Which recruitment CRM has the best AI?

I build the AI side of our product, so I spend a lot of time looking at what everyone else has shipped. The honest summary is that the gap between the best and the worst in this market is enormous and almost completely invisible from the outside, because everybody describes theirs with the same six words.

These are the four things I would test if I were buying, in the order I would test them.

Test one: does it ever say it does not know

A language model always produces an answer. That is what it is for, and it is the single most important thing to understand before you let one near your database.

Give it an email that says pass this one to Sara, when your agency has a Sarah in Leeds and a Sara Collingwood in Manchester. A model asked to pick will pick. It will not hesitate, and the record it writes will look precisely as trustworthy as a record that is correct. Nothing on the screen will say this one was a guess.

Multiply that across every ambiguous email, CV and call note in a month. The result is a database that is quietly wrong in ways nobody can find, which is far more expensive than a database that is obviously wrong.

So ask to see an ambiguous case. Hand them a real one. If the software writes an answer regardless, you have learned what it will do two thousand times a month.

Ours reports a number for how certain it is, and there is a line at three quarters. Below it nothing is written and the case goes back to a recruiter. We keep test cases whose only purpose is to prove it stays unsure when it should, which sounds like a strange use of an afternoon until you have seen the alternative.

Test two: is the AI doing work, or making conversation

There are two kinds of AI in recruitment software and they are worth about different amounts to you.

The first is a chat box. You type a question, it answers, and you decide what to do. It is useful, it took about a fortnight to build in 2024, and everybody has one.

The second does a specific job without being asked. It sorts every reply to your outreach so the interested ones sit at the top of your morning. It writes the notes from a call and puts them on the record. It reads the tone of a meeting. It fills fields on a job from your own lists rather than from its imagination. Nobody has to remember to use it, which is the whole point, because the thing recruiters reliably forget to do is use the optional tool.

A product with one chat box and no working agents has AI in the sense that a car has a radio.

Test three: can they name the models, and say what happens when one fails

Ask which models they use. A vendor who owns their AI properly will name them, tell you what happens when one is slow or down, and find the question slightly dull. A vendor who does not will talk about their partnership with a large technology company.

The follow-up matters more. Models change underneath everybody, sometimes overnight, and the answers they give change with them. If a product sends your text straight out to whatever is on the other end, nobody there knows when the behaviour shifted until a customer complains.

What ought to sit in between is a layer the vendor controls, which tests a model against their own cases before it reaches you, keeps a second one in reserve, and measures what each call costs. Building that is unglamorous and it is the difference between a product that survives a provider's bad Tuesday and one that does not.

Test four: can they tell you where AI touches your data

Your clients are going to ask you this, so you need to be able to ask your vendor.

Most cannot answer. The list of places a model gets called grows every month and a list maintained by hand is stale the week it is written. The revealing response is a confident number that turns out to come from a slide deck.

We stopped keeping ours by hand for that exact reason. A program reads every line of code we have, here and across the other systems we run, and refuses to finish if it finds anything touching AI it cannot account for. The first time we ran it against our own code it found more than forty places our hand-written list had missed.

What good and bad look like side by side

Ask	A product with a chat box	A product with an AI estate
What happens when it is unsure?	It is very accurate	It reports confidence and hands low ones to a person
What does it do unprompted?	Waits to be asked	Sorts replies, writes notes, fills fields, flags risk
Which model is it?	Leading AI technology	Named, with a reserve and a measured cost
Where does AI touch our data?	Across the platform	A count, and how it is kept current
How do you know an update has not broken it?	We test thoroughly	A battery of cases run against the live model before release

What I would actually do

Take one ambiguous email and one messy CV into every demo you attend. Not tidy ones. The kind that arrive on a Friday afternoon with half the information missing and a name that could be two people.

Watch what the software does with them. Everything worth knowing about a vendor's AI is visible in that one moment, and none of it is visible in the part of the demo they prepared.

The products worth your money are the ones where somebody has thought hard about being wrong. That is a much rarer thing in this market than a chat box, and it is the only part of it that will still matter to you in three years.

---

Lokesh is Founder and Head of Engineering at Recruitly.