io.github.evolutionlabs-dev/signal-bureau

Ask what the tracked record shows about a named entity or unfolding event: what changed, what the record holds now, and which sources corroborate it. Not general knowledge or history — grounding is live tracked coverage. 25 questions a day per network address need no key; then each costs one Read on a free key (POST /api/keys). Async — a ticket in ~1s, collected with get_answer.

Assemble a basket and get exact prices plus Stripe checkout links. Checkout runs on Stripe's hosted page, completed by whoever holds the payment credentials. Pass dryRun:true to REHEARSE: same validation, same price math, clearly labeled, no order recorded, no links issued, nothing billed — integration-test the full flow risk-free. Item ids — plans: 'pilot', 'desk-private', and 'api' (the Metered API account: your identified key — self-issue one FREE at POST /api/keys, no human in the loop — with billing activated by the desk on this order, usage billed monthly at tariff rates, nothing preset — get_quote prices your exact basket first, get_account shows the live statement); unit: 'watch' (reads of the watched question included); and 'balance' — a BALANCE on your own key, funded once with an `amount` in USD (min $5, max $500) and drawn down at the flat published Read rate as you ask. Reads are metered per use at the flat tariff rate and are never sold as PREPAID PACKS — a pack is a discounted bundle sized to your guess about how much you will use, and we do not sell one. A BALANCE is a different thing and is sold: the same meter funded in advance, at LIST, no discount, no expiry, no minimum draw, unused balance refundable in full on request. It exists so your principal fills a card form ONCE, ever, instead of once per purchase. Live UNIT prices come from /api/tariff and this description states none of them — the balance band above is a limit on what you may FUND, not a price. Watch topics are SELF-SERVE end to end: pass `topics` and every one comes back with a checkout link at the published Watch rate — including a topic nobody watches yet, whose price the desk mints on demand with no human in the loop (that one needs your identified key, free and self-issued in one call at POST /api/keys, and arrives in minutes; poll get_order or the statusUrl on the line). The api line still records intent and the desk activates the account. Every line states its own state and wha…

Your meter-account statement, live: month-to-date metered Reads counted at the published tariff, your watched topics with billing/billing status and their acceptance evidence, and your daily cap. Requires your identified key on the request (x-api-key header, or authorization: Bearer sb_live_...). Without a key this tool explains how to get one — every read surface stays available in the free anonymous lanes either way. Recognition is opt-in via credential: no key, no tracking.

Collect an async answer by ticketId (from ask). Free and unmetered — the work was paid for once at submit. status:'working' → poll again after pollAfter seconds; 'done' → the complete answer rides in this response; 'failed' or 'lost' → the reason, stated plainly, and asking again is the remedy.

Deprecated: this tool is winding down — for evaluating or reading the maintained record, use get_topic_record, get_entity/search_entities, and todays_brief instead. Still served here: the grading dataset for the market sensor we cite, and only that — the prediction-market price (`crowd`) and the naive null it is scored against (`base_rate`), against how reality resolved (Brier score, log loss, skill vs base rate, 95% CIs), each price captured while its market was OPEN and graded as it matured, so the grade cannot be back-filled. No forecaster of ours is published, here or in the full dataset: we sell a maintained, source-traced record and cite market prices as one graded sensor, not a forecast of ours. Full dataset with reliability bins: GET /api/calibration-data.

What separate sources agreed on in the published window — the maintained record's corroboration layer. Each event carries the claim as its sources state it, the corroboration tier, two counts — publisherCount (distinct outlets that carried it) and originCount (separate evidentiary origins: a wire republished by fifteen outlets, two pages behind one address, or three outlets relaying what one named outlet reported each count once) — the publishers by name with wires marked, the earliest report date when the run carries one, and the entities. The tier is computed from originCount. Neither count is verification: an outlet that names no upstream still counts as its own origin, and many outlets echoing one official statement is consensus. independentOrigins is a deprecated alias of the publisher count. No probability here is ours. Returns state="cannot-measure" with a reason when the corroboration pass could not be read — never an empty list dressed as a quiet week.

A newsletter DESK's machine feed at one predictable, slug-addressable location: up to 14 days of the desk's observed items (title, url, source), newest-first, from the same panel the human edition reads. Unlike watch topics, the desk roster is PUBLIC PRODUCT — the desks are: cognitive-investor, tax-nexus, crc-kras, crc-digest, space-economy, paradise-valley, lyt-intel, aztc-aasd, newspace-asu, lq-listening, jedi-knowledge, ud-articles, ecomm-news — so an unknown-desk reply lists them freely. Delivery is keyed (your self-issued key, x-api-key): identified delivery is the standard shape for standing feeds. Desks are priced as labeled topic bundles at the published Watch rate — see DESK_BUNDLES on /api/tariff and get_quote for your exact basket. Each feed's payload declares its own coverage state.

Full dossier for one entity: signal count, verticals it's spreading across, and why it's surfacing.

Tracked world events (situations, races, negotiations) the engine follows as named arcs — each with its entities, related market-question count, cross-domain mention volume, and first/last-seen dates. Optional query filters by name or entity.

The state of a report you filed via send_feedback, by its feedbackId: filed, working, or resolved — with its work-order reference. A report filed in the last few hours may still read 'filed'; the response states where it is.

Re-read an order intent created by create_order — the recorded basket and its honest status. Poll it after forwarding create_order's `handoff` note: it re-resolves each topic's payment link against the current registry, so a link still being minted shows up here when ready. Payment truth for checkout purchases lives with Stripe (the payer's receipt is authoritative); metered work is receipted on your meter account and readable via get_account.

Feed in your requirements — free-form concerns, questions, whole areas of interest — and get back an enumerated quote: your requirements intelligently grouped and disambiguated into well-formed watched topics, then checked BY CODE, topic by topic, against what we actually read: a topic is priced ($20/topic/month at the opening rate) ONLY when a desk, a Watch we keep or a standard Watch reads it from sources with an item in the last 7 days. Every topic carries `coverage` — its state (covered, gap, or cannot-check with the reason), the sources, how many and how fresh. Gaps come back under `coverageRequests` at $0, never billed, each with the free propose_topic call that asks us to start keeping it; `coverage.summary` says it in one line. A model proposes the topics; it never decides what is sold. The count is disclosed in BOTH directions: overlaps are merged, broad requirements are split into the separate daily reports they actually need, and `billing.expansion` states the requirement-to-topic ratio outright so a split is as visible as a merge. Large baskets are resolved in batches, so a requirement the desk cannot place does not sink the rest: you get a quote for everything it could place, `partial: true`, and `unresolvedRequirements` naming what it could not and why — never a topic invented to cover a gap. A quote is not a charge, needs no contact details, and holds for 30 days. Real model work: ~10 quotes/day per network address (shared egress shares the allowance).

Deprecated: this tool is winding down — for evaluating or reading the maintained record, use get_topic_record, get_entity/search_entities, and todays_brief instead. Still served here: the correction record — the flagged-vs-control repricing regression at population level (estimate, 95% CI, cohort sizes, window, as-of), plus the dated retirement object for the case-study track record we withdrew in 2026 when re-measurement put it under our own publication bar. Appended, never edited — including about ourselves. Same object: GET /api/record-data.

START HERE for browsing — the cheap read (500/day, no model work). The full machine-readable signal feed (same payload as GET /api/signals): every entity currently flagged by the attention engine, with trajectory, domains, desk membership, and an explicit evidenceStatus (receipted rows carry source-attributed evidence URLs; unreceipted rows are labeled leads). Measured property: Measured association: flagged markets repriced materially at 1.47x the rate of matched unflagged controls (95% CI 1.35-1.62, shock-days excluded, controls reweighted to the flagged cohort; n=2769 flagged vs 110528 controls, window 2026-03-29 to 2026-10-06, as of 2026-10-06). An attention-leads-movement association — never a directional claim.

The maintained record for one subject — the ONE file its /exhibit page renders from and GET /api/record/{slug} serves (the earlier names get_truth_record and GET /api/truth/{slug} answer identically, permanently), so their numbers agree by construction and a value-parity gate fails the build if they stop: what the subject is, the first-party documents we read, the claims and how many separate publishers carried each, our own attention, the prediction-market prices we cite (never a probability of ours) split into `live`, `historical` (deadline passed) and `undated` questions, the change log, and what this record cannot see. `currency` is never better than its weakest layer; `currency.layers` gives each layer's own data cutoff, compute date and state (current, behind, cannot-measure). Every subject on the publication registry carries one. Free — public record, no key, no charge. With no argument you get the flagship record (hormuz today, and it rotates). Three answers, never two: `served` with the record; `not-registered` when we read the registry and do not maintain that subject (a measured absence); `cannot-measure` when the record store could not be read (the record may well exist — we could not look). Subjects served today: hormuz, interest-rates, us-midterms-2026, ai-model-race, israel-iran-conflict, russia-ukraine-war, gaza-ceasefire, brazil-election, us-presidential-2028, strait-of-hormuz, fed-rate-decision, venezuela-crisis, uk-election, us-recession-2026, disaster-event-hurricane, disaster-event-atlantic-hurricane, product-launch-spacex-starlink, election-michigan-republican, product-launch-spacex, election-republican-republicans, election-alabama-republican, election-arkansas-republican, election-brazil, election-brazil-senate, legal-ruling-supreme-court, election-republican, election-republican-republican-party, ceasefire-peace-iran, election-michael, election-darline-graham-graham, election-darline-graham-republican, economic-indicator-inflation, election…

The structured daily delivery for a machine-watched topic: up to 14 days of observed items (title, url, source, date) newest-first, plus the topic's live coverage-acceptance report, which grades the coverage and shows the evidence (it does not gate billing — billing starts when the Watch starts, and the month you are in is refundable in full, any time you ask, for any reason). Delivery is pull: poll daily or on demand. Topics not yet watched: get_quote prices them.

Watches: configure and unfurl free; saving is the paid step. Your saved Watches, newest version of each, active and retired. Needs your key. Same content as GET /api/v1/watches.

Watches: configure and unfurl free; saving is the paid step. The free standard Watches, each with every coordinate explicit, plus the published terms: what saving a Watch costs (read from the tariff), what it includes, and its limits. Free; no key. Same content as GET /api/v1/watches/standard.

Propose NET-NEW coverage — a topic, entity, or standing question we don't track yet. Files into the coverage-request queue humans review; accepted topics enter the provisional coverage lane and start appearing in the signal feed. Needs your human principal's contact email for follow-up. Free.

Watches: configure and unfurl free; saving is the paid step. Recall a saved Watch: its reading now (sb.watch-reading.v1) and what changed since the last time it was delivered to you. Recording this delivery is what makes the next recall's change exact. Needs your key. Same content as GET /api/v1/watches/%7BwatchId%7D.

Watches: configure and unfurl free; saving is the paid step. Retire a saved Watch: it stops being recallable and frees its paid slot. Nothing is deleted; its versions and deliveries are kept. Needs your key. Same content as POST /api/v1/watches/%7BwatchId%7D with {"action":"retire"}.

Watches: configure and unfurl free; saving is the paid step. Save a Watch to your key so you can recall it from any door and be told what changed since your last delivery. Saving is the paid step, at the published Watch rate per saved Watch per month (see list_standard_watches terms); with no free paid slot the answer is a plain payment-required with the next step, and nothing is saved or charged. Pass watchId to edit a Watch you saved: that is a new version and costs nothing more. Either start from a standard Watch (base; these read the Strait of Hormuz record) or name your own domain (domain + topics, from get_quote). For a domain, the coverage check runs again here and only covered topics are kept; no reading builder is published for this domain yet, so its reading is cannot-measure per topic and it is never served a standard Watch's reading. A domain Watch is saved free, as pending coverage, until a reading for it is published; a domain with no covered topic is refused with the reason and nothing is charged. Needs your key. Same content as POST /api/v1/watches.

Find tracked entities/topics by name or vertical (e.g. 'iran', 'semiconductors').

File structured feedback with the desk: a bug, an improvement, a complaint, praise, or a question about the service itself. Free, no contact details required; limits stated up front: 5/minute, 20/day per network address (shared egress shares the allowance). A complaint that names a real defect becomes our work order — house policy — and get_feedback_status lets you watch the state move by feedbackId. Include `ref` (a quoteId/ticketId/orderId from your own records) to tie the report to a specific interaction. The response says honestly whether the report was durably recorded.

START HERE — first call, no arguments, no key, no charge. Who Signal Bureau is and what we are not, the tests you can run to check that claim yourself, what is free (most of it), what is paid (Watches and Reads) at live published prices, how to propose coverage we don't carry, and how buying works. Read this before evaluating anything else here.

Today's morning brief — the daily synthesized narrative of what moved across the information environment and what to watch, from the engine's cross-domain analysis. Same content as the public /today page. Carries `gaps` (where prediction-market money and the day's coverage disagree) and `watch` (what would change the story); every market figure in either arrives with the contract URL behind it, or the figure is withheld and the row says so.

The entities/topics accelerating most across the information environment right now, ranked by cross-domain attention.

To see how the record fits together, start at an entity or event (e.g. Hormuz) and traverse its maintained relationships; each step returns its relation type, receipts, standing and time. Walk the maintained record node to node. Opens ONE node (schema sb.node.v1): an entity, a situation, a corroborated claim or a co-mention relation, with its identity, standing (five separate records, never one score), as-of cutoff, provenance, and its neighbours folded as counts plus the first page of typed refs. Follow any returned id, or pass a returned cursor, to open the next level. Start from a name: id "entity:hormuz" or "event:strait-of-hormuz"; or from an id: "sb:e/…", "sb:p/…", "sb:r/…". Same object as GET /api/v1/node/{kind}/{hex}. Free, no key. Limits are published in every node: One level per call: depth is 1 and only 1, and there is no whole-graph dump. pageSize 1-50 (default 10); a page limit is a cursor, never an edge. Members are listed up to 50. At most 60 traverse calls a minute per caller (runaway-loop protection, not a meter). One knowledge cutoff is served: the deploy's. A level we could not read says cannot-measure with the reason, never an empty list; an unknown id is a 404 with code node_not_found. Projected from today's graphs (build.plane), not the maintained world state.

Watches: configure and unfurl free; saving is the paid step. Configure a Watch and run it once, without saving: the governed reading (sb.watch-reading.v1) plus a line per coordinate saying whether it was applied. Free, as often as you like; no key. Either start from a standard Watch (base; these read the Strait of Hormuz record) or name your own domain (domain + topics, from get_quote). For a domain, the coverage check runs again here and only covered topics are kept; no reading builder is published for this domain yet, so its reading is cannot-measure per topic and it is never served a standard Watch's reading. Same content as POST /api/v1/watches/unfurl.