Model

Equity research analyst: 21 ways to use Ora

Covers a sector: earnings previews and reviews, estimate beats, dividends and the tape. Each example is a complete, runnable request with the real answers it returned (42 requests, captured 2026-10-31), what they mean and, where it fits, the action it would send.

Run withAnswers were captured on ora-fin-0.1.1. Another model changes the request JSON and the Playground link; run it there to see its answers.

Rule functions and facts used by this player (69)

sma 13 days_to_earnings 5 beat_eps_last 4 last_earnings_gap 4 last_eps 4 abs 3 last_earnings_move 3 eps_surprise_pct 3 raised_last 3 max 3 beat_streak 2 pre_earnings_close 2 ema 2 div_yield_ttm 2 years_of_growth 2 days_since_earnings 2 eps_year_ago 2 offset 2 adx 2 diminus 2 diplus 2 days_to_split 2 beats_last4 1 beat_revenue_last 1 eps_growth_yoy 1 roc 1 cut_last 1 macd 1 macdsignal 1 revenue_growth_yoy 1 revenue_surprise_pct 1 linreg 1 log 1 ref 1 sqrt 1 std 1 days_since_split 1 last_split_ratio 1 reverse_split_last 1 splits_5y 1 atr 1 cci 1 willr 1 next_report_amc 1 next_report_bmo 1 miss_eps_last 1 misses_last4 1 swinghigh 1 swinglow 1 hlc3 1 median 1 obv 1 percentrank 1 sum 1 harami_bull 1 morning_star 1 piercing_line 1 tweezer_bottom 1 rsi 1 wma 1 barssince 1 highest 1 highestbars 1 last_div_amount 1 last_eps_est 1 last_revenue 1 next_split_ratio 1 prev_div_amount 1 revenue_year_ago 1

Examples 1–10 of 21 · page 1 of 3

Equity research analyst · example 1

NVDA earnings preview: date, streak and setup into the print

Build the preview note: when NVDA reports, its beat record, how it reacted last time, and whether the stock goes into the print in an uptrend.

ora-fin-0.1.1NVDA6 questions

StateNVDA
Questions6 asked
Answersreal, captured
Actionsnone

State

{"symbol":"NVDA"} The server fills in the latest completed session.

Questions

`soon`	rule	`days_to_earnings <= 10` Reports earnings within 10 days
`streak`	rule	`beat_streak >= 4` Beat four quarters in a row
`beats3`	English → rule	Has the stock beaten EPS estimates in at least 3 of the last 4 quarters?
`big_react`	rule	`abs(last_earnings_move) > 5` Last earnings move bigger than 5%
`trend_in`	rule	`days_to_earnings <= 10 and C > sma(C, 50)` Earnings within 10 days, above the 50-day
`beat_next`	forecast	Will the stock beat earnings next quarter? Beating earnings next quarter

Answers

Question	Answer	Reading
`soon` Reports earnings within 10 days	0.0563	false
`streak` Beat four quarters in a row	0.9463	true
`beats3` Has the stock beaten EPS estimates in at least 3 of the last 4 quarters compiled to `beats_last4 >= 3`	0.8591	true
`big_react` Last earnings move bigger than 5%	0.9463	true
`trend_in` Earnings within 10 days, above the 50-day	0.0563	false
`beat_next` Beating earnings next quarter	0.516	52% · close to even

What it means

For NVDA on the session of 2026-10-30: True now: Beat four quarters in a row; Has the stock beaten EPS estimates in at least 3 of the last 4 quarters; Last earnings move bigger than 5%. Not true: Reports earnings within 10 days; Earnings within 10 days, above the 50-day. Forecasts: Beating earnings next quarter 52%.

The facts fill the preview table directly; the beat-next-quarter forecast is shown as odds, separate from the analyst's own estimate.

Request JSON

{
  "model": "ora-fin-0.1.1",
  "state": {
    "symbol": "NVDA"
  },
  "questions": {
    "soon": {
      "type": "yes_no",
      "ask": "days_to_earnings <= 10"
    },
    "streak": {
      "type": "yes_no",
      "ask": "beat_streak >= 4"
    },
    "beats3": {
      "type": "yes_no",
      "instructions": "Has the stock beaten EPS estimates in at least 3 of the last 4 quarters?"
    },
    "big_react": {
      "type": "yes_no",
      "ask": "abs(last_earnings_move) > 5"
    },
    "trend_in": {
      "type": "yes_no",
      "ask": "days_to_earnings <= 10 and C > sma(C, 50)"
    },
    "beat_next": {
      "type": "yes_no",
      "instructions": "Will the stock beat earnings next quarter?"
    }
  }
}

Response JSON (NVDA, real)

{
  "model": "ora-fin-0.1.1",
  "answers": {
    "soon": {
      "yes_no": 0.0563,
      "rule": "days_to_earnings <= 10",
      "basis": "rule"
    },
    "streak": {
      "yes_no": 0.9463,
      "rule": "beat_streak >= 4",
      "basis": "rule"
    },
    "beats3": {
      "yes_no": 0.8591,
      "rule": "beats_last4 >= 3",
      "basis": "pattern"
    },
    "big_react": {
      "yes_no": 0.9463,
      "rule": "abs(last_earnings_move) > 5",
      "basis": "rule"
    },
    "trend_in": {
      "yes_no": 0.0563,
      "rule": "days_to_earnings <= 10 and C > sma(C, 50)",
      "basis": "rule"
    },
    "beat_next": {
      "yes_no": 0.516
    }
  },
  "context": {
    "symbol": "NVDA",
    "as_of": "2026-10-30"
  }
}

abs beat_streak beats_last4 days_to_earnings last_earnings_move sma

Try it in the Playground

Equity research analyst · example 2

JPM earnings review: beat on both lines, and did the stock hold?

After the bank reports, document whether EPS and revenue beat, the surprise size, the gap, and whether the stock holds above its pre-report close.

ora-fin-0.1.1JPM6 questions2 actions

StateJPM
Questions6 asked
Answersreal, captured
Actions2 rules · dry run

State

{"symbol":"JPM"} The server fills in the latest completed session.

Questions

`both`	rule	`beat_eps_last > 0.5 and beat_revenue_last > 0.5` Beat on EPS and revenue last quarter
`surprise`	rule	`eps_surprise_pct > 5` EPS beat by more than 5%
`rev_beat`	English → rule	Did revenue beat estimates last quarter?
`gap`	rule	`last_earnings_gap > 0` Gapped up after the last report
`above_pre`	rule	`C > pre_earnings_close` Holding above the pre-earnings close
`eps_g`	rule	`eps_growth_yoy > 10` EPS up more than 10% on the year

Answers

Question	Answer	Reading
`both` Beat on EPS and revenue last quarter	0.1409	false
`surprise` EPS beat by more than 5%	0.0844	false
`rev_beat` Did revenue beat estimates last quarter compiled to `beat_revenue_last > 0.5`	0.1409	false
`gap` Gapped up after the last report	0.9463	true
`above_pre` Holding above the pre-earnings close	0.6505	true
`eps_g` EPS up more than 10% on the year	0.6893	true

Actions

Rules on the answers decide what to send.

both >= 0.6→Emailresearch-team

else→Emailresearch-team

What each action would send 1 of 2 fired · dry run, nothing sent

review_noterule false: skipped

mixed_notewould send (dry run)Email → research-team

{
  "subject": "JPM review: mixed quarter (2026-10-30)",
  "text": "JPM did not beat on both lines (rule 14%). Revenue beat: 14%. EPS growth over 10%: 69%."
}

What it means

For JPM on the session of 2026-10-30: True now: Gapped up after the last report; Holding above the pre-earnings close; EPS up more than 10% on the year. Not true: Beat on EPS and revenue last quarter; EPS beat by more than 5%; Did revenue beat estimates last quarter. Fired: mixed_note (Email → research-team).

Either branch drafts the review email to the team; the analyst adds the why, the facts are already in it.

Request JSON

{
  "model": "ora-fin-0.1.1",
  "state": {
    "symbol": "JPM"
  },
  "questions": {
    "both": {
      "type": "yes_no",
      "ask": "beat_eps_last > 0.5 and beat_revenue_last > 0.5"
    },
    "surprise": {
      "type": "yes_no",
      "ask": "eps_surprise_pct > 5"
    },
    "rev_beat": {
      "type": "yes_no",
      "instructions": "Did revenue beat estimates last quarter?"
    },
    "gap": {
      "type": "yes_no",
      "ask": "last_earnings_gap > 0"
    },
    "above_pre": {
      "type": "yes_no",
      "ask": "C > pre_earnings_close"
    },
    "eps_g": {
      "type": "yes_no",
      "ask": "eps_growth_yoy > 10"
    }
  },
  "actions": [
    {
      "id": "review_note",
      "when": "both >= 0.6",
      "do": "email",
      "connection": "research-team",
      "subject": "{{symbol}} review: beat on EPS and revenue ({{as_of}})",
      "message": "{{symbol}} beat on both lines ({{both|pct}}). Surprise over 5%: {{surprise|pct}}. Gapped up: {{gap|pct}}. Holding above the pre-report close: {{above_pre|pct}}."
    },
    {
      "id": "mixed_note",
      "when": "else",
      "do": "email",
      "connection": "research-team",
      "subject": "{{symbol}} review: mixed quarter ({{as_of}})",
      "message": "{{symbol}} did not beat on both lines (rule {{both|pct}}). Revenue beat: {{rev_beat|pct}}. EPS growth over 10%: {{eps_g|pct}}."
    }
  ],
  "dry_run": true
}

Response JSON (JPM, real)

{
  "model": "ora-fin-0.1.1",
  "answers": {
    "both": {
      "yes_no": 0.1409,
      "rule": "beat_eps_last > 0.5 and beat_revenue_last > 0.5",
      "basis": "rule"
    },
    "surprise": {
      "yes_no": 0.0844,
      "rule": "eps_surprise_pct > 5",
      "basis": "rule"
    },
    "rev_beat": {
      "yes_no": 0.1409,
      "rule": "beat_revenue_last > 0.5",
      "basis": "pattern"
    },
    "gap": {
      "yes_no": 0.9463,
      "rule": "last_earnings_gap > 0",
      "basis": "rule"
    },
    "above_pre": {
      "yes_no": 0.6505,
      "rule": "C > pre_earnings_close",
      "basis": "rule"
    },
    "eps_g": {
      "yes_no": 0.6893,
      "rule": "eps_growth_yoy > 10",
      "basis": "rule"
    }
  },
  "context": {
    "symbol": "JPM",
    "as_of": "2026-10-30"
  },
  "actions": [
    {
      "id": "review_note",
      "fired": false,
      "status": "skipped"
    },
    {
      "id": "mixed_note",
      "fired": true,
      "status": "dry_run",
      "do": "email",
      "connection": "research-team",
      "preview": {
        "subject": "JPM review: mixed quarter (2026-10-30)",
        "text": "JPM did not beat on both lines (rule 14%). Revenue beat: 14%. EPS growth over 10%: 69%."
      }
    }
  ]
}

beat_eps_last beat_revenue_last eps_growth_yoy eps_surprise_pct last_earnings_gap pre_earnings_close

Try it in the Playground

Equity research analyst · example 3

Semiconductor coverage sheet: AMD, MU, TXN, QCOM, INTC

One row per covered chip name: trend, momentum, last quarter's beat and next report date, for the weekly sector pack.

ora-fin-0.1.15 symbols, one request each5 questions

State5 symbols
Questions5 asked
Answersreal, captured
Actionsnone

State

{"symbol":"AMD"} then MU, TXN, QCOM, INTC, one request each. The server fills in the latest completed session.

Questions

`trend`	rule	`C > ema(C, 20) and ema(C, 20) > sma(C, 50) and sma(C, 50) > sma(C, 200)` Stacked averages: close > 20 EMA > 50 > 200
`momentum`	rule	`roc(C, 20) > 5` Up more than 5% in 20 sessions
`beat`	English → rule	Did the stock beat EPS estimates last quarter?
`earn_soon`	English → rule	Is earnings in the next 14 days?
`beat_spy`	forecast	Will it beat SPY over the next month? Beating SPY over a month

Answers

Symbol	`trend`rule	`momentum`rule	`beat`rule	`earn_soon`rule	`beat_spy`forecast
`AMD`	0.1048	0.0932	0.8591	0.9463	0.54
`MU`	0.1325	0.07	0.8591	0.0537	0.559
`TXN`	0.8676	0.3351	0.8591	0.0537	0.513
`QCOM`	0.076	0.0884	0.1409	0.9463	0.506
`INTC`	0.0538	0.058	0.8591	0.0537	0.525

true false not known for rules; forecasts are odds. Hover a column for its question.

What it means

Session of 2026-10-30, 5 symbols: Stacked averages: close > 20 EMA > 50 > 200: true for TXN of 5. Up more than 5% in 20 sessions: true for none of 5. Did the stock beat EPS estimates last quarter: true for AMD, MU, TXN, INTC of 5. Is earnings in the next 14 days: true for AMD, QCOM of 5. Highest odds for “Beating SPY over a month”: MU at 56%.

Identical questions per symbol make the sheet comparable; sort by trend and odds of beating SPY, flag names reporting soon.

Request JSON (AMD; the others differ only in the symbol)

{
  "model": "ora-fin-0.1.1",
  "state": {
    "symbol": "AMD"
  },
  "questions": {
    "trend": {
      "type": "yes_no",
      "ask": "C > ema(C, 20) and ema(C, 20) > sma(C, 50) and sma(C, 50) > sma(C, 200)"
    },
    "momentum": {
      "type": "yes_no",
      "ask": "roc(C, 20) > 5"
    },
    "beat": {
      "type": "yes_no",
      "instructions": "Did the stock beat EPS estimates last quarter?"
    },
    "earn_soon": {
      "type": "yes_no",
      "instructions": "Is earnings in the next 14 days?"
    },
    "beat_spy": {
      "type": "yes_no",
      "instructions": "Will it beat SPY over the next month?"
    }
  }
}

Response JSON (AMD, real)

{
  "model": "ora-fin-0.1.1",
  "answers": {
    "trend": {
      "yes_no": 0.1048,
      "rule": "C > ema(C, 20) and ema(C, 20) > sma(C, 50) and sma(C, 50) > sma(C, 200)",
      "basis": "rule"
    },
    "momentum": {
      "yes_no": 0.0932,
      "rule": "roc(C, 20) > 5",
      "basis": "rule"
    },
    "beat": {
      "yes_no": 0.8591,
      "rule": "beat_eps_last > 0.5",
      "basis": "pattern"
    },
    "earn_soon": {
      "yes_no": 0.9463,
      "rule": "days_to_earnings <= 14",
      "basis": "pattern"
    },
    "beat_spy": {
      "yes_no": 0.54
    }
  },
  "context": {
    "symbol": "AMD",
    "as_of": "2026-10-30"
  }
}

beat_eps_last days_to_earnings ema roc sma

Try it in the Playground

Equity research analyst · example 4

Staples dividend monitor: PG, KO, PEP, CL, KMB

Track payout facts for the consumer staples coverage list: still raising, no cut, yield level and growth streak.

ora-fin-0.1.15 symbols, one request each5 questionsworkflow · Mon at 08:00 ET

ScheduleMon at 08:00 ET
State5 symbols
Questions5 asked
Answersreal, captured
Actionsnone

State

{"symbol":"PG"} then KO, PEP, CL, KMB, one request each. The server fills in the latest completed session.

Questions

`raised`	rule	`raised_last > 0.5` Raised its last dividend
`no_cut`	rule	`cut_last < 0.5` Did not cut its last dividend
`yield3`	rule	`div_yield_ttm > 3` Yield above 3%
`grow10`	rule	`years_of_growth >= 10` Ten years of dividend growth
`trend`	rule	`div_yield_ttm > 2 and C > sma(C, 200)` Yield above 2% and above the 200-day

Answers

Symbol	`raised`rule	`no_cut`rule	`yield3`rule	`grow10`rule	`trend`rule
`PG`	0.1409	0.8591	0.2091	0.9463	0.9431
`KO`	0.1409	0.8591	0.0537	0.9463	0.9463
`PEP`	0.1409	0.8591	0.9463	0.9463	0.1034
`CL`	0.1409	0.8591	0.0537	0.9463	0.9337
`KMB`	0.1409	0.8591	0.9463	0.9463	0.8926

true false not known for rules; forecasts are odds. Hover a column for its question.

What it means

Session of 2026-10-30, 5 symbols: Raised its last dividend: true for none of 5. Did not cut its last dividend: true for PG, KO, PEP, CL, KMB of 5. Yield above 3%: true for PEP, KMB of 5. Ten years of dividend growth: true for PG, KO, PEP, CL, KMB of 5.

A Monday workflow refreshes the dividend table; a cut or a lost streak is the line to write about.

As a scheduled workflow (Mon at 08:00 ET)

Create it under Workflows in the console: it runs these questions for every symbol on the schedule and fires the actions per symbol. The answers above are what one run returned.

{
  "name": "Staples dividend monitor: PG, KO, PEP, CL, KMB",
  "symbols": "PG KO PEP CL KMB",
  "days": [
    1
  ],
  "at_time": "08:00",
  "model": "ora-fin-0.1.1",
  "questions": {
    "raised": {
      "type": "yes_no",
      "ask": "raised_last > 0.5"
    },
    "no_cut": {
      "type": "yes_no",
      "ask": "cut_last < 0.5"
    },
    "yield3": {
      "type": "yes_no",
      "ask": "div_yield_ttm > 3"
    },
    "grow10": {
      "type": "yes_no",
      "ask": "years_of_growth >= 10"
    },
    "trend": {
      "type": "yes_no",
      "ask": "div_yield_ttm > 2 and C > sma(C, 200)"
    }
  }
}

Request JSON (PG; the others differ only in the symbol)

{
  "model": "ora-fin-0.1.1",
  "state": {
    "symbol": "PG"
  },
  "questions": {
    "raised": {
      "type": "yes_no",
      "ask": "raised_last > 0.5"
    },
    "no_cut": {
      "type": "yes_no",
      "ask": "cut_last < 0.5"
    },
    "yield3": {
      "type": "yes_no",
      "ask": "div_yield_ttm > 3"
    },
    "grow10": {
      "type": "yes_no",
      "ask": "years_of_growth >= 10"
    },
    "trend": {
      "type": "yes_no",
      "ask": "div_yield_ttm > 2 and C > sma(C, 200)"
    }
  }
}

Response JSON (PG, real)

{
  "model": "ora-fin-0.1.1",
  "answers": {
    "raised": {
      "yes_no": 0.1409,
      "rule": "raised_last > 0.5",
      "basis": "rule"
    },
    "no_cut": {
      "yes_no": 0.8591,
      "rule": "cut_last < 0.5",
      "basis": "rule"
    },
    "yield3": {
      "yes_no": 0.2091,
      "rule": "div_yield_ttm > 3",
      "basis": "rule"
    },
    "grow10": {
      "yes_no": 0.9463,
      "rule": "years_of_growth >= 10",
      "basis": "rule"
    },
    "trend": {
      "yes_no": 0.9431,
      "rule": "div_yield_ttm > 2 and C > sma(C, 200)",
      "basis": "rule"
    }
  },
  "context": {
    "symbol": "PG",
    "as_of": "2026-10-30"
  }
}

cut_last div_yield_ttm raised_last sma years_of_growth

Try it in the Playground

Equity research analyst · example 5

NFLX post-earnings drift check for the follow-up note

Days after the report, check whether the beat, gap and hold above the pre-report price add up to drift.

ora-fin-0.1.1NFLX5 questions

StateNFLX
Questions5 asked
Answersreal, captured
Actionsnone

State

{"symbol":"NFLX"} The server fills in the latest completed session.

Questions

`drift`	rule	`beat_eps_last > 0.5 and last_earnings_gap > 0 and C > pre_earnings_close` Post-earnings drift: beat, gapped up, still above the pre-earnings close
`recent`	rule	`days_since_earnings <= 5` Reported in the last 5 days
`fell`	English → rule	Did the stock fall after its last earnings report?
`macd`	English → rule	Is the MACD line above its signal line?
`up_week`	forecast	Will the stock be higher in a week? Higher in a week

Answers

Question	Answer	Reading
`drift` Post-earnings drift: beat, gapped up, still above the pre-earnings close	0.0537	false
`recent` Reported in the last 5 days	0.0813	false
`fell` Did the stock fall after its last earnings report compiled to `last_earnings_move < 0`	0.9463	true
`macd` Is the MACD line above its signal line compiled to `macd(C) > macdsignal(C)`	0.1584	false
`up_week` Higher in a week	0.506	51% · close to even

What it means

For NFLX on the session of 2026-10-30: True now: Did the stock fall after its last earnings report. Not true: Post-earnings drift: beat, gapped up, still above the pre-earnings close; Reported in the last 5 days; Is the MACD line above its signal line. Forecasts: Higher in a week 51%.

Drift true supports a 'the market is still repricing' paragraph; false means the reaction is already in the price.

Request JSON

{
  "model": "ora-fin-0.1.1",
  "state": {
    "symbol": "NFLX"
  },
  "questions": {
    "drift": {
      "type": "yes_no",
      "ask": "beat_eps_last > 0.5 and last_earnings_gap > 0 and C > pre_earnings_close"
    },
    "recent": {
      "type": "yes_no",
      "ask": "days_since_earnings <= 5"
    },
    "fell": {
      "type": "yes_no",
      "instructions": "Did the stock fall after its last earnings report?"
    },
    "macd": {
      "type": "yes_no",
      "instructions": "Is the MACD line above its signal line?"
    },
    "up_week": {
      "type": "yes_no",
      "instructions": "Will the stock be higher in a week?"
    }
  }
}

Response JSON (NFLX, real)

{
  "model": "ora-fin-0.1.1",
  "answers": {
    "drift": {
      "yes_no": 0.0537,
      "rule": "beat_eps_last > 0.5 and last_earnings_gap > 0 and C > pre_earnings_close",
      "basis": "rule"
    },
    "recent": {
      "yes_no": 0.0813,
      "rule": "days_since_earnings <= 5",
      "basis": "rule"
    },
    "fell": {
      "yes_no": 0.9463,
      "rule": "last_earnings_move < 0",
      "basis": "pattern"
    },
    "macd": {
      "yes_no": 0.1584,
      "rule": "macd(C) > macdsignal(C)",
      "basis": "comparison"
    },
    "up_week": {
      "yes_no": 0.506
    }
  },
  "context": {
    "symbol": "NFLX",
    "as_of": "2026-10-30"
  }
}

beat_eps_last days_since_earnings last_earnings_gap last_earnings_move macd macdsignal pre_earnings_close

Try it in the Playground

Equity research analyst · example 6

MSFT beat quality: surprise size, growth and reaction

Separate a quality beat (revenue, growth, positive reaction) from a low-bar beat for the client call.

ora-fin-0.1.1MSFT5 questions

StateMSFT
Questions5 asked
Answersreal, captured
Actionsnone

State

{"symbol":"MSFT"} The server fills in the latest completed session.

Questions

`surprise`	English → rule	Did EPS beat estimates by more than 5% last quarter?
`rev_growth`	English → rule	Did revenue grow more than 5% year over year?
`eps_up`	English → rule	Is EPS up year over year?
`gap`	English → rule	Did the stock gap up after its last earnings?
`rev_surprise`	rule	`revenue_surprise_pct > 1` Revenue beat estimates by more than 1%

Answers

Question	Answer	Reading
`surprise` Did EPS beat estimates by more than 5% last quarter compiled to `eps_surprise_pct > 5`	0.0537	false
`rev_growth` Did revenue grow more than 5% year over year compiled to `revenue_growth_yoy > 5`	0.9463	true
`eps_up` Is EPS up year over year compiled to `last_eps > eps_year_ago`	0.9463	true
`gap` Did the stock gap up after its last earnings compiled to `last_earnings_gap > 0`	0.8374	true
`rev_surprise` Revenue beat estimates by more than 1%	0.9463	true

What it means

For MSFT on the session of 2026-10-30: True now: Did revenue grow more than 5% year over year; Is EPS up year over year; Did the stock gap up after its last earnings; Revenue beat estimates by more than 1%. Not true: Did EPS beat estimates by more than 5% last quarter.

Growth and revenue facts true alongside the EPS beat is the stronger story; a beat with a negative reaction is worth a paragraph on expectations.

Request JSON

{
  "model": "ora-fin-0.1.1",
  "state": {
    "symbol": "MSFT"
  },
  "questions": {
    "surprise": {
      "type": "yes_no",
      "instructions": "Did EPS beat estimates by more than 5% last quarter?"
    },
    "rev_growth": {
      "type": "yes_no",
      "instructions": "Did revenue grow more than 5% year over year?"
    },
    "eps_up": {
      "type": "yes_no",
      "instructions": "Is EPS up year over year?"
    },
    "gap": {
      "type": "yes_no",
      "instructions": "Did the stock gap up after its last earnings?"
    },
    "rev_surprise": {
      "type": "yes_no",
      "ask": "revenue_surprise_pct > 1"
    }
  }
}

Response JSON (MSFT, real)

{
  "model": "ora-fin-0.1.1",
  "answers": {
    "surprise": {
      "yes_no": 0.0537,
      "rule": "eps_surprise_pct > 5",
      "basis": "pattern"
    },
    "rev_growth": {
      "yes_no": 0.9463,
      "rule": "revenue_growth_yoy > 5",
      "basis": "pattern"
    },
    "eps_up": {
      "yes_no": 0.9463,
      "rule": "last_eps > eps_year_ago",
      "basis": "pattern"
    },
    "gap": {
      "yes_no": 0.8374,
      "rule": "last_earnings_gap > 0",
      "basis": "pattern"
    },
    "rev_surprise": {
      "yes_no": 0.9463,
      "rule": "revenue_surprise_pct > 1",
      "basis": "rule"
    }
  },
  "context": {
    "symbol": "MSFT",
    "as_of": "2026-10-30"
  }
}

eps_surprise_pct eps_year_ago last_earnings_gap last_eps revenue_growth_yoy revenue_surprise_pct

Try it in the Playground

Equity research analyst · example 7

LLY initiation: the technical context section

For a new coverage initiation, describe the chart objectively: long trend, regression slope, distance from highs and volatility.

ora-fin-0.1.1LLY6 questions

StateLLY
Questions6 asked
Answersreal, captured
Actionsnone

State

{"symbol":"LLY"} The server fills in the latest completed session.

Questions

`trend200`	English → rule	Is the stock above its 200-day moving average?
`slope`	rule	`linreg(C, 50) > ref(linreg(C, 50), -10)` 50-day regression line higher than ten sessions ago
`near_high`	rule	`C >= 0.98 * max(H, 252)` Within 2% of the 52-week high
`drawdown`	rule	`C < 0.8 * max(H, 252)` More than 20% off the 52-week high
`hv40`	rule	`std(log(C / C[-1]), 20) * sqrt(252) > 0.4` Annualized 20-day volatility above 40%
`rally10`	forecast	Will it rally at least 10% at some point in the next month? A 10% rally within a month

Answers

Question	Answer	Reading
`trend200` Is the stock above its 200-day moving average compiled to `C > sma(C, 200)`	0.9463	true
`slope` 50-day regression line higher than ten sessions ago	0.9463	true
`near_high` Within 2% of the 52-week high	0.4572	on the line (false)
`drawdown` More than 20% off the 52-week high	0.0537	false
`hv40` Annualized 20-day volatility above 40%	0.1939	false
`rally10` A 10% rally within a month	0.603	60% · likely

What it means

For LLY on the session of 2026-10-30: True now: Is the stock above its 200-day moving average; 50-day regression line higher than ten sessions ago. Not true: More than 20% off the 52-week high; Annualized 20-day volatility above 40%. On the line: Within 2% of the 52-week high. Forecasts: A 10% rally within a month 60%.

The answers become plain sentences in the initiation; the forecast is labelled as model odds, not the rating.

Request JSON

{
  "model": "ora-fin-0.1.1",
  "state": {
    "symbol": "LLY"
  },
  "questions": {
    "trend200": {
      "type": "yes_no",
      "instructions": "Is the stock above its 200-day moving average?"
    },
    "slope": {
      "type": "yes_no",
      "ask": "linreg(C, 50) > ref(linreg(C, 50), -10)"
    },
    "near_high": {
      "type": "yes_no",
      "ask": "C >= 0.98 * max(H, 252)"
    },
    "drawdown": {
      "type": "yes_no",
      "ask": "C < 0.8 * max(H, 252)"
    },
    "hv40": {
      "type": "yes_no",
      "ask": "std(log(C / C[-1]), 20) * sqrt(252) > 0.4"
    },
    "rally10": {
      "type": "yes_no",
      "instructions": "Will it rally at least 10% at some point in the next month?"
    }
  }
}

Response JSON (LLY, real)

{
  "model": "ora-fin-0.1.1",
  "answers": {
    "trend200": {
      "yes_no": 0.9463,
      "rule": "C > sma(C, 200)",
      "basis": "comparison"
    },
    "slope": {
      "yes_no": 0.9463,
      "rule": "linreg(C, 50) > ref(linreg(C, 50), -10)",
      "basis": "rule"
    },
    "near_high": {
      "yes_no": 0.4572,
      "rule": "C >= 0.98 * max(H, 252)",
      "basis": "rule"
    },
    "drawdown": {
      "yes_no": 0.0537,
      "rule": "C < 0.8 * max(H, 252)",
      "basis": "rule"
    },
    "hv40": {
      "yes_no": 0.1939,
      "rule": "std(log(C / C[-1]), 20) * sqrt(252) > 0.4",
      "basis": "rule"
    },
    "rally10": {
      "yes_no": 0.603
    }
  },
  "context": {
    "symbol": "LLY",
    "as_of": "2026-10-30"
  }
}

linreg log max offset ref sma sqrt std

Try it in the Playground

Equity research analyst · example 8

Bank peers relative strength: JPM, BAC, WFC, C, GS

Rank the large banks by trend and momentum before the sector earnings season preview.

ora-fin-0.1.15 symbols, one request each5 questions

State5 symbols
Questions5 asked
Answersreal, captured
Actionsnone

State

{"symbol":"JPM"} then BAC, WFC, C, GS, one request each. The server fills in the latest completed session.

Questions

`above_50d`	rule	`C > sma(C, 50)` Above the 50-day average
`three_m`	rule	`C > C[-63]` Higher than three months ago
`adx`	rule	`adx(14) > 20 and diplus(14) > diminus(14)` Trending up (ADX over 20 and +DI over −DI)
`earn_soon`	rule	`days_to_earnings <= 10` Reports earnings within 10 days
`beat_spy`	forecast	Will it beat SPY over the next month? Beating SPY over a month

Answers

Symbol	`above_50d`rule	`three_m`rule	`adx`rule	`earn_soon`rule	`beat_spy`forecast
`JPM`	0.3034	0.2625	0.1012	0.0537	0.488
`BAC`	0.0951	0.1028	0.1214	0.0537	0.473
`WFC`	0.3296	0.2303	0.1271	0.0537	0.505
`C`	0.0765	0.1175	0.0891	0.0537	0.476
`GS`	0.099	0.1125	0.2235	0.0537	0.529

true false not known for rules; forecasts are odds. Hover a column for its question.

What it means

Session of 2026-10-30, 5 symbols: Above the 50-day average: true for none of 5. Higher than three months ago: true for none of 5. Trending up (ADX over 20 and +DI over −DI): true for none of 5. Reports earnings within 10 days: true for none of 5. Highest odds for “Beating SPY over a month”: GS at 53%.

Leaders on trend and momentum go first in the preview; a name reporting within days gets its own line.

Request JSON (JPM; the others differ only in the symbol)

{
  "model": "ora-fin-0.1.1",
  "state": {
    "symbol": "JPM"
  },
  "questions": {
    "above_50d": {
      "type": "yes_no",
      "ask": "C > sma(C, 50)"
    },
    "three_m": {
      "type": "yes_no",
      "ask": "C > C[-63]"
    },
    "adx": {
      "type": "yes_no",
      "ask": "adx(14) > 20 and diplus(14) > diminus(14)"
    },
    "earn_soon": {
      "type": "yes_no",
      "ask": "days_to_earnings <= 10"
    },
    "beat_spy": {
      "type": "yes_no",
      "instructions": "Will it beat SPY over the next month?"
    }
  }
}

Response JSON (JPM, real)

{
  "model": "ora-fin-0.1.1",
  "answers": {
    "above_50d": {
      "yes_no": 0.3034,
      "rule": "C > sma(C, 50)",
      "basis": "rule"
    },
    "three_m": {
      "yes_no": 0.2625,
      "rule": "C > C[-63]",
      "basis": "rule"
    },
    "adx": {
      "yes_no": 0.1012,
      "rule": "adx(14) > 20 and diplus(14) > diminus(14)",
      "basis": "rule"
    },
    "earn_soon": {
      "yes_no": 0.0537,
      "rule": "days_to_earnings <= 10",
      "basis": "rule"
    },
    "beat_spy": {
      "yes_no": 0.488
    }
  },
  "context": {
    "symbol": "JPM",
    "as_of": "2026-10-30"
  }
}

adx days_to_earnings diminus diplus offset sma

Try it in the Playground

Equity research analyst · example 9

AMZN: flag an outsized earnings reaction to the desk

When the report reaction exceeds five percent, post to the research Slack so the analyst can publish a quick take.

ora-fin-0.1.1AMZN5 questions2 actions

StateAMZN
Questions5 asked
Answersreal, captured
Actions2 rules · dry run

State

{"symbol":"AMZN"} The server fills in the latest completed session.

Questions

`recent`	rule	`days_since_earnings <= 5` Reported in the last 5 days
`big`	rule	`abs(last_earnings_move) > 5` Last earnings move bigger than 5%
`gap`	rule	`last_earnings_gap > 0` Gapped up after the last report
`surprise`	rule	`eps_surprise_pct > 5` EPS beat by more than 5%
`drop5`	forecast	Will it drop at least 5% at some point in the next month? A 5% drawdown within a month

Answers

Question	Answer	Reading
`recent` Reported in the last 5 days	0.8967	true
`big` Last earnings move bigger than 5%	0.0537	false
`gap` Gapped up after the last report	0.0537	false
`surprise` EPS beat by more than 5%	0.0537	false
`drop5` A 5% drawdown within a month	0.462	46% · close to even

Actions

Rules on the answers decide what to send.

recent >= 0.6 and big >= 0.6→Slackresearch-desk

else→Slackresearch-desk

What each action would send 1 of 2 fired · dry run, nothing sent

quick_takerule false: skipped

no_takewould send (dry run)Slack → research-desk

{
  "text": "AMZN (2026-10-30): no outsized post-earnings reaction to write up (recent report 90%, big reaction 5%)."
}

What it means

For AMZN on the session of 2026-10-30: True now: Reported in the last 5 days. Not true: Last earnings move bigger than 5%; Gapped up after the last report; EPS beat by more than 5%. Forecasts: A 5% drawdown within a month 46%. Fired: no_take (Slack → research-desk).

The alert only asks for a quick take when the report is fresh and the move was big; otherwise it says so.

Request JSON

{
  "model": "ora-fin-0.1.1",
  "state": {
    "symbol": "AMZN"
  },
  "questions": {
    "recent": {
      "type": "yes_no",
      "ask": "days_since_earnings <= 5"
    },
    "big": {
      "type": "yes_no",
      "ask": "abs(last_earnings_move) > 5"
    },
    "gap": {
      "type": "yes_no",
      "ask": "last_earnings_gap > 0"
    },
    "surprise": {
      "type": "yes_no",
      "ask": "eps_surprise_pct > 5"
    },
    "drop5": {
      "type": "yes_no",
      "instructions": "Will it drop at least 5% at some point in the next month?"
    }
  },
  "actions": [
    {
      "id": "quick_take",
      "when": "recent >= 0.6 and big >= 0.6",
      "do": "slack",
      "connection": "research-desk",
      "message": "{{symbol}} ({{as_of}}): reported in the last 5 days and the reaction was over 5%. Gap up {{gap|pct}}, surprise over 5% {{surprise|pct}}. Quick take needed."
    },
    {
      "id": "no_take",
      "when": "else",
      "do": "slack",
      "connection": "research-desk",
      "message": "{{symbol}} ({{as_of}}): no outsized post-earnings reaction to write up (recent report {{recent|pct}}, big reaction {{big|pct}})."
    }
  ],
  "dry_run": true
}

Response JSON (AMZN, real)

{
  "model": "ora-fin-0.1.1",
  "answers": {
    "recent": {
      "yes_no": 0.8967,
      "rule": "days_since_earnings <= 5",
      "basis": "rule"
    },
    "big": {
      "yes_no": 0.0537,
      "rule": "abs(last_earnings_move) > 5",
      "basis": "rule"
    },
    "gap": {
      "yes_no": 0.0537,
      "rule": "last_earnings_gap > 0",
      "basis": "rule"
    },
    "surprise": {
      "yes_no": 0.0537,
      "rule": "eps_surprise_pct > 5",
      "basis": "rule"
    },
    "drop5": {
      "yes_no": 0.462
    }
  },
  "context": {
    "symbol": "AMZN",
    "as_of": "2026-10-30"
  },
  "actions": [
    {
      "id": "quick_take",
      "fired": false,
      "status": "skipped"
    },
    {
      "id": "no_take",
      "fired": true,
      "status": "dry_run",
      "do": "slack",
      "connection": "research-desk",
      "preview": {
        "text": "AMZN (2026-10-30): no outsized post-earnings reaction to write up (recent report 90%, big reaction 5%)."
      }
    }
  ]
}

abs days_since_earnings eps_surprise_pct last_earnings_gap last_earnings_move

Try it in the Playground

Equity research analyst · example 10

NVDA split history for the per-share data footnote

Confirm recent splits and the ratio before comparing per-share numbers across years in a model.

ora-fin-0.1.1NVDA5 questions

StateNVDA
Questions5 asked
Answersreal, captured
Actionsnone

State

{"symbol":"NVDA"} The server fills in the latest completed session.

Questions

`split3y`	rule	`days_since_split <= 1095` Split in the last three years
`ratio4`	rule	`last_split_ratio >= 4` Last split at least 4-for-1
`multi`	rule	`splits_5y >= 2` Two or more splits in five years
`reverse`	rule	`reverse_split_last > 0.5` Last split was a reverse split
`announced`	rule	`days_to_split <= 365` A split is announced

Answers

Question	Answer	Reading
`split3y` Split in the last three years	0.9463	true
`ratio4` Last split at least 4-for-1	0.9463	true
`multi` Two or more splits in five years	0.1409	false
`reverse` Last split was a reverse split	0.1409	false
`announced` A split is announced	0.0537	false

What it means

For NVDA on the session of 2026-10-30: True now: Split in the last three years; Last split at least 4-for-1. Not true: Two or more splits in five years; Last split was a reverse split; A split is announced.

Split facts tell the analyst which periods need adjusting; an announced split is only known once it is in the record.

Request JSON

{
  "model": "ora-fin-0.1.1",
  "state": {
    "symbol": "NVDA"
  },
  "questions": {
    "split3y": {
      "type": "yes_no",
      "ask": "days_since_split <= 1095"
    },
    "ratio4": {
      "type": "yes_no",
      "ask": "last_split_ratio >= 4"
    },
    "multi": {
      "type": "yes_no",
      "ask": "splits_5y >= 2"
    },
    "reverse": {
      "type": "yes_no",
      "ask": "reverse_split_last > 0.5"
    },
    "announced": {
      "type": "yes_no",
      "ask": "days_to_split <= 365"
    }
  }
}

Response JSON (NVDA, real)

{
  "model": "ora-fin-0.1.1",
  "answers": {
    "split3y": {
      "yes_no": 0.9463,
      "rule": "days_since_split <= 1095",
      "basis": "rule"
    },
    "ratio4": {
      "yes_no": 0.9463,
      "rule": "last_split_ratio >= 4",
      "basis": "rule"
    },
    "multi": {
      "yes_no": 0.1409,
      "rule": "splits_5y >= 2",
      "basis": "rule"
    },
    "reverse": {
      "yes_no": 0.1409,
      "rule": "reverse_split_last > 0.5",
      "basis": "rule"
    },
    "announced": {
      "yes_no": 0.0537,
      "rule": "days_to_split <= 365",
      "basis": "rule"
    }
  },
  "context": {
    "symbol": "NVDA",
    "as_of": "2026-10-30"
  }
}

days_since_split days_to_split last_split_ratio reverse_split_last splits_5y

Try it in the Playground

Information, not investment advice. Rules answer from the latest completed daily session; forecasts are probabilities. Actions ran as dry runs: nothing was sent. More in Sell side: Sell-side sales trader, Execution trader / desk, Market maker, Prop trading firm, Compliance officer.

Create an account Open the Playground Everything here also lives in the console, next to your keys and usage.

Individuals

Buy side

Sell side

Corporates

Builders

Institutions

NVDA earnings preview: date, streak and setup into the print

State

Questions

Answers

What it means

JPM earnings review: beat on both lines, and did the stock hold?

State

Questions

Answers

Actions

What it means

Semiconductor coverage sheet: AMD, MU, TXN, QCOM, INTC

State

Questions

Answers

What it means

Staples dividend monitor: PG, KO, PEP, CL, KMB

State

Questions

Answers

What it means

NFLX post-earnings drift check for the follow-up note

State

Questions

Answers

What it means

MSFT beat quality: surprise size, growth and reaction

State

Questions

Answers

What it means

LLY initiation: the technical context section

State

Questions

Answers

What it means

Bank peers relative strength: JPM, BAC, WFC, C, GS

State

Questions

Answers

What it means

AMZN: flag an outsized earnings reaction to the desk

State

Questions

Answers

Actions

What it means

NVDA split history for the per-share data footnote

State

Questions

Answers

What it means