Double - Your AI career agent that gets you hired
by•
Double is your personal AI career agent. Just text it, and it manages your entire career: finding your roles, applying for you, growing and maintaining your network, and making recruiters chase after you.
Replies
Whats up guys, if you have any questions regarding the product I'll be awake all day responding so please please lmk
Really interesting concept. How does Double learn from outcomes such as recruiter replies, rejections, and interviews to improve the roles it pursues and the way it represents each user? Can users also see why Double believes a particular opportunity is worth pursuing before it takes action?
@j_mehta1 We have a custom memory layer that stores all of the actions/outcomes double takes on your behalf so it learns what works and what doesn't. In regards to users being able to see why double believes a particular opportunity is worth it, there is no UI per se, but all you have to do is ask double to explain!
Lancepilot
Nice launch , qq how does the agent balance token limit optimization when reviewing long multi-page corporate career documents alongside deep user profile sets?
@istiakahmad We don't feed raw docs into context. Long documents and profiles get extracted into structured data against our own skills/occupation taxonomies, then we use embeddings to retrieve only what's relevant to the task at hand, backed by a persistent user profile so the agent isn't re-reading everything each time. The model spends tokens reasoning, not re-parsing boilerplate. Happy to go deeper if you're building in this space!
minimalist phone: reduce your screentime
Which data it "reads over the internet" in terms of getting information about the job positions? Also LinkedIn?
@busmark_w_nika we crawl 80k+ company career pages weekly and get job listings STRAIGHT from the source, so no aggregators like linkedin or indeed as they are quite unreliable.
minimalist phone: reduce your screentime
@lucapiekarski Aaaa, okay, thank you for clarification! :)
Lot of people use Claude to fix their resumes and apply to jobs. But they still end up doing the search and manually applying. I was wondering how accurate is the AI when it automates this task and does it improve over time ?
@reda_roqai_chaoui Hi Reda, good question! Double is quite accurate with this kind of thing, we also have strict guardrails in place so double never does anything you don't want it to do. In addition to this, double also has a memory system so it is capable of learning and improving over time!
Spycost
Really interesting concept. I’d love to try how Double finds relevant roles and handles outreach.
@glebarios Thanks so much for the support Hlib! Excited to hear what you think!
Would love to see a calendar integration that blocks out time for interview prep or networking follow ups, since right now the agent handles applications but I still have to manually schedule everything around it.
@harun154545 We are actively working to integrate google calendar + mail. Double will be able to do that automatically in a couple of weeks! Thanks so much for checking us out and the feedback!
Hey everyone! I'm Vance, Double's CTO, and I'll be here all day to answer any questions you have. Also, let me know any features you'd like to see!
Congrats on shipping. The thing I would protect here is the crawler, not the agent.
Luca's answer to Nika is the most interesting line in this thread. Crawling 80k company career pages weekly and skipping the aggregators is a real asset, it is hard to copy, and it is the part nobody in the comments is talking about. Everything else in the pitch, applying for you and growing your network, is something ten other tools are claiming this month.
The risk on the applying side is timing. This is the year hiring teams started drowning in AI applications, and a lot of them are now filtering for exactly that, so volume is turning into a liability rather than an edge. If Double applies to 200 roles for me and 190 are near misses, I have not been represented, I have been mass mailed, and that lands on my name rather than yours.
So the version I would want is fewer and better. Ten roles pulled straight from company career pages, matched properly, with something written that actually sounds like me. That happens to be the story your crawler lets you tell and your competitors cannot.
One small thing on the site. It is worth saying plainly what happens to my CV, and whether anything gets posted or sent as me before I connect an account. For a product that speaks on my behalf, that answer is most of the decision.
@abdullah_javaid3 Hey Abdullah! Thank you so much for the message. This is really good advice, and exactly the direction we're trying to go towards. You are completely correct about the volume and mass-apply issue. This is one of the biggest issues in the job market today, and leads to a viscous cycle of: volume applying leading to more rejection leading to more applying...
We want to solve this issue by doing what all our competitors don't: advise people on the best next steps to take, growing their online portfolio/presence by showcasing their projects + contributions, and connecting them to the right people to help them. We want to think about the applying as a 'given' - nobody wants to fill in applications and all we do is simplify the tedious process. We do not support mass apply, and specifically made it so that every application is carefully optimized and tailored. We are continuously searching for better ways for candidates to stand out, ones that don't rely on spray-and-pray which is killing the job market.
In the future, we are also thinking about adding a layer of friction for people that apply to roles that don't fit. We believe that everyone can shoot for any role, but if it isn't a match, Double takes the steps to advise them how to become a fit.
Side note: We have already built the feature that carefully recommends select jobs to users and are shipping that today! I've also written a few blog posts on this exact issue, would love if you could check it out: https://trydouble.ai/articles/youre-a-lemon
@loup_wang Thanks for the thoughtful reply, and I read the lemon piece. The Akerlof framing is spot on, and it is the first time I have seen it applied to hiring without turning into a complaint about recruiters.
Two thoughts it left me with.
Your essay makes the case for the parts of Double you described here better than the site currently does. If a tailored application is cheap for everyone now, the durable value sits in the portfolio, the contributions and the warm intros, which is exactly where you say you are heading. Might be worth letting that lead, since it is also the harder part to copy.
On building a new signal, the test I would use is asymmetry rather than effort. It has to cost a weak candidate more than a strong one, otherwise the pile just gets more expensive without getting any clearer. Your idea of adding friction for roles that do not fit is the right instinct, and it works as long as that friction stays light for someone who genuinely does fit.
Really glad the select recommendations are shipping today, that sounds like the same direction. Good luck with the rest of the launch.