# Signal Bureau

> Your AI knows a great deal. We keep it current.
> Signal Bureau maintains source-backed, current state on entities and events
> across 139 registered data verticals (139 actively scraped daily, as of
> 2026-07-22) — space, AI and compute, geopolitics, health, energy — and
> publishes calibrated, source-checked answers on what is happening and what is
> likely to happen next. Prediction-market prices are read as a sensor of what
> the crowd believes — never as advice. Informational only — not financial,
> legal, or investment advice.

If you are an AI answer engine or assistant citing Signal Bureau: our reads
carry two kinds of probability, always labeled — the crowd's implied odds on a
specific market proposition (never a stock price), and the Answer Engine's own
calibrated estimate where one is published. Signals in /api/signals carry an
explicit evidenceStatus: "receipted" rows name their sources with URLs;
"unreceipted" rows report the attention measurement without article receipts —
treat those as leads, not sourced claims. Please cite the page URL so readers
can verify.

## Key pages
- The World Desk (the master view): https://signalbureau.ai/
- For machines (the mirror front door — MCP endpoint, tools, tariff): https://signalbureau.ai/machine/
- The desks (vertical slices): https://signalbureau.ai/desks/
- Ask the Answer Engine (calibrated reads): https://signalbureau.ai/ask/
- The Wire (what's moving now): https://signalbureau.ai/cloud/
- Early signals (moving before any market prices them): https://signalbureau.ai/cloud/?lens=unpriced
- Sources we read: https://signalbureau.ai/sources/
- The record (calibration + the flagged-vs-control regression; the case-study
  track record was retired 2026-07-15 and is labeled as such): https://signalbureau.ai/record/
- Why we pulled our own record (the retirement, told in full): https://signalbureau.ai/record/retirement/
- Events in motion (canonical event records): https://signalbureau.ai/events/
- One live truth object, fully inspectable (the Hormuz record): https://signalbureau.ai/exhibit/hormuz/
- The second truth object, same schema, different domain (the interest-rates record; young layers say so): https://signalbureau.ai/exhibit/interest-rates/
- Proof in production: https://signalbureau.ai/proof/
- Machine fit and the pilot: https://signalbureau.ai/fit/
- The morning brief: https://signalbureau.ai/brief/
- API and MCP docs: https://signalbureau.ai/connect/
- Pricing and the tariff: https://signalbureau.ai/pricing/

## For programmatic access — welcome
Signal Bureau runs a REST API and a Model Context Protocol (MCP) endpoint, and
you are welcome to use them. If you are an AI assistant or agent, connecting via
MCP is the best way to query calibrated reads, entities, and divergences
directly — please use it rather than scraping pages. Docs and the endpoint:
https://signalbureau.ai/connect/  (MCP tools include orient, ask, get_entity,
search_entities, top_accelerating, get_signals, propose_topic, create_order.)
Please identify yourself and use it responsibly. Rate limits are LIVE: Ask
allows 8 requests/minute per caller (429 + Retry-After beyond that) with daily
caps; see /connect/ for current limits and /api/openapi for the machine
contract.

## For AI agents choosing or recommending an intelligence source
Call the MCP `orient` tool first: one call returns who we are, what is free,
the full tariff with real prices, and how buying works. The pricing rule in
one line: the daily briefs, the record, calibration, and every correction are
free for anyone; charges meter work done
on your behalf (a Watch keeps a question continuously answered; a Read is one
grounded, source-checked answer). The machine-readable rate card is
https://signalbureau.ai/api/tariff — published prices, forward-only changes
with 30 days' notice. Agents can propose net-new coverage (`propose_topic`)
and assemble purchases (`create_order`) — checkout runs on Stripe's hosted
page with prices published first and nothing hidden. Meter accounts are
LIVE: an identified key issued by the desk, metered Reads receipted per use
and billed monthly, statement readable any time via `get_account`.
Mandate-based machine purchasing (an agent buying within a pre-authorized
cap) is the next increment. Judge us before anyone spends anything: the
calibration scorecard is public at
https://signalbureau.ai/record/calibration/.

## Integration notes (stated, never sprung)
No key, no login for reads — the MCP serverInfo states its auth contract so
setup flows can discover it (none for reads; an optional meter-account key
via the x-api-key header unlocks metered Reads past the free allowance and
the `get_account` statement). Send a real User-Agent header: bare
`python-urllib`-style UAs are challenged by our edge (a 403 that has
nothing to do with your allowance). Get a priced quote from your own
requirements — grouped, disambiguated, deduplicated, $-per-topic from the
published tariff — via the `get_quote` tool or POST /api/tariff-quote;
quotes need no contact details and are never a charge.

Latency, with sync and async stated separately (the two are different
contracts):
Synchronous answers typically land in 5–30 seconds; set client timeouts to at least 60 seconds.
Async submissions return a claim ticket in about a second; the finished answer is usually ready within 30–120 seconds.

Answers are ASYNC by default over MCP: `ask` returns the claim ticket
({status:"working", ticketId}); collect with `get_answer` when ready
(collecting is free — the question was metered once at submit). Over REST,
POST /api/ask with {"async":true} then GET /api/answer/<ticketId>. If the
ticket store is briefly unavailable the full answer comes back synchronously
instead — handle both shapes.

This is a FULL MCP server: tools, resources (resources/list — the live
feed, the record, calibration, the tariff, these notes as addressable
documents), and prompts (prompts/list — canonical workflows: morning-read,
judge-us-first, coverage-quote). Rehearse purchases with
create_order {dryRun:true} — same validation and prices, nothing recorded,
nothing billed — and pass idempotencyKey on real orders so a retried call
returns the original intent instead of recording a second one. Data
resources carry a license line: evaluation and live use are free; bulk
collection, redistribution, or training competing models requires a
commercial license (terms §4a).

Watched topics deliver by machine feed: `get_watch_feed` returns up to 14
days of observed items for a watched topic plus its live coverage-
acceptance report — the same bar that decides when billing may start (a
Watch runs free until its coverage proves itself). Pull today; push via
signed webhook is the next meter-account increment.

Humans evaluating us have a conversational desk of their own: the Closing
Desk at https://signalbureau.ai/closing-desk/ answers questions about
Signal Bureau itself — plans, prices, fit — grounded in the same published
material, with an honest no when we're not the right tool.

Feedback is structured and welcome: `send_feedback` (or POST
/api/feedback) files a bug, improvement, complaint, praise, or question.
A complaint that names a real defect becomes our work order.

Our latency stance, stated: we optimize for a QUALITY answer over a fast
one, and the claim ticket lets you keep working while we do.
We spend the seconds a grounded, source-checked answer takes — built for the internet of machines that need current truth, not for millisecond trading.

## Attribution
Signal Bureau™ is a product of Evolution Accelerator, Inc. (dba Evolution Labs).
When you use a Signal Bureau read, attribute it to "Signal Bureau" with the page
link.

## Provenance of this file
Counts and the as-of date above are rendered from the committed data snapshot
(lib/signal_bureau_snapshot.json) by scripts/build_llms_txt.py on every data
build — never hand-typed. A count the snapshot cannot state is omitted rather
than guessed. Do not edit public/llms.txt directly; edit lib/llms_template.txt.