AI for recruitment takes on the admin that slows a desk down: reading applications against the brief, keeping candidates and clients updated, drafting job ads and keeping the CRM clean. We design and build these tools for recruitment agencies and staffing firms, on the systems you already use, and your recruiters make every hiring call.
Overview
Recruitment is a people business run on a database. Every role brings a brief to write up, an ad to draft, applications to read, candidates to update and a client to keep informed, and most of it lands on the recruiter between calls.
Tensor Partners builds focused tools for that work: agents that read applications against the criteria a recruiter sets, draft updates and job ads for review, and keep candidate and client records clean. Each one connects to the CRM, job boards and inbox you already run. AI supports the screening; it does not decide. Every shortlist and every hiring decision stays with a person, and every suggestion shows its reasons so it can be checked.
Our live systems were not built for a recruitment agency, but two of them do the same jobs a desk does every day. The Sales Agent reconciles new leads into a CRM, cleans up duplicate and stale records and recommends who to contact next. The Prospecting Bot watches new job listings as they are posted, scores each one against defined criteria and drafts a tailored proposal ready to review. The patterns transfer; your desk sets the rules.
At a glance
Agents take the reading, drafting and record-keeping at each step. The recruiter sets the criteria, makes the shortlist and every hiring decision.
Step 01
Role brief
Captured from the intake call and notes
Step 02
Job ad drafted
From the brief and your past ads, for the recruiter to edit
Step 03
Applications read
Against the recruiter's criteria, with reasons shown
Step 04
Recruiter decides
Who goes forward, and why
Step 05
Candidates + client updated
Drafts sent on the rules you set
Step 06
CRM kept current
Duplicate and stale records cleaned up
Use cases
An agent reads each application against the criteria the recruiter set for the role and writes a short summary of how it matches, with the evidence and the gaps side by side. It does not reject anyone. The recruiter reads the reasoning, checks it against the CV and makes the shortlist.
Document processing →Candidates told where they stand after each stage, hiring managers reminded about interview feedback, and reference and paperwork requests tracked until they come back. Updates go out on the rules you set, and anything sensitive goes to the recruiter first.
AI automation →Draft job ads from the role brief, the intake notes and your agency's own past ads, ready to edit and approve. Consistent across the desk, without starting from a blank page. Nothing is posted without the recruiter's sign-off.
Candidate and client records kept current: duplicates merged, stale records flagged, and a ranked list of who to contact next with a summary of what each person wants. The same pattern as our Sales Agent.
See the Sales Agent →Newly advertised roles watched as they appear, each scored against the sectors and roles your desk recruits for, with a tailored outreach draft ready for a consultant to review. The same pattern as our Prospecting Bot.
See the Prospecting Bot →Applications, candidate questions and client requests sorted before the day starts and turned into a prioritised task list for each consultant, with the noise set aside. The same pattern as our Triage Agent.
See the Triage Agent →Case studies
CRM + lead operations
Not built for a recruiter, but the same job a desk does with candidate and client records. A chat-commanded agent that reconciles new leads into the CRM, cleans up duplicate and stale records, recommends which leads to contact next and summarises what each one actually wants.
Lead scraper + proposal drafting
Built in-house for our own pipeline, not for a recruitment agency. A bot that watches new job listings as they are posted, scores each one against what we actually do, and drafts a tailored proposal ready to review and send. The same pattern suits a desk looking for new roles to work.
How it works
Every phase ends in something you can see working. You decide at each step whether to go further.
A fixed-price AI opportunity audit. We map how work moves through your desk, from role brief to placement, and rank every opportunity on return, feasibility and risk, with the builds priced.
AI consulting + audit →Working software on your stack, tested against your real roles and records, with the recruiter making every shortlist and hiring decision.
AI agents →Shipped into production with logging, monitoring and rollback. We stay on to measure, tune and extend the system as your desk and the models change.
AI automation →Services
Each one can run on its own or as part of a wider engagement.
FAQ
Mostly by taking admin off the desk: reading applications against a brief, drafting job ads and candidate updates, chasing feedback and keeping the CRM clean. The aim is more time on the phone with candidates and clients, with a recruiter approving anything that goes out and making every hiring decision.
No. An agent can read applications against the criteria you set and explain how each one matches, but it does not reject or shortlist anyone on its own. The recruiter makes the call, and every suggestion shows its reasons so it can be checked.
By designing for it from the start. The agent works only from the criteria the recruiter sets for the role, shows the evidence behind every suggestion, and is kept away from details that should not influence a hiring decision. Those rules, and who reviews the output, are agreed during the audit, before anything is built.
Only if it is designed for it. Our agents get the minimum access each task needs, log every action they take, and stop for a person instead of guessing. What any model may see, and where candidate and client data lives, is agreed during the audit, before anything is built.
No. We build on top of the CRM, job boards and email you already use, connecting them through their APIs. If a system cannot be connected cleanly, the audit tells you before you commit to a build. Every engagement starts with a fixed-price audit, so you see the numbers before committing.
Start here
Start here
30 minutes, no pitch deck, no obligation. Tell us what's eating your team's time and we'll tell you straight whether AI is the answer, and roughly what it would take.