Review preparation
Maya Okafor, Engineering Manager at Northwind, asked who had recognised Priya Sharma this quarter and for what. Memtro read the recognitions where Priya was a receiver and grouped the messages by hashtag, with who gave each.
Who has recognised Priya this month, and for what?
Bonusly holds the recognition your people give each other. Memtro reads recognitions in a period, newest first, with giver, receivers, message, company value hashtag and points. It filters by a person's email or by hashtag, and counts the top givers, receivers and hashtags. It looks at the last 30 days unless you name another period. When asked and once an administrator has granted the action by name, it can give recognition from a named giver, which spends their points, notifies the receivers and posts on the company feed, and edit or permanently delete a recognition within Bonusly's 24-hour window.
Ask in plain English from chat, your editor, a scheduled job or your own agent. The model picks the right Bonusly tool, reads what it needs, and answers with the source cited.
These tools change something in Bonusly. 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.
Once Bonusly 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.
Who has recognised Priya this month, and for what?
Who gave the most recognition in the last 30 days?
Which company values came up most this quarter?
What recognition has Dan received for #ownership?
Give Priya 10 points from me for the launch, under #teamwork.
Maya Okafor, Engineering Manager at Northwind, asked who had recognised Priya Sharma this quarter and for what. Memtro read the recognitions where Priya was a receiver and grouped the messages by hashtag, with who gave each.
Tom Reilly, Product Lead at Acme Ltd, asked Memtro to give Dan Fletcher and Sarah Chen 5 points each from him for the release, under #ownership. Memtro gave the recognition from Tom, which spent his points, notified Dan and Sarah and posted on the company feed for everyone to see.
The teams that lean on Bonusly most, a question each of them asks, and what they connect beside it.
A record in Bonusly 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 Bonusly, open Company → Integrations → API & Tokens and create a token. Anyone can make a personal one under Settings → API.
Choose the recognition:read and user:read scopes, plus recognition:write only if Memtro may give, edit or delete recognition when asked, and an expiry. Copy the token, as it is shown once.
In Memtro, open Connections → Bonusly and paste it as the Access token.
Ask: Who has recognised Priya this month, and for what?
Chat in the dashboard, the OpenAI-compatible API, scheduled jobs, and any MCP client: Claude Code, OpenCode, Cursor, Claude Desktop. The Bonusly tools are the same everywhere.
Only when you ask, and only what it has been granted: give Bonusly recognition from a named giver: spends their points, notifies the receivers and posts on the company feed; edit the message of a Bonusly recognition (only the giver, within 24 hours); delete a Bonusly recognition permanently (the giver within 24 hours, or a company admin). 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.
Access token. In Bonusly, open Company → Integrations → API & Tokens and create a token. Anyone can make a personal one under Settings → API.
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