Before a callback
Sarah Chen, team lead at Acme Ltd, asked what had happened with a customer before calling back. Memtro found the customer by email and read the last conversation's timeline: the internal notes in full and when each message arrived.
What happened in this customer's last Gladly conversation?
Gladly connects Memtro to customer service. It finds customers by email, phone or external id and reads conversations with status, inbox, assignee and topics. A timeline gives internal notes in full, but customer messages as type and time only. It also reads tasks, agents, inboxes, teams and topics. When asked and granted, it can add notes, assign, close or reopen conversations, manage topics and tasks, reply to a customer, send an email or SMS, manage customer profiles and redact a message. With events on, Gladly tells Memtro when a conversation opens or closes, and a job can start on it.
Ask in plain English from chat, your editor, a scheduled job or your own agent. The model picks the right Gladly tool, reads what it needs, and answers with the source cited.
These tools change something in Gladly. 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 Gladly, choosing the same kinds; the tab shows Gladly's own steps. Each event can start a job, with the event as its input. Gladly sends a secret with every delivery, and one without it is refused.
Events and webhooksOnce Gladly 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.
What happened in the last conversation with priya@acme.example?
Which open tasks does this customer have, and who owns them?
Which agents are on the returns team?
Which help-centre answers were updated recently?
Add an internal note to her open conversation saying the refund is approved.
Sarah Chen, team lead at Acme Ltd, asked what had happened with a customer before calling back. Memtro found the customer by email and read the last conversation's timeline: the internal notes in full and when each message arrived.
At Northwind, a job starts when Gladly reports a conversation was closed. It reads the timeline and, as granted, creates a follow-up task for the customer in Tom Reilly's inbox. Tom sees the task in Gladly, and the customer is not notified.
The teams that lean on Gladly most, a question each of them asks, and what they connect beside it.
A record in Gladly 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 Gladly, open Settings, Users and tick API User on the agent's profile. Signed in as that agent, open More settings, API Tokens and create a token. A dedicated API agent is safer.
In Memtro, open Connections → Gladly and enter the Gladly organization, such as acme, the API user's email and the API token.
An administrator grants the actions by name, such as sending SMS, to the teams that may use them. Events are turned on from the connection's Events tab, and the address is then added in Gladly's webhook settings.
Ask what happened in a customer's last conversation.
Chat in the dashboard, the OpenAI-compatible API, scheduled jobs, and any MCP client: Claude Code, OpenCode, Cursor, Claude Desktop. The Gladly tools are the same everywhere.
Only when you ask, and only what it has been granted: add an internal note to a conversation; assign, close or reopen a conversation; add topics to a conversation; remove a topic from a conversation; create a task for a customer; update, close or reassign a task; reply to a customer's message (the customer receives it); send an email to a customer; send an SMS to a customer (charged per segment); create a customer profile; update a customer profile; delete a customer and all their conversations (permanent); redact the content of a message (permanent). 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.
Gladly organization, API user's email and API token. In Gladly, open Settings, Users and tick API User on the agent's profile. Signed in as that agent, open More settings, API Tokens and create a token. A dedicated API agent is safer.
Yes. Turn events on in the connection's Events tab on the Connections page, then add the address it shows as a webhook in Gladly, choosing the same kinds; the tab shows Gladly'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