Recruitment agency lead generation from live job ads

What a recruitment lead generation agent is

A recruitment lead generation agent finds companies that are hiring right now for the roles your agency places, and hands you the ones worth calling. It reads live job ads, keeps only the companies that match the clients you want, researches each one, finds the people doing the hiring and drafts a first email to each of them for someone on your team to send.

The reason to start from job ads is that a job ad is the one public signal that a company has the exact problem you solve, this week. A list of companies in the right sector and the right size tells you who might need a recruiter one day. An open ad for a financial controller tells you who needs one now, which role, and roughly how long they have been looking. The work that turns that signal into a pipeline is not difficult, it is relentless: checking the boards every week, throwing out the companies you would never work with, and finding a real name behind every ad. That is the part an agent can do on the schedule you choose, which is the part a billing consultant never has time for.

We build that agent for you rather than selling you a database to search yourself. You tell us which roles you place and which clients you want; we build the agent around that, you watch it work on real job ads, and we keep it running from then on. It is one of the agents we build, and it is built the same way as the rest of our work as an AI automation agency.

What our lead generation agent has done

We built this agent for Hoxton Circle, a recruitment firm that places senior finance leaders, mostly chief financial officers. On its first run, up to 1 November 2026, it found 34 companies hiring the roles the firm places. The case study below shows what was built and what that first run found.

There is no result figure on that page yet, on purpose. A first run is too early to count placements, so the honest thing to show is the work itself: which companies the agent kept, what it found out about each one, and who it found behind each ad.

Case studies

Three AI agents built for Hoxton Circle, a recruitment firm that places finance leaders. Three AI agents built for Hoxton Circle, a recruitment firm that places finance leaders: one finds companies with open finance roles, one answers job seekers, one makes LinkedIn carousels.

How the agent finds companies that are hiring

The agent works through the same steps every time it runs, even though the roles, the sources and the clients it looks for are yours.

1. It searches live job ads for the roles you place. The list of roles is yours, written down role by role, with the practice you care most about ranked first, so it looks for a Head of Tax or an interim month-end close as precisely as you would.
2. It searches the places companies actually post. Job boards such as LinkedIn and Indeed, the applicant tracking systems companies post through, and company careers pages. It records which sources it checked on each run, so a source it skipped is visible rather than silently missing.
3. It keeps only recent ads. You set the window, and an ad older than that drops off, so the list is about who is hiring now rather than who was hiring in the spring.
4. It checks each company against your ideal client. Size, sector, location and anything else you filter on, written down with you before the agent runs, so it keeps the companies you would actually pitch and throws out the rest.
5. It researches each company it keeps. Revenue, headcount, industry, stage and website, each with a note of where the figure came from and the date it was checked.
6. It finds the people doing the hiring. Names, titles, email addresses and LinkedIn profiles, with an address marked Verified or Predicted by how sure the agent is of it.
7. It drafts a first email to each contact. A person on your team reads it, changes it, and sends it, or doesn't.

It also keeps the reasons. For every job ad it saw, it records what the source returned and whether it kept or dropped the ad, so any company on your list can be traced back to the ad that put it there.

Who it looks for: your ideal client, written down

The agent is only as useful as its picture of the clients you want, which is why we write that picture down with you before it searches anything. For Hoxton Circle that meant the firm's own list of every role it recruits for across its four practices, the sixteen industries it works in, the locations it covers and a minimum company size, with finance roles ranked first because finance is most of the firm's work.

Some of that is a hard rule and some is only a guide, and the difference matters. A minimum company size can be a rule: below it, the company is dropped. Headcount, for Hoxton, is a guide: a smaller company that fits everything else still counts. We also agree what happens to a company the agent cannot size, so that a firm with no published figures is set aside to be checked rather than quietly lost.

Your own judgement goes into the rules as well. A company you remove from the list stays removed: the agent skips it on every later search instead of finding it again next week.

The hiring contacts it finds, and how sure it is of them

For each company it keeps, the agent finds the people likely to own the hire, such as the chief financial officer for a controller role, and gives you their name, title, email address and LinkedIn profile.

An email address is given one of two labels. Verified means the address has been checked. Predicted means the agent built it from the company's email format and could not check it, for example because the company's mail server accepts every address. The label tells whoever sends the email how much to trust the address before it bounces.

The same honesty applies to the company research. A figure the agent could not find stays blank rather than being guessed, and an estimate it could not confirm is labelled as an estimate. Hovering over a figure shows where it came from and when it was checked.

The outreach it drafts, and the person who sends it

The agent drafts a short first email to each contact, opening with the role their company is advertising and what your agency could do about it. It never sends anything. A consultant opens the draft, rewrites whatever sounds wrong, and decides whether it goes at all.

That is a deliberate line rather than a missing feature. A recruitment agency's reputation travels with every email sent in its name, and a hiring manager who receives a clumsy automated note remembers the agency that sent it. The agent's job is to put the right company, the right person and a reasonable first draft in front of your team; the conversation is yours.

How we build it, and how long it takes

We build the agent around your roles and your ideal client, and you see it working on real job ads before it does the job on its own. You pick one person on your team to work with us day to day, usually whoever does your business development. Here is how it runs.

1. A 30-minute consultation. You tell us which roles you place, which clients you want and where you look for them today. We tell you what we would build and give you the price.
2. Scope. We watch how your team finds new clients today and write down your roles, your ideal client and the sources it should search, so we agree what the agent will do.
3. Build. We build it inside the tools you already use, around the rules we wrote down together.
4. Test. It runs on live job ads, checked by us, until it gets it right. We show you the companies it found and the ones it threw out, and you tell us where it got your ideal client wrong. We change the rules until its list looks like one your own team would have drawn up.
5. Live. It does the job on its own, searching live job ads on the schedule you choose while your team works the companies it finds, and we keep it working.

How quickly its list looks like your own depends mostly on how precisely your ideal client can be written down. An agency that already knows its roles and its client profile gets there sooner; one that is still deciding who it wants to sell to takes longer, and the scope is a good place to decide. Fully functioning and delivering value in 30 days guaranteed, or you pay nothing more until your agents are.

What it costs

Ours is one flat monthly fee for unlimited agents: this agent, and any other you want after it, for the same fee, month to month. We give you the price on the call.

We set it on the consultation once we know how many roles and sources it has to search and how many contacts you want it to find. What it will not do is charge you by the search, the company or the contact: the usage is in the fee, so a busy month costs the same as a quiet one, and you can stop any month. Fully functioning and delivering value in 30 days guaranteed, or you pay nothing more until your agents are. What it would cost you to run an agent like this is the subject of what an AI agent costs.

An agent, a lead generation agency, or a data tool

There are three common ways for a recruitment agency to find new clients, and the right one depends on how much of the work you want to keep in house.

A lead generation agency runs the whole thing for you: it builds the list, writes the campaign, sends the outreach and books meetings into your diary. That suits an agency that wants meetings and is happy for someone else to speak in its name. What you give up is control over who is contacted and what they are told.

A data tool gives you search filters and contact details, and leaves the searching, the judging and the writing to your consultants. It suits a team with the time to use it every week.

An agent sits between the two. It does the searching, the filtering and the research to your written rules, and hands your team a list of companies and a draft for each contact; your people decide who hears from you and in what words. Testing it on real job ads is how you find out whether that is the shape you want.

Your data, and the tools the agent can reach

We handle your data under UK GDPR, and we walk you through exactly where it goes on the consultation. The agent can only reach the sources and systems you approve, and you can withdraw that access at any time.

The list stays yours. The companies, the research and the contacts can go wherever your team already works, and nothing about the way the agent works depends on your data living with us.

Recruitment agencies often want more than one agent. We also build an AI recruitment chatbot that answers job seekers from your live vacancies, and an AI LinkedIn carousel generator that turns your jobs newsletter into LinkedIn carousels in your own style. How they fit together is the subject of AI agents for recruiters.

Tell us which roles you place

Tell us which roles your agency places, which clients you want more of, and how you find them today. We will tell you on the call whether an agent can take that work, what we would build, and what it would cost.

One flat monthly fee for unlimited agents, month to month. Fully functioning and delivering value in 30 days guaranteed, or you pay nothing more until your agents are.