Terminal arrow_forward

How It Works

Blue Beacon Research is a research platform, not a prediction machine. Research integrity is the whole point of this page — what we claim, and exactly how you can check it yourself.

4,616

Signals tracked

Every signal in the system, counted live from the database.

290

Signals, last 7 days

Rolling count of signals created in the past week.

30

Sources monitored

RSS feeds plus other data sources.

What we claim, and how you can check it

Claim

Every signal has a Sources tab listing the reports it was built from, linking out to the original article where the publisher's URL is available.

How you can check it

Open any signal and check its Sources tab.

Claim

When the AI model is unavailable, we wait for it instead of guessing. Older signals from the keyword period stay marked as auto-classified.

How you can check it

An auto-classified signal shows a note on its page: "This signal was auto-classified — Claude analysis is temporarily unavailable."

Claim

We do not add a severity bonus for a story running as the headline versus being buried in the body.

How you can check it

The headline-placement severity bonus in our scoring code is set to zero.

Claim

Confidence reflects the model's certainty in its own read of the event — not how many reports we have.

How you can check it

Stated directly in the product's own onboarding tour, next to the confidence score.

Claim

When multiple reports describe the same event, we count them as merged reports — not as distinct outlets.

How you can check it

The reports count increments on every merged report, regardless of whether the outlet repeats.

Claim

We publish a performance statistic only when the sample, the period, the thresholds and a plain baseline are stated and a pre-declared test shows a result above that baseline.

How you can check it

The publication standard is written on the Method page.

Claim

Claude classifies an event for market impact, including a possible up, down, or volatile move in a listed commodity or currency pair, and does not recommend a position, a size, or an entry or exit.

How you can check it

The briefing and research-chat instructions state that limit. A direction on a signal is an impact reading, not an instruction to act.

Our written standard is on the Research Standard page. Errors are logged on the Corrections page.

Limits — what we don't do yet

  • Severity and confidence are model outputs, not guarantees.
  • 0% of signals in the last 7 days (0 of 290) were classified by the keyword fallback rather than the model — computed live from our own records.
  • ACLED conflict data: not connected. Conflict signals use news sources only.
  • A merged "reports" count can include more than one article from the same outlet — it is not a count of distinct sources.

See the full history on the Method page.