A job search is dozens of conversations at once.
Who said yes, who already helped, who needs a nudge that is not annoying. The search ends, and the few hundred people who took your call are worth more than the offer.
The job to be done
A page for the pressure behind the query.
Start with the work that falls through the cracks, then decide whether an external relationship memory earns a place in your day.
Wend, measured
92
people from one WhatsApp read, before you grant a single permission.
0.63s
to read 69,000 messages and find the people in them. No model call.
2.4s
for one extraction on the Mac itself, at no cost.
Measured on a real Mac running macOS 26.4.1. On-device extraction needs Apple silicon with Apple Intelligence turned on.
How Wend helps job-seekers
The search starts with your real network
Import your LinkedIn archive as one ZIP and every connection lands before your first outreach. WhatsApp comes in with no permission prompt. Day one is a full graph, not an empty one.
Every conversation, in one memory
Paste the call notes or forward the thread and your agent proposes who it was, what was said and what you promised. Approve once. Your next message picks up exactly where you left off.
Find the warm path in
Ask who you know at a target company and get the second-degree route: who introduced you to whom, who worked where. That is a graph query, not a guess.
Nudge at the right time
Cadences track which threads have gone quiet, and the daily digest surfaces them before the role fills. Your agent drafts the follow-up too.
With Wend, you can
Track every informational interview and what you promised to send
Get reminded to follow up with a recruiter before the role closes
Find the alum or mutual who can refer you into a target company
Leave the search with a network you keep, not a spreadsheet you abandon
FAQ
How does this help with a job search?
It keeps every thread somewhere your assistant can query it, finds warm paths into target companies through people you already know, and surfaces the follow-ups going cold. A LinkedIn archive imports at any size, so day one starts full.
Can it write the outreach?
Yes. Your agent writes the draft from what your graph actually holds about that person, and you decide whether to send it.
What does it cost during a search?
The memory is free forever. Wendy is $29 a month or $290 a year, flat at any network size, so you can pay for it through the search and stop after. The search ends and the network stays: nothing is deleted for non-payment, and you can export all of it.
Wend for other people like you
Relationship memory built for job-seekers.
It installs on your Mac, builds the graph out of what is already there, and answers from the AI you already use. Every fact keeps its source. $29 a month, flat at any network size.
Access is invite only right now.