01
The problem
An agent that only answers questions is of limited use. It becomes
valuable once it acts on the data, and that is also where the risk
starts.
A recruiter repeats the same handful of actions all day: find a job
posting, filter applications, call someone, move an interview, follow
up. Each one takes a minute or two. Put end to end, they fill most of
the working day.
Automating reads is straightforward. Automating writes, meaning
creating, editing and sending, takes far more care. A model that gets a
read wrong gives a wrong answer and you correct it. A model that gets a
write wrong damages a customer's data.
All of this also had to work over the phone, with real
candidates, in real time.
02
What I built
An agent that acts
Adèle takes over the actions a recruiter used to repeat by hand: find a
job posting, filter applications, schedule an interview, follow up. You
talk to her normally and she chains the steps.
Nothing changes without the user's approval
Before any change, the user sees what will be modified and confirms it
themselves. An approved action can still be undone.
On the phone, in real time
Adèle places and receives real calls. She qualifies the candidate,
offers time slots and confirms an appointment. She also handles being
interrupted mid-sentence.
What I take from it
The quality of an agent comes down to the design of its tools and to
the guardrails around its writes. A customer accepts letting an AI
modify their data when they see the preview before execution, when
they confirm it themselves, and when they know how to roll it back.
