
Hal’s portal, Settings → Zulip, as it first opens. The four steps come first, then the four values Hal needs.

See what Hal surfaces on your own clients.

No deck. Ask us anything first. When you want to see Hal on your own tenants, we sign a short evaluation agreement and stand up your instance; you connect one tenant, Hal watches it for 14 days, and we walk you through what he found.

  1. 01You ask us your questions. No deck, no demo dataset.
  2. 02You sign a short evaluation agreement, and we stand up your own instance.
  3. 03You connect one tenant from your own admin console. Hal watches it for 14 days.
  4. 04We walk through what he found. Keep going month to month, or revoke the scopes yourself and stop.