Offer stage check
The hiring manager asks where the three finalists for Product Designer stand. Memtro reads each opportunity in Lever: the interviews done, the notes and scores on each profile, and whether an offer is drafted, approved or signed.
Ask where any candidate stands in Lever: stage, interviews, notes and offer status.
Connect Lever with an API key and Memtro reads job postings, candidates by posting or stage, and one candidate's interviews, notes and offer status. Salary ranges and offer terms are never read. The hourly sync writes each new candidate, hire and archived candidacy into memory. When you ask, and once an administrator has granted each action by name, it can add notes, move or archive candidates, add candidates, submit feedback, and create or publish job postings, recorded against the acting user. Publishing a posting makes it public at once, and a rejection automation in Lever may email the candidate.
Ask in plain English from chat, your editor, a scheduled job or your own agent. The model picks the right Lever tool, reads what it needs, and answers with the source cited.
These tools change something in Lever. 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 Lever for you. Each event can start a job, with the event as its input. Lever signs every delivery, and one whose signature does not check out is refused before it is read.
Events and webhooksOnce Lever 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 is in the Onsite stage for the Product Designer posting?
What interviews does Marcus Bell have scheduled, and who has left notes on him?
Which candidates were archived last month, and for what reasons?
Move Marcus Bell to the Offer stage
Add a note to Marcus Bell's profile: reference checks complete, both positive, ready for offer approval
The hiring manager asks where the three finalists for Product Designer stand. Memtro reads each opportunity in Lever: the interviews done, the notes and scores on each profile, and whether an offer is drafted, approved or signed.
Sophie Turnbull, the recruiter, asks Memtro to note that Marcus Bell's references are both positive and move him to Offer. Memtro adds the note to his profile and moves the opportunity in Lever, both recorded against the acting user, and the hiring team sees the change.
The teams that lean on Lever most, a question each of them asks, and what they connect beside it.
A record in Lever 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 Lever open Settings → Integrations and API → API Credentials → Generate New Key, ticking read access to postings, opportunities, interviews, notes, offers, stages, users and archive reasons. The key is shown once
For the actions also tick write access to what they change: notes, opportunities, feedback, postings, requisitions and users
In Memtro open Connections → Lever, paste the API key, add the Acting user's email that notes and stage moves are recorded against, and connect. A sandbox key only works with the sandbox Base URL https://api.sandbox.lever.co/v1
Ask which candidates are in the onsite stage for an open posting
Chat in the dashboard, the OpenAI-compatible API, scheduled jobs, and any MCP client: Claude Code, OpenCode, Cursor, Claude Desktop. The Lever tools are the same everywhere.
Only when you ask, and only what it has been granted: add a note to a candidate's profile; move a candidate to another pipeline stage; archive a candidate with a reason (reject, withdrawn or hired), or unarchive them; add a candidate as a new opportunity; add tags to a candidate; remove tags from a candidate; submit interview feedback on a candidate; create a job posting (draft, internal or published); edit a job posting or change its state (publish, close); create a requisition; deactivate a Lever user. 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 Lever records into memory as entities.
API key. In Lever open Settings → Integrations and API → API Credentials → Generate New Key, ticking read access to postings, opportunities, interviews, notes, offers, stages, users and archive reasons. The key is shown once.
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 Lever 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