Building AI tools that do boring work. Claude Code, SEO, Automation, Agents. Sharing what works and what doesn't.
Mumbai, India
Joined June 2026
- Tweets6.9K
- Following1.5K
- Followers1.7K
- Likes4.2K
how to find X posts worth replying to (the 3 filters i use)
2 to 1,000 followers in 81 days, mostly by replying. these are the filters that decided which posts got a reply.
the play: right accounts > fresh posts > one specific point
> first steps
- go to: x.com/search-advanced
- put your topic in "these words". pick 2 or 3 topics you can actually say something about
- under engagement, set minimum likes to 10, so you land on posts people are already reading
- set "from" to yesterday's date. search, then open the Latest tab
> the 3 filters
- the account has 5,000+ followers, unless you two already talk. hover the name to check
- the post is under a day old. after that, everyone has scrolled past
- you have one specific thing to add: a number, a step, a mistake you made. if all you have is "great point", skip it
> the catch
- most replies stay quiet. 15 to 27 oct, my middle reply got 17 views. my best got 1,349
- per post, my own posts did better: 168 views vs 49 for a reply. replies are how new people find you, not a shortcut
- one account's numbers, not a rule from X
> what not to do
- don't reply to the same person twice in a day
- don't paste an AI draft as it is. people spot it (someone once answered mine with "AI reply????")
- don't put your link in a reply
i built humanish to run these filters and draft the reply in my voice. i still read and send every one: tryhumanish.com/?utm_source=…
reply with your topic and i'll tell you which filter i'd tighten first. bookmark this for your next reply session
what it doesn't do: post for you. every reply is a draft. you read it, change what you want, and send it yourself.
casual and formal tones hold up best. funny and sarcastic are still hit and miss.
not ready to pay? the AI-tell checker is free, no account needed. paste a reply and see how AI it reads: tryhumanish.com/check?utm_so…
receipts, from X's own analytics. july: 5,115 impressions. august: 156,854, with 249 new follows.
and follows over time, from the first one on 10 july to today.
2 to 1,000 followers on X in 81 days, mostly by replying.
july: 5,115 impressions. august: 156,854.
so i built humanish. it finds posts worth replying to and drafts in your voice. you press send.
$29/mo: tryhumanish.com/?utm_source=…
Claude Code Didn't Get Worse. Your Chat Did. (Explained Simply)
Your AI assistant seems to get dumber the longer you talk to it. It didn't change. The pile did. We set a trap, ran a real test, and found a week-old chat carries more words than The Great Gatsby before it even starts.
The Boring Developer: a fox called Bori and a developer who reads his own logs. Every episode takes a week of real posts from X and runs one real test.
Humanish finds people worth replying to on X, drafts a reply in your voice, and throws it out if it reads like AI.
You read it, fix a word if you want, and send it yourself.
The system i use personally is open at tryhumanish.com
One tap and a draft is shorter, funnier, more direct, or softer.
Paste what someone said to you into Reply back and get an answer in your voice.
And the checker is free: paste any reply and see how AI it sounds.
Today’s posts, written in your voice. 4 a day on Standard, 8 on Pro.
Each one uses a real format: before and after, short story, a mistake and what you do now.
Copy one and post it, or send the batch to Buffer.