Checkout incident review
Priya Sharma, SRE lead at BigCo, asked which P1 incidents were open on checkout. Memtro listed each with its status, assignees and creation time, and read the war-room notes on the oldest.
Which P1 incidents are open on checkout, and who has them?
Squadcast, now SolarWinds Incident Response, answers what is on fire and who has it. You see incidents by window, status, priority, service and assignee, one incident with its timeline, war-room notes, teams, services, users, on-call schedules and escalation policies. When asked and granted, Memtro can add or delete notes, acknowledge, resolve, reassign, re-prioritise, snooze or tag incidents and write postmortems. Squadcast can tell Memtro when an incident is triggered, acknowledged or resolved, and a job can start on it. You add the address in Squadcast's webhook settings yourself. A stakeholder token can read but not act.
Ask in plain English from chat, your editor, a scheduled job or your own agent. The model picks the right Squadcast tool, reads what it needs, and answers with the source cited.
These tools change something in Squadcast. The model is told to use them only when you ask for exactly that, and an administrator grants each one by name to the teams that may use it; a personal connection acts only after its owner allows it.
Turn events on in the connection's Events tab on the Connections page, then add the address it shows as a webhook in Squadcast, choosing the same kinds; the tab shows Squadcast's own steps. Each event can start a job, with the event as its input, and can be remembered where you choose. Squadcast sends a secret with every delivery, and one without it is refused.
Events and webhooksOnce Squadcast is connected, these are the kinds of things people ask. Plain questions, no syntax. If the answer lives partly in another system you have connected, Memtro looks there too.
Which P1 incidents are open on checkout?
What does the timeline of the last database incident show?
Who is notified at each step of the Payments escalation policy?
Which incidents were resolved yesterday?
Add a note to the checkout incident saying the rollback is done.
Priya Sharma, SRE lead at BigCo, asked which P1 incidents were open on checkout. Memtro listed each with its status, assignees and creation time, and read the war-room notes on the oldest.
At Northwind, a job starts when Squadcast sends an incident triggered event. Memtro reads the incident and its service's escalation policy, then, as granted, adds a war-room note with the service's dependencies for Dan Fletcher, who is on call.
The teams that lean on Squadcast most, a question each of them asks, and what they connect beside it.
A record in Squadcast is rarely the whole story. Connect the systems that hold the rest and Memtro checks them together, then remembers what it learned so the next question starts further along.
Using something else for the same job, or both? Each connector has its own tools; connect as many as you like.
In Squadcast, open your profile, find API Tokens under your user settings and generate a new token. It carries your role.
In Memtro, open Connections → Squadcast, paste it into API token and set Region to US or EU. Team ID is needed only with several teams.
An administrator grants the actions by name, such as Resolve incident or Reassign incident, to the responders who may use them.
Ask which P1 incidents are open on checkout. Events are turned on from the connection's Events tab, and the address is then added in Squadcast's webhook settings.
Chat in the dashboard, the OpenAI-compatible API, scheduled jobs, and any MCP client: Claude Code, OpenCode, Cursor, Claude Desktop. The Squadcast tools are the same everywhere.
Only when you ask, and only what it has been granted: add a note to an incident's war room; delete a war-room note; acknowledge an incident; resolve an incident with a resolution reason; reassign an incident to a user, squad or escalation policy; set an incident's priority; snooze an incident's notifications; add tags to an incident; write a postmortem for an incident. Every other tool reads, searches or lists. The Connections page labels the tools that act, an administrator grants each one by name to the teams that may use it, and a personal connection acts only after its owner allows it.
A personal connection serves only your own requests. A shared connection serves the organisation: everyone, or only the teams an admin chooses. Admins can always add shared connections; other members need the permission.
Credentials are encrypted at rest. Tool results are cached briefly so agent loops do not repeat identical calls, and the facts the model extracts are saved to your organisation's memory with provenance (system, record and link) so they can be checked and superseded.
API token and Region. In Squadcast, open your profile, find API Tokens under your user settings and generate a new token. It carries your role.
Yes. Turn events on in the connection's Events tab on the Connections page, then add the address it shows as a webhook in Squadcast, choosing the same kinds; the tab shows Squadcast's own steps. A job set to start "When an event arrives" then runs once for each matching event, with the event as its input. The run treats the event as outside data, never as instructions, and anything the run remembers is kept as unverified.
Seven-day free trial, then one monthly price per organisation. Connectors, jobs and memory are never metered.
Sign in, add a provider key, create an API key and point your tools at Memtro. It takes about five minutes.
7-day free trial · card on file, nothing charged until it ends · cancel any time