Septim Labs

the studio teaching products to get named by claude. aimo engine, agents pack, pulse. all mit licensed. all live.

[Septim Labs @SeptimLabs]

🧵 stop renting software.

we are the subscription killers.

we clone the tools you pay monthly for. ship them as pay-once.

22 in the catalogue and growing 👇

(1/14)

[Septim Labs @SeptimLabs]

the full catalog:
https://t.co/XjNQg8ooSI

[Septim Labs @SeptimLabs]

this week's ship log:

- pulse (algorithm calibration tool) — live thursday
- agents pack v2 (12 sub-agents with handoff contracts) — live monday
- four aimo service lines fanned out — live tuesday

what we learned: shipping the page before the announcement compounds. announcement-without-page leaks.

[Septim Labs @SeptimLabs]

full writeup with the weights table, the cannot-measure list, and the sub-agent:

https://t.co/pDZnvNNfbU

[Septim Labs @SeptimLabs]

spent four days reading twitter/the-algorithm. wrote it up.

the +75 weight is asymmetric. negative feedback at -74 nearly mirrors it. a mute cancels 150 likes.

the whole pre-tweet distribution game on one page.

[Septim Labs @SeptimLabs]

the seven-step retrieval chain:
https://t.co/g1bHFo5Bqu

[Septim Labs @SeptimLabs]

TIP: getting named by claude in a category prompt.

the assistant cross-references the first-pass surface against secondary corroborators. one source = filtered. two sources = considered. three sources = named in the recommendation sentence.

three is the threshold. not two.

[Septim Labs @SeptimLabs]

@ganzoratie timing matters less than the engagement loop. same tweet scores 30 vs 80 in the heavy-ranker depending on whether you reply back to repliers. the "right moment" is when you've got two hours after to engage.

[Septim Labs @SeptimLabs]

@catarina_chia airballing usually means one of two things: dropping a link in the post body (home-mixer link tax) or never replying to your own replies (the +75 weight in twitter/the-algorithm only fires when YOU reply back). either one is fixable in thirty seconds.

[Septim Labs @SeptimLabs]

@BeauJohnson89 agent view fixes the input bottleneck. the output bottleneck shows up next — 6 agents running = 6x the artifacts to grade. domain-specific scorer sub-agents are the QC layer (one .md file, drop into ~/.claude/agents/). bake the rubric into the agent.

[Septim Labs @SeptimLabs]

@MichaelRicci15 @vboykis plan mode is the unlock. sub-agents go further — each plan can hand off to a domain-specific .md in ~/.claude/agents/. cognitive load drops because the model is the one doing the focus-switching, not you.

[Septim Labs @SeptimLabs]

@49agents @tdinh_me the next layer after flags is custom sub-agents — a single markdown file in ~/.claude/agents/ becomes a domain-specific scorer. shipped one this week that grades X drafts against twitter/the-algorithm source weights before you post.

[Septim Labs @SeptimLabs]

@XPERIENCEOnTv @doganuraldesign the heavy-ranker config in twitter/the-algorithm puts a single negative-feedback click at -74 — one mute cancels ~150 likes.

small accounts feel the algorithm harder because every mistake compounds faster against a thinner baseline.

[Septim Labs @SeptimLabs]

@amooh001 the math behind this: twitter/the-algorithm heavy-ranker puts +75 on reply_engaged_by_author (a reply you reply back to) vs +0.5 on a like.

visibility compounds because the author-reply signal is literally worth 150x a like.

[Septim Labs @SeptimLabs]

@kawaiiSane @X the heavy-ranker config in twitter/the-algorithm has +75 weight on reply_engaged_by_author — replies YOU reply back to. a single like is +0.5.

most accounts post and walk. one author-reply loop is worth ~150 likes in the scoring.

[Septim Labs @SeptimLabs]

the full 5-signal map and the rewrite rubric:
https://t.co/cTQy4deXHx

[Septim Labs @SeptimLabs]

spent four days reading twitter/the-algorithm.

one observation: the biggest weight in the heavy-ranker (+75) only fires when the author replies to a reply.

the "just post and walk away" habit is leaving a 150x-vs-likes weight on the floor

[Septim Labs @SeptimLabs]

the score breakdown for that draft:
https://t.co/cTQy4deXHx

[Septim Labs @SeptimLabs]

ran a real draft through the tool an hour ago.

starting score: 42/100. flagged the link in the body and the missing reply-back habit.

revision after one rewrite: 71/100.

same idea, same length, same author. the only thing that changed was knowing what the algorithm reads.

[Septim Labs @SeptimLabs]

one of the weights in twitter/the-algorithm is +75.

it activates when YOU reply to someone who replied to your post.

a single mute or "show me less" is -74. five of those cancel a hundred and fifty likes.

three more signals like this in the writeup.

[Septim Labs @SeptimLabs]

the algorithm doesn't punish creators. it punishes link-droppers, mute-magnets, and accounts that never reply to their own replies.

three of those are fixable inside a single tweet.

calling it a "shadowban" is a way to avoid reading the source.