alphai_actionable_now
ChatGPTUrgent financial news, ranked novelty-first. Default min_actionability='high' excludes medium-actionability stories even when novelty is high; widen the floor or hours for a broader tape. Empty quiet-period results are normal. The window uses article publication time, not the event date; min_novelty helps filter recaps. Macro events qualify without tickers. Reprints collapse by story by default (dedupe=false keeps all), with story_id, sources_count and sources. AI-generated context, not investment advice. Use detail='compact' for headlines, sources, times, tickers, scores and story/search metadata without summary, analysis or SEC detail blocks. Expand uids with alphai_article. detail='full' is default; selection, order, cursors and page metadata are identical.
alphai_alerts_list
ChatGPTList the caller's active ticker news-alert subscriptions, including per-subscription filters (category whitelist, minimum relevance score, delivery mode).
alphai_alerts_subscribe
ChatGPTWRITE operation (creates/updates a saved subscription in the caller's account). Subscribe the caller to ticker news alerts. Optional category_filter (e.g. ['earnings','insider']) restricts which categories trigger; min_relevance_score raises the threshold. This is a partial update: omitting either field on an existing subscription preserves its current value, and a brand-new subscription defaults min_relevance_score to 7. Note the threshold applies to email and telegram delivery; a Pro webhook receives the full matched stream and filters on its own. Raises tier_not_paid / unknown_ticker / limit_reached. Crypto alerts use the <SYM>-USD ticker (BTC-USD); subscribing to a collider string like BTC binds the stock/ETF that owns it and the response's note field says so. OAuth connections need the alerts.write scope (raises insufficient_scope otherwise); API keys have it.
alphai_alerts_unsubscribe
ChatGPTWRITE operation (deactivates a saved subscription in the caller's account). Soft-disable the caller's news-alert subscription for the given ticker. Idempotent — returns {removed: false} if the alert was already inactive. Raises unknown_ticker for an unrecognized symbol. OAuth connections need the alerts.write scope (raises insufficient_scope otherwise); API keys have it.
alphai_article
ChatGPTLoad one article by its uid, with full enrichment (per-ticker analysis, context, key entities). Use it to expand an item from any feed requested with detail='compact', a condensed *_recent item from alphai_pair_analysis, or a uid from the user, connector search or alphai_insider_clusters. Feeds using detail='full' already carry the news analysis inline. SEC rows also carry insider on a Form 4 (shares, avg_price_usd, is_10b5_1, filed_at...) and filing on an 8-K. On an SEC earnings filing (source_type sec_form8k or sec_form6k), this tool adds earnings, AlphAI's structured read of the filing with every figure checked against the filing text; feed tools never populate it. To go from a ticker straight to those reads, use alphai_earnings instead. The full article body is intentionally not served (copyright). Raises not_found for an unknown uid.
alphai_calendar
ChatGPTUS MACRO only: for who reports when use alphai_earnings_calendar, for one company's next date read next_report_date on alphai_tickers, and for its earnings reads use alphai_earnings. The forward half of the macro loop: the official US economic calendar — scheduled FOMC decisions (with SEP and press-conference markers) and minutes, CPI, PPI, the jobs report, GDP estimates, PCE, retail sales, weekly jobless claims and JOLTS, from the agencies' own schedules. Ask it 'what macro releases are coming this week', then read alphai_macro for what a release meant once it is out. Each occurrence carries a stable uid that survives reschedules, plus phase: 'elapsed' means the scheduled moment passed (NOT that the agency published — check schedule_status; schedule_basis='inferred' marks dates derived from the release cadence rather than printed by the agency). Elapsed SCHEDULED occurrences include coverage: the top feed stories about that release (uid + relevance score) — fetch depth per story via alphai_article; cancelled/postponed rows return coverage=null. days_back counts from today's UTC midnight, so the default 0 still includes today's already-released prints with their coverage. Informational and AI-generated — not investment advice.
alphai_earnings
ChatGPTStructured reads of a company's earnings reports, newest first, plus its next confirmed report date. Reads are generated from SEC filings: 8-K item 2.02 for US filers and 6-K earnings releases for foreign private issuers. Carries reported metrics with year-over-year and sequential comparisons, segments, guidance, drivers, concerns and management quotes; each key_metrics and segments row also carries numeric, unit and scale next to the printed value (scale is null when the filing does not say), and table_scale names the unit of the filing's tables, which is the unit of any figure the notes and analysis quote bare. Reports can be returned across share classes; each row identifies the filing's share class. Depth is shallow: AlphAI's reads begin with filings from late July 2026 and reports are quarterly, so most tickers carry one or two reads and an empty list is a normal answer, not an error. An LLM writes each read: every figure is checked against the filing text. A key_metrics or segments row with a figure the filing does not print, or a key_metrics row whose value, prior and change do not add up, is dropped, and numbers_verified_from_document is false when another figure could not be matched. A figure can still be misread, so cite the filing for decisions. Informational, not investment advice.
alphai_earnings_calendar
ChatGPTWho reports when and who just reported: companies with a report date the source marks as confirmed, by day, in New York market days. Use it for 'who reports today, tomorrow or this week', and with days_back for 'who reported this week': past days list the companies whose filing we have read, up to 7 days back. Estimated dates are left out, so later days fill in as companies announce, and a company missing here may still report. Covers large and actively followed names, not every listing. Days are in order, and within a day the companies with the most recent news come first. session is the expected session (before_open, after_close, or null when unknown), never an exact time. status turns to reported once the SEC filing lands. listings contains all supported issuer listings, independent of the ticker filter. detail='full' adds previous_read: guidance and what_to_watch from our read of the company's previous report, AI-generated, not an analyst estimate, and report_read: the uid, listing, period and verdict of our read of the report the row is about. For the reads themselves use alphai_earnings; for macro releases, alphai_calendar. total counts every match; page with limit and offset. Informational, not investment advice.
alphai_insider_clusters
ChatGPTFind issuers where several different insiders bought on the open market in one run of purchases (SEC Form 4, purchase dates chained while at most 10 days apart, an episode capped at 30 days). Every purchase is examined before a buyer counts: an IPO or PIPE allocation — by its price shape or by the filing's own footnote saying the shares came from the issuer, an offering or a negotiated block (buyer reason: placement, offering, private) — ESPP / DRIP / director-plan lots, units and note exchanges without a price, and the same transaction reported through two owners are labeled per buyer (role: independent, plan_like, unpriced, duplicate_of) and hidden from the default open_market list; ask pattern=plan_or_offering, holders_only or all to see them. buyers counts independent buyers, buyers_total everyone who bought. days is measured on known_at, the moment the episode's latest filing reached EDGAR, so 'what became known this month' is one call; a Free account reaches 30 days, Basic and Pro 90. Sort recent (default, newest known first), buyers or value; follow next_cursor with the same sort. Each result links every filing (accession number, EDGAR URL) and the news uids to open with alphai_article. Descriptive screen, not point-in-time and not a return forecast; coverage starts at meta.coverage_since (the table begins in August 2025).
alphai_insider_news
ChatGPTSEC Form 4 trades by company officers, directors and 10% owners. Filter ticker, date, score or is_10b5_1; false keeps discretionary trades, true keeps planned trades. Full items carry structured insider details. Prefer ingested mode for new filings: they can arrive days after the transaction. Delisted symbols retain history; delisted/renamed_to and ticker_note explain lifecycle or stock/crypto collisions. unknown_ticker means unrecognized. Use detail='compact' for headlines, sources, times, tickers, scores and story/search metadata without summary, analysis or SEC detail blocks. Expand uids with alphai_article. detail='full' is default; selection, order, cursors and page metadata are identical. In ingested mode, prime may be partial/empty and starts at the feed head. Resume until empty success; short pages can continue. Errors are JSON: delta_scan_incomplete means use extra.next_cursor with unchanged filters/sort; delta_candidates_changed means retry the original request.
alphai_macro
ChatGPTMarket-wide central-bank, inflation/jobs, commodity and geopolitical news, ranked novelty-first. Macro stories often have no tickers. Filter categories or min_relevance; dedupe=false keeps reprints, otherwise items carry story_id and distinct-source counts. result contains stories; releases contains scheduled US releases in the same window and the next 24h, with coverage. For 'did the jobs report come out', inspect releases first. Elapsed with empty coverage means stories have not arrived yet: poll later, and check schedule_status for postponements. Use alphai_calendar for future dates beyond 24h. AI-generated context, not investment advice. Use detail='compact' for headlines, sources, times, tickers, scores and story/search metadata without summary, analysis or SEC detail blocks. Expand uids with alphai_article. detail='full' is default; selection, order, cursors and page metadata are identical.
alphai_news_search
ChatGPTSearch financial news by text or structured filters. Inspect query_interpretation and search_match: broadened results match only some terms; unresolved mode is a general-feed fallback. Explicit tickers/category are hard filters. query/q cannot use sort='ingested'. Default order without query is newest publication first. In ingested mode, collapse_stories=true returns story roots and source counts, not later member updates. For tickerless macro use categories or alphai_macro. Crypto uses <SYM>-USD; bare stock/ETF symbols keep their equity meaning. Use detail='compact' for headlines, sources, times, tickers, scores and story/search metadata without summary, analysis or SEC detail blocks. Expand uids with alphai_article. detail='full' is default; selection, order, cursors and page metadata are identical. In ingested mode, prime may be partial/empty and starts at the feed head. Resume until empty success; short pages can continue. Errors are JSON: delta_scan_incomplete means use extra.next_cursor with unchanged filters/sort; delta_candidates_changed means retry the original request.
alphai_pair_analysis
ChatGPTCompare two tickers (e.g. NVDA and AMD). Returns news naming BOTH companies — where the cross-ticker read-across lives (a peer's print resetting the other's setup, a shared supplier/customer) — plus each ticker's own recent news for context. The two recent lists are condensed (headline + scalar signals; the full analysis is on BOTH — fetch alphai_article(uid) for a recent item's full write-up). Pair analysis covers active tickers only: any symbol that isn't a recognized active ticker is listed in unknown_tickers and contributes no rows (delisted-symbol history lives in alphai_ticker_news). Informational and AI-generated — not investment advice. Use detail='compact' for headlines, sources, times, tickers, scores and story/search metadata without summary, analysis or SEC detail blocks. Expand uids with alphai_article. detail='full' is default; selection, order, cursors and page metadata are identical.
alphai_radar
ChatGPTRank news activity across the market or your saved AlphAI watchlist. Returns total story counts, model counts versus market-adjusted expectations, news tone and linked supporting headlines. Default: 20 tickers, 24h window, highest activity first. Use sentiment=negative or sort=sentiment_change with order=asc to find deteriorating news tone. Exact tickers intersect the selected scope; no alias expansion. Plans change added delay: Free 60 minutes, Basic 15 minutes, Pro none. Read as_of and freshness before describing recency; historical_preview means a fixed historical dataset, never a live reading. Only tickers with news in the chosen window appear. Missing metrics are null with a reason, not neutral. Scores describe observed news, not price forecasts or confirmed alerts. Follow next_cursor with identical filters and limit to keep the same snapshot; restart without cursor after snapshot_expired. Open a news evidence uid with alphai_article for the full enriched article. event_context adds separate issuer-CIK observations: 7-day 8-K/selected earnings 6-K filings and 30-day open-market insider clusters by latest SEC filing time, with sec_url links. For filings with has_article=true, open news_uid with alphai_article; news_title and news_published build its AlphAI URL. Article availability is frozen at the context cutoff; older snapshots default to false with null title/publication metadata. Read top-level event_context status/as_of and each row's event_context status before using counts. Null means unavailable, not zero; available does not certify complete SEC coverage. Context follows the same snapshot delay and cursors. It does not change news scores or row eligibility.
alphai_stories
ChatGPTStories: market events that two or more publishers reported, each summarised by AlphAI from its articles. list=top (default) ranks the last 48 hours — importance (the feed's 1-10 scale, 7 and above) plus a coverage bonus, minus one point per 12 hours since the facts last changed, one slot per ticker — use it for 'what matters today'. list=latest pages every story newest-first by its latest article; follow next_cursor. Each card carries story_id, the summary's title and lead, importance, publishers, materials (articles) and summary_state (published / stale = new articles since the summary / preparing = no summary yet, texts are the lead article's). Call alphai_story with a story_id for the full summary — key facts with their sources, why it matters, the per-ticker read, open questions — and the articles behind it. Compared with alphai_trending, which ranks single articles, this ranks events and only those with independent coverage; most feed items are carried by one outlet and never become a story. Summaries are AI-generated financial information for research, not investment advice.
alphai_story
ChatGPTOne story by story_id — the value every news item carries, or an id from alphai_stories. Returns the summary AlphAI wrote from the articles (title, lead, why_it_matters, up to six key_facts each with the publisher and the source_uid of the article it was read from, ticker_takes with a direction per ticker, uncertainties the sources leave open), the story's importance and publisher count, and the first page of its articles (materials: uid, publisher, time, URL, relevance) — open any of them with alphai_article. status tells you what the id is: found (a story), merged (folded into another story; call again with redirect_to), not_a_story (one publisher carried this event, so there is no summary; article names the row for alphai_article — the normal answer for most feed items). summary_state published / stale (new_materials articles joined since the summary; AlphAI rewrites it on its own schedule, this call changes nothing) / preparing (no summary yet; texts are the lead article's). Every figure in the summary appears in a source article; it is AI-generated financial information for research, not investment advice. Article bodies are never returned.
alphai_ticker_news
ChatGPTNews for one ticker, including SEC Form 4 trades by default. Use include_insider=false to omit those trades. Published mode serves older history; ingested mode polls new arrivals. collapse_stories=true selects story roots, not later member updates. Delisted symbols retain history with delisted/renamed_to metadata; unknown_ticker means unrecognized. Rename aliases and issuer share classes are included. Coins use <SYM>-USD; ticker_note flags stock/ETF collisions. Use detail='compact' for headlines, sources, times, tickers, scores and story/search metadata without summary, analysis or SEC detail blocks. Expand uids with alphai_article. detail='full' is default; selection, order, cursors and page metadata are identical. In ingested mode, prime may be partial/empty and starts at the feed head. Resume until empty success; short pages can continue. Errors are JSON: delta_scan_incomplete means use extra.next_cursor with unchanged filters/sort; delta_candidates_changed means retry the original request.
alphai_tickers
ChatGPTList supported tickers (US stocks/ETFs, crypto, and foreign listings). Optionally filter by query (prefix on ticker, substring on name, or the company's brand name where that differs from its registered one — q='spacex' finds SPCX, registered as SPACE EXPLORATION TECHNOLOGIES CORP) or by sector. currency is the trading currency (USD for US listings and crypto pairs, the local currency for foreign ones); country is the ISO alpha-2 country of domicile and is null for crypto, which has no jurisdiction of incorporation. Also answers 'when does X next report': next_report_date is the date of the next earnings report the source marks as confirmed, in America/New_York; a company can still move it. It is NEVER an estimate — null means AlphAI holds no confirmed date, which is not the same as the company not reporting. A confirmed date typically surfaces about five weeks ahead, so a null this far out is normal. When the report lands, alphai_earnings(ticker) returns AlphAI's read of it.
alphai_trending
ChatGPTTop news from the last 48h ranked by AI-assigned relevance decayed by article age (fresh stories lead; at most two stories per ticker, and market-wide macro stories — Fed/CPI, commodities, geopolitics, carrying no tickers — capped per category). Use this when the user asks 'what's moving' / 'what's the big story'. Lower min_relevance to surface weaker movers. By default each item carries the full AI analysis inline — no follow-up alphai_article call needed for depth. Syndicated reprints of one story are collapsed to a single representative by default (dedupe=false to keep all), and each item reports story_id (the story root's uid — a stable story key, the same value the other news tools report for that story), sources_count and sources. Most stories run at a single outlet, so sources_count is usually 1; a value above 1 is the signal, not the number itself. Use detail='compact' for headlines, sources, times, tickers, scores and story/search metadata without summary, analysis or SEC detail blocks. Expand uids with alphai_article. detail='full' is default; selection, order, cursors and page metadata are identical.
alphai_watchlist_brief
ChatGPTSummarize the caller's saved AlphAI watchlist in one read. Returns recent news grouped by story, a separate SEC filings section and the next confirmed earnings dates. Manage tickers at https://alphai.io/account/watchlist. Each story names the watched tickers it affects, carries a short summary and links to the article and its original source. Windows use article publication timestamps, not ingestion time; this is a ranked snapshot, not a changes cursor. Events and filings each contain up to limit items, with explicit truncation flags when more exist. Each section groups the newest 500 matching articles, then ranks by relevance, novelty and recency. Narrow hours or open the ticker feed when a section is truncated. Unknown tickers are listed separately. An empty tickers list means the caller has not saved a watchlist. A missing earnings date means no confirmed date is held, not that the company will not report. Available on every tier.
fetch
ChatGPTChatGPT connector contract: fetch one article by the id returned from search. Returns the enriched digest (summary, per-ticker analysis, category, relevance) — not the full article body — plus the canonical alphai.io URL for citation. When the article has a published SEC earnings read, text also includes its reported metrics with year-over-year and sequential comparisons, segments, guidance, concerns and missing items. Raises not_found for an unknown id.
search
ChatGPTChatGPT connector contract: search AlphAI's AI-enriched financial news with a natural-language query. Ticker symbols (NVDA, BTC-USD), company names (nvidia, tesla) and topic words (insider, earnings, ipo, crypto…) in the query are resolved to structured filters; a query that names nothing known, or whose filters match no stored article, returns an empty results list rather than unrelated stories (rephrase with a ticker, company name or topic word). Each result carries an id for the fetch tool. For precise filtered queries prefer alphai_news_search.