Monday applicant review
On Monday the head of engineering at Northwind asks who applied for the backend role last week. Memtro lists the new candidates for that job with source and rating, and reads the panel's notes on the two already interviewed.
Ask who applied for a role in Recruitee this week, and what the panel thought.
Connect Recruitee with a personal API token and company ID, and Memtro reads candidates with email, source, rating and the jobs they applied to, jobs with status, department and candidate count, notes on a candidate, and recruiting tasks. It reads on demand and there is no hourly sync. When you ask, and once an administrator has granted the action by name, it can add notes, tags, tasks and candidates, move or disqualify a candidate, which may email them, publish a job on your public careers site, close or archive jobs, and permanently delete a candidate. Everything is done as you.
Ask in plain English from chat, your editor, a scheduled job or your own agent. The model picks the right Recruitee tool, reads what it needs, and answers with the source cited.
These tools change something in Recruitee. 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 Recruitee, choosing the same kinds; the tab shows Recruitee's own steps. Each event can start a job, with the event as its input. Recruitee signs every delivery, and one whose signature does not check out is refused before it is read.
Events and webhooksOnce Recruitee 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 applied for the product manager role this week?
Which roles are published right now, and how many candidates does each have?
What did the panel think of Priya Sharma?
Move Priya Sharma to the final interview stage for the backend role
Publish the draft Data Analyst job on our careers site
On Monday the head of engineering at Northwind asks who applied for the backend role last week. Memtro lists the new candidates for that job with source and rating, and reads the panel's notes on the two already interviewed.
Recruiter Lena Hoffmann asks Memtro to draft a Data Analyst job for Acme from the hiring manager's notes and publish it. Memtro creates the draft, she checks it, and on her go-ahead Memtro publishes it. The job goes live on Acme's careers site and its job boards, where anyone can apply.
The teams that lean on Recruitee most, a question each of them asks, and what they connect beside it.
A record in Recruitee 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 Recruitee → Settings → Apps and plugins → Personal API tokens choose New token. The token has your access, and anything Memtro changes is done as you
Copy the token and the company ID shown on the same page
In Memtro open Connections → Recruitee, paste the Personal API token and the Company ID, and connect
Ask who applied for a role this week
Chat in the dashboard, the OpenAI-compatible API, scheduled jobs, and any MCP client: Claude Code, OpenCode, Cursor, Claude Desktop. The Recruitee tools are the same everywhere.
Only when you ask, and only what it has been granted: add a note to a candidate; add tags to a candidate; create a recruiting task; add a candidate; edit a candidate's name, emails, phones or links; permanently delete a candidate; put a candidate on a job; move a candidate to another stage of a job; disqualify a candidate from a job; requalify a disqualified candidate; create a job as a draft; publish a job on the careers site; close a job; archive a job; complete or reopen a task; edit a task. 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 Company ID. In Recruitee → Settings → Apps and plugins → Personal API tokens choose New token. The token has your access, and anything Memtro changes is done as you.
Yes. Turn events on in the connection's Events tab on the Connections page, then add the address it shows as a webhook in Recruitee, choosing the same kinds; the tab shows Recruitee'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