Engineering note
AlfaBrief looks like a crypto-news site. It's really an autonomous pipeline— software that reads the market firehose, decides what actually moves prices, writes the brief, fact-checks its own draft, and publishes. Day to day, no one touches it. This is what's underneath.
Every stage has one job. The key decision is which stage runs which model — the expensive one only ever sees work the cheap one already approved.
Monitor
CODEA handful of crypto news feeds plus a live exchange data stream, checked every five minutes. Everything lands in one queue of candidates.
Filter & score — the gate
HAIKUA cheap, fast model scores each candidate 0–1 for market impact against a fixed rubric. Most are dropped right here. This is the cost gate — it's why the expensive model never has to read the whole firehose.
Deduplicate
CODEA seven-day window drops anything already covered, matched on story identity rather than wording — so the same event never gets processed or published twice, however many outlets run it.
Rank & cap
CODESurvivors are ranked by a composite score — recency, USD magnitude, token significance, source consensus. A hard daily cap then takes only the top few, which bounds both output and the worst-case bill.
Rewrite
SONNETThe only place the quality model runs. It turns each surviving story into an original, trader-focused brief — thesis, context, data, what invalidates it — written from the source, not copied from it.
Verify — grounding pass
HAIKUA second cheap-model pass re-reads the draft against the source and strips any claim the source doesn't support. If a rewrite invents a number, this is what removes it before it ships.
Fact-check gate
CODEA deterministic check, no AI in it: every dollar figure in the draft must trace back to the source. An untraceable figure — a made-up ETF outflow, an inflated exploit total — holds the article instead of publishing it. It exists because a soft AI-only check let a fabricated number slip through once.
Publish
CODEThe finished brief goes live on the site and into the ~5-day digest — categorised, timestamped, tagged by risk type. A Next.js frontend overlays live prices and market signals from exchange APIs. No manual step anywhere.
Constraint
The pipeline shares a single LLM API key with another system I run, so every call it makes is money out of my own pocket. Left naive, a busy news day would quietly run up the bill. So the whole design is shaped around spending the expensive model as rarely as possible.
The cheap model gates the expensive one. A small, fast model filters everything first. The quality model only ever sees the handful of stories that survive — never the raw feed. Reading the whole firehose with the expensive model would cost multiples more for the same output.
A hard daily cap. However much news breaks, only a fixed number of briefs get the expensive rewrite. The cap turns an open-ended cost into a known, flat one.
Right model for the job. The rewrite gets the strong model because quality shows. Filtering and fact-checking get the cheap one — that work is judgement, not prose, and judgement is where the cheap model is already good enough.
Net effect: roughly a 60% cost cut with no drop in the quality of what publishes — and a bill that can't run away on a heavy day. The whole system runs for about $10/month.
The system writes the articles. I built the system — and I'd rather be straight about both sides of that than oversell it.
Deliberately boring where boring is fine, so the effort goes where it matters.
Running autonomously since 27 May 2026 · roughly $10/month to operate.
Digest every ~5 days. Market-moving intelligence for active traders. Free — no spam, unsubscribe at any time.