How is this different from notes in our ATS?

ATS notes are written for humans and rarely resurface at the right moment. Glen gives agents memory they retrieve and write automatically in one MCP call, so the relevant history about a candidate or a manager appears in context while the agent works.

Does the whole recruiting team share one memory?

Yes. Glen is org-shared, so every recruiter's agents read and write the same store. A candidate's prior history or a manager's real preference one recruiter captures is immediately available to everyone else's agents.

Shared memory for recruiters

Recruiters live on context that is easy to lose: the candidate who was a great fit but not ready last year, the hiring manager's real bar versus the job description, the feedback pattern that keeps killing offers, the silver-medalist worth revisiting for the next role. That knowledge ends up in an ATS field no one reads, in scattered notes, and in the recruiter who owned the req, so when the role reopens or the candidate resurfaces, the team starts over. When recruiters bring in AI agents to screen resumes, draft outreach, or summarize interviews, those agents know nothing about the team's history with a candidate or the manager's true preferences. Glen, shared memory for AI agents, gives those agents a durable, team-shared memory as a single MCP tool that retrieves relevant context and records new findings in one round trip.

Connect Glen to the agents your recruiting team uses, a resume-screening assistant, an outreach drafter, an interview-summarizer, and each gets one tool that reads the relevant history and writes back what it learned. Before an agent screens a candidate, it pulls what the team already knows: that this person interviewed strongly two years ago, that the hiring manager actually weights systems design over algorithms, that a similar profile was rejected for a fixable reason. After an interview, the agent records the feedback and the durable signal so the next role and the next recruiter benefit. You stop re-sourcing candidates the team already vetted and stop relearning each manager's preferences from scratch.

The shift is that recruiting knowledge becomes a shared, living asset instead of dying in stale ATS fields and personal notes. Glen is org-scoped, so the memory spans every recruiter and every agent on the team. One recruiter's agent records that a hiring manager rejects candidates without startup experience; every other agent factors it in, so outreach and screening stay aligned with the real bar. Because Glen is a standard MCP server, the same memory is readable from any MCP client, so a screening agent, an outreach assistant, and an interview-notes summarizer all draw on one consistent record of candidates and roles. Wire it in once over OAuth or an API key and let your team's recruiting knowledge compound across reqs instead of resetting every time a role reopens.

FAQ

How is this different from notes in our ATS?: ATS notes are written for humans and rarely resurface at the right moment. Glen gives agents memory they retrieve and write automatically in one MCP call, so the relevant history about a candidate or a manager appears in context while the agent works.
Does the whole recruiting team share one memory?: Yes. Glen is org-shared, so every recruiter's agents read and write the same store. A candidate's prior history or a manager's real preference one recruiter captures is immediately available to everyone else's agents.