Checking a deploy
Dan Fletcher, engineering lead at Acme Ltd, asked whether yesterday's deploy had made things worse. Memtro compared the last two deploys by error count and rate, and listed the open incidents with their first backtrace line.
Which errors are open in production, and did the last deploy make things worse?
AppSignal connects Memtro to your application monitoring. It reads error and performance incidents with state, severity, namespace, occurrence counts and the first backtrace line, and deploys with revision, who deployed and the errors each saw. It reads performance per action, with mean duration, throughput, error rate and N+1 queries, plus uptime monitors and their alerts, and metric timeseries. When asked, and once an administrator has granted the action by name, it can change an incident's state or severity, add notes to logbooks, and create, update or delete custom markers. The token is yours, so Memtro sees what you see.
Ask in plain English from chat, your editor, a scheduled job or your own agent. The model picks the right AppSignal tool, reads what it needs, and answers with the source cited.
These tools change something in AppSignal. 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 AppSignal, choosing the same kinds; the tab shows AppSignal's own steps. Each event can start a job, with the event as its input. AppSignal signs every delivery, and one whose signature does not check out is refused before it is read.
Events and webhooksOnce AppSignal 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 incidents are open in production?
Did the error rate go up after the last deploy?
Which actions were slowest over the last 24 hours?
Are any uptime monitors alerting right now?
Close incident 42 and note that the fix shipped this morning
Dan Fletcher, engineering lead at Acme Ltd, asked whether yesterday's deploy had made things worse. Memtro compared the last two deploys by error count and rate, and listed the open incidents with their first backtrace line.
Maya Okafor, developer at Northwind, asked Memtro to close the timeout incident and note the fix. Memtro closed it in AppSignal and added the note to its logbook, where everyone on the app could read it. Its notifications stopped until it happens again.
The teams that lean on AppSignal most, a question each of them asks, and what they connect beside it.
A record in AppSignal 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 AppSignal, open your avatar → Personal settings → Personal API token and copy it. The token is yours, so the connection stops working if you leave the organisation.
Open the app in AppSignal and copy its id from the URL, the part after /sites/.
In Memtro, open Connections → AppSignal and paste Personal API token and App id.
Ask your first question: which incidents are open in production?
Chat in the dashboard, the OpenAI-compatible API, scheduled jobs, and any MCP client: Claude Code, OpenCode, Cursor, Claude Desktop. The AppSignal tools are the same everywhere.
Only when you ask, and only what it has been granted: change an incident's state (open, in progress, closed) or severity; add a note to an incident's logbook; add a note to a performance action's logbook; create or update a custom marker on the app's graphs; delete a custom marker. 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.
Personal API token and App id. In AppSignal, open your avatar → Personal settings → Personal API token and copy it. The token is yours, so the connection stops working if you leave the organisation.
Yes. Turn events on in the connection's Events tab on the Connections page, then add the address it shows as a webhook in AppSignal, choosing the same kinds; the tab shows AppSignal'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