curatedai.net
Directory Categories Radar Models Leaderboard Guides Prompts Skills Briefing Newsletter
Light Dark
AI AUTOMATION & INTEGRATION

I build the pipeline that runs CuratedAI, then I read everything it produces.

01 Output

A year of it

265 active days in the last year Quiet Busy

265 days out of 371. Every block is one day, sized and inked by what came out of it: stories published in the briefing, tools reviewed into the directory, changes shipped to this site. The blank ones are days nothing did. Hover any day to see what it actually was.

One day’s reading

  1. 01King Charles Warns AI Leaders of 'Existential Danger' at Scotland SummitBBC Technology
  2. 02OpenAI Launches Astra for Law, Targeting Big Law FirmsOpenAI
  3. 03Anthropic Launches Claude Code Projects for Always-On, Parallel Dev WorkAnthropic
  4. 04Huawei Plans Q1 2027 Launch of New Ascend AI Chip as It Takes On NvidiaTechCrunch AI
  5. 05Base Labs Launches Open-Weight AI Safety Partnership With Hugging Face and GoodfireTechCrunch AI
  6. 06DeepMind Offshoot Emulate Nears $4 Billion Valuation a Month After FoundingFinancial Times Tech
  7. 07Meta-Tied Data Center Taps US Junk Bonds for the First TimeBloomberg Technology
  8. 08Arm CEO More Confident Its New AI Chip Can Meet $2B Revenue GoalCNBC Technology
  9. 09Iceland-Based Treble Raises $18 Million for Its Voice Simulation PlatformTechCrunch AI
  10. 10Comp AI Raises $34M Series A for AI-Driven ComplianceTechMeme

the ten that came through, 17 September 2026

209 in, 10 out. Every tick is a story that arrived on a typical day. The ten standing full height are the ones that survived. Across the 170 days where I have both the intake and the published briefing, 35,519 went in and 1,703 came out. About one in twenty-one. The other twenty are the job.

tools reviewed
378
briefings published
227
stories, all sourced
2,272
guides written
122
pages generated
1,936
02 The standard

Most people who write about AI tools do not run them. Most people who run them do not write. I do both, which is the only reason this directory is worth reading.

My work is AI automation and integration: wiring models into systems that already exist, building pipelines that carry content from source to publication, and making the dull parts run unattended. CuratedAI is one of those systems, built and maintained end to end. The briefing, the directory and the newsletter all come out of it.

That is also the review standard. A tool goes in when I have seen it work, and the listing says when something is gated, region-locked or shipped as weights with no product behind it. Nothing here is paid for. No tool appears because a company asked.

Every briefing story links to where it came from: the announcement, the paper, the repo. You should be able to check my reading instead of trusting it.

03 What I work on

What I work on

  • AI automation
  • Systems integration
  • Content pipelines
  • Agent workflows
  • Model evaluation
  • Video automation
04 Things I built

Things I built

Two systems run everything on this site. Both are mine, end to end. Read them stage by stage →

AI Shorts Clipper

PRIVATE · PYTHON · ~7,500 LINES

The node marked Shorts & reels in the schematic above is not a person with an editor. It is this: a pipeline that takes a YouTube URL and returns finished vertical clips with burnt-in word-level captions, a written hook, a description and a publish slot. It runs unattended.

8 hooks, one kept3 a day, then it stopstranscriptINkeyword score01model re-rank02cut segments03transcribe04burn captions05hook tournament06render 9:1607quota gate08scheduledOUT
  • The hook is a tournament, not a prompt. Eight candidates are generated, validated, judged, run off against each other and trimmed to twelve words. Any clip that falls back to its own title gets a second pass automatically, because the fallback is the failure case and it should not ship quietly.
  • Publishing is quota arithmetic. The YouTube API allows 10,000 units a day and an upload costs 1,600, so the scheduler posts three, spends 4,800, writes its state and stops. It picks up where it left off the next morning.
  • A y/N prompt is not a safety gate. Anything that rewrites already scheduled or already live videos passes through a separate confirmation that a reflexive return key, a piped yes, or a --yes flag cannot satisfy. Everything reachable from a terminal eventually gets run by accident.
three passes, no shared pickstwelve deliverables61 sourcesINscore01rank x30230-day dedupe03reconcile041 per company05write x1206render cards07validate08briefingOUT

Content Creation Workforce

PRIVATE · PYTHON · ~74,000 LINES

The machine behind the daily briefing. It reads 61 sources every morning, ranks a few hundred stories three separate ways, reconciles the three into one Top 10, and then fans that single curation out into twelve finished deliverables: the briefing itself, a narration script, social copy for five platforms, thumbnail and card artwork. 227 published days come out of it.

  • It ranks the day three times and makes the versions disagree. One pass by raw AI score, one by a composite, one tuned for spread, each forbidden from reusing the first pass’s picks. Thirty distinct stories surface, and the final ten are reconciled out of that, capped at one story per company so a single funding round cannot take the day.
  • Yesterday’s news is the hardest thing to filter. A thirty-day lookup blocks exact URLs and titles, then the same company plus the same key terms, then the same company plus five overlapping words. “Cursor Raises $2.3B” on Monday kills “Cursor $2.3B Valuation” on Thursday, which no exact-match check would ever catch.
  • Nothing ships unvalidated. A final pass checks every deliverable for completeness, duplicate titles and dead links before the day is called done. Twelve outputs generated from one source is twelve chances to publish something malformed at four in the morning.
05 Elsewhere

Elsewhere

YouTube ↗ @curatedaidotnet ↗ @aitickerdaily ↗ LinkedIn ↗