Retro follow-up
A week after the Acme payments outage, the engineering manager asks what is still open. Memtro lists the incident's five action items, three done and two open, with priority, due date and assignee, one of them two days overdue.
Ask which action items are still open from last week's incident, and what happened when.
Connect Rootly with an API key and Memtro reads incidents with status, severity, services, teams and milestone times, each incident's timeline, action items, alerts and services. The hourly sync writes each incident into memory as it changes. When asked, and once an administrator has granted the action by name, it can declare, update, mitigate, resolve or cancel incidents, and your Rootly workflows may page responders when it does. It can permanently delete an incident, escalate an alert, which pages the next on-call level, acknowledge or snooze alerts, and add timeline events and action items.
Ask in plain English from chat, your editor, a scheduled job or your own agent. The model picks the right Rootly tool, reads what it needs, and answers with the source cited.
These tools change something in Rootly. 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, choose the kinds you want, and Memtro registers its address with Rootly for you. Each event can start a job, with the event as its input, and can be remembered where you choose. Rootly signs every delivery, and one whose signature does not check out is refused before it is read.
Events and webhooksOnce Rootly 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 action items are still open from last week's incident?
What happened during the checkout outage on Tuesday, in order?
How long did it take to mitigate the last SEV1?
Which alerts came in overnight, and from which source?
Resolve the Northwind outage incident with a note that the retry fix is deployed
A week after the Acme payments outage, the engineering manager asks what is still open. Memtro lists the incident's five action items, three done and two open, with priority, due date and assignee, one of them two days overdue.
During the Brightwave Ltd login incident, Priya Nair asks Memtro to record that the cache was flushed at 14:05 and then mark the incident mitigated. Memtro adds an internal timeline event and marks it mitigated, and the team's Rootly workflow posts the change to the incident channel.
The teams that lean on Rootly most, a question each of them asks, and what they connect beside it.
A record in Rootly 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 Rootly open the Organization dropdown → Organization Settings → API Keys and Generate New API Key
Choose Global, which covers the whole organisation, and the narrowest role that can read incidents, and edit incidents and alerts if you want the actions. A Team key sees only that team's records
Paste the API key into Connections → Rootly in Memtro and connect
Ask which action items are still open from last week's incident
Chat in the dashboard, the OpenAI-compatible API, scheduled jobs, and any MCP client: Claude Code, OpenCode, Cursor, Claude Desktop. The Rootly tools are the same everywhere.
Only when you ask, and only what it has been granted: add an internal event to an incident's timeline; add an action item to an incident; declare an incident (your Rootly workflows may page responders and open a channel); update an incident's title, summary, status, severity, services, environments or teams; mark an incident mitigated; resolve an incident; cancel an incident; delete an incident (permanent); assign an incident role to a user; subscribe users to an incident's updates; acknowledge an alert (stops its escalation); resolve an alert; snooze an alert for some minutes; escalate an alert (pages the next on-call level); update an action item's summary, status, priority, due date or assignee. 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. An hourly sync anchors recently changed Rootly records into memory as entities.
API key. In Rootly open the Organization dropdown → Organization Settings → API Keys and Generate New API Key.
Yes. Turn events on in the connection's Events tab on the Connections page, choose the kinds you want, and Memtro registers its address with Rootly for you. 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