# How we give every applicant a fair first read Each new application wakes an agent that checks the resume against the role's written rubric, quotes its evidence, and suggests interview times for strong fits. A person decides every case. Canonical page: https://themachine.myapps.ai/use-cases/resume-triage Post a job and the applications pile up faster than anyone can give them proper attention. So the reading gets hurried. Each resume gets a glance, two reviewers reach two different verdicts, and the criteria written into the role slowly slip out of view. A great candidate can vanish in a skim, and the bar shifts with whoever happens to be on screening duty that day. Our fix is an agent on Machine that handles the first pass the same way every time. When an application lands, the agent checks it against the role's written rubric, writes up a structured screen backed by quotes, and suggests interview times when the fit is strong. It never turns anyone down. Every yes or no belongs to a person. We use this exact setup on the people who apply to us. - **Team:** Machine - **Runs on:** Each application as it arrives - **Connected systems:** Applications inbox / ATS · Written role rubric · Google Calendar - **Mode:** Fires on a trigger · people make all the calls ## The problem Inconsistency creeps in at the very first glance. A big pile means quick reads, and quick reads wander. Hand one resume to two reviewers and you can get two answers. Sometimes a candidate is marked down for something the job description never asked for. Good people slip through the cracks, and the standard depends on who is holding the pile. The common workarounds just move the problem. Keyword filters latch onto the wrong words and silently throw out strong applicants. A hurried human pass loses its consistency somewhere around lunch. And an AI screener judging by its own private sense of "good" creates a fairness problem of its own: nobody can see its reasoning, nobody answers for it, and nobody can audit it. ## What we built With Machine, every new application starts an agent. It gets its own **session**, which is simply a fresh cloud computer (a sandbox) set up for that one applicant, holding the role's written rubric plus limited access to Google Calendar. The agent compares the resume with the rubric and writes a structured screen listing strengths, gaps and a score, each backed by quotes from the application. If the match is strong, it also suggests interview times on the hiring manager's calendar. Then a person makes the call, every single time. ## How it works ### Make a new application the starting gun We hook up the applications inbox, or the ATS, so that each arriving application kicks things off. Every one gets its own **session**, a brand-new sandbox loaded with just that resume. One applicant, one session, one throwaway computer. Screens never bleed into each other, and many can run at once. ### Hand the agent the role's rubric The written rubric for the role goes into the agent's **skills** and **memory**, the playbook it carries into every run. It spells out the must-haves and the nice-to-haves, what convincing evidence looks like for each, and how points are given. The agent judges against that rubric and nothing more. If the rubric changes, we edit the file and the next screen follows the new version. ### Wire up the calendar Using **connectors**, which are narrow connections to your tools with the keys held on our servers so the model never sees a raw token, the agent can: - **Read the whole application.** It works from the candidate's own words, so the screen can quote them directly. - **Measure it against the rubric.** It lists strengths, gaps and a score, and pins each one to a quote from the resume. - **Suggest interview times.** For a strong fit, it finds free slots on the hiring manager's Google Calendar and offers them for a person to confirm. ### Draw the lines Only the written rubric counts, and the agent always shows the evidence behind each strength, gap and score, so anyone can check its work. It will not reject an applicant on its own. Advancing or declining is always a person's decision: the agent hands over the screen and the suggested times, and the hiring manager chooses. Credentials are stored encrypted in the **Secrets Manager** and only handed to the agents you grant them to. ### Open each application already screened Once that is running, every new applicant shows up already measured against the rubric. You get a structured screen with a score and the quotes that justify it, plus suggested interview times when the fit is strong. The hiring manager weighs the evidence, makes the call and confirms a time. The first pass is steady, and a human still owns the outcome. > **The pattern** > Each application fires a **trigger** that opens a session carrying the role's > rubric in its **skills** and **memory**, plus a narrow **connector** to Google > Calendar. The agent judges by the written rubric alone and shows its evidence. > It never rejects anyone by itself, and people make every call. ## Guardrails This agent reads people's applications, and what it writes influences who gets hired. So fairness and human judgment are part of how it is locked down: - **Isolation.** Each applicant gets a separate sandbox. The session can see only the resume it was given and can reach only the calendar. All that comes back out is the screen and the suggested times. - **Scoped secrets.** Keys for the inbox, ATS and calendar are stored encrypted in the Secrets Manager and only handed to the agents you grant them to. - **Human approval gate.** No applicant is ever rejected automatically. Scores come from the written rubric alone, each with its evidence on show, and a person decides whether anyone moves forward. - **Everything is code.** The rubric, the agent's setup and its permissions all live as files in the repo. They carry version history, and changing them takes a reviewed **change request**, not a toggle in some dashboard. ## The outcome - **Every application:** Measured by one shared written rubric, quotes included - **A person decides:** The agent never rejects a candidate on its own - **3 systems:** Inbox, rubric and calendar handled by a single agent The first pass is now steady and easy to check. Each applicant is judged by the same written rubric, with the quotes that earned every score sitting right there, and strong fits come with interview times already suggested. Hiring managers stop skimming and start deciding on evidence. Whether someone moves forward or not is still up to a person.