Update to Ultralayer

{
  "description": "Wording changes between one earnings press release and the last — what the company started saying, stopped saying, or now says differently. Operation is list_changes.",
  "included_files": [],
  "name": "changes",
  "skill_md_contents": "---\nname: changes\ndescription: Wording changes between one earnings press release and the last — what the company started saying, stopped saying, or now says differently. Operation is list_changes.\n---\n\n# Changes\n\n`list_changes` compares a company’s latest earnings press release to the previous one. Each result is one thing they added, removed, or rewrote.\n\n| Operation | Role |\n|-----------|------|\n| `list_changes` | Return matching wording changes |\n\nEvery filter works **without a ticker list**, so this is a market-wide screen as much as a single-filing read: who redefined a metric this quarter, who rewrote what the outlook assumes, who quietly dropped a risk. The material change is usually the one nobody headlined.\n\n---\n\n## When to use\n\n**Use it for** the language, not the numbers: what this release says that last quarter’s did not, what they stopped mentioning, how a metric is now defined, how segments are cut, what the outlook assumes.\n\n**Not this tool:** the outlook figure or who raised / lowered → `list_guidance`. Guide vs actual → `list_guidance_outcomes`. Headlines, rumor, or what the market is reacting to → Wire. Anything outside an earnings press release → your own web search.\n\n---\n\n## Use cases\n\n**Realtime change tape** — What companies just started or stopped saying, market-wide, minutes after each release. No tickers.\n```json\n{\n  \"sort\": \"timestamp\",\n  \"min_materiality_score\": 0.5,\n  \"detail\": \"standard\",\n  \"limit\": 40\n}\n```\n\n**Comparability breaks** — A redefined non-GAAP metric or a re-cut segment silently invalidates every model and screen built on the old basis, and it is stated once in the release. Highest-value screen here. INTU dropping share-based comp from non-GAAP scores 0.97; moving Mailchimp into its own segment scores 0.88.\n```json\n{\n  \"change_categories\": [\"metric_definition\", \"reporting_structure\"],\n  \"sort\": \"materiality\",\n  \"min_materiality_score\": 0.7,\n  \"detail\": \"standard\",\n  \"limit\": 30\n}\n```\n\n**What the outlook now assumes** — Not the figure, the basis: a deal folded in, a tariff line added, a multi-year target dropped. A guide that looks cut is sometimes just re-based. Then `list_guidance` for the number.\n```json\n{\n  \"change_categories\": [\"guidance_basis\"],\n  \"sort\": \"materiality\",\n  \"min_materiality_score\": 0.5,\n  \"detail\": \"standard\",\n  \"limit\": 30\n}\n```\n\n**Quiet de-risking** — What they stopped saying: a lawsuit no longer named, a KPI no longer highlighted, an assumption dropped. The proof is `prior_quote`.\n```json\n{\n  \"change_kinds\": [\"removed\"],\n  \"sort\": \"materiality\",\n  \"min_materiality_score\": 0.5,\n  \"detail\": \"standard\",\n  \"limit\": 30\n}\n```\n\n**Theme sweep** — No text search. One theme (tariffs, refunds, AI capex) lands across several categories; pass a few and read the summaries.\n```json\n{\n  \"change_categories\": [\"policy\", \"guidance_basis\", \"discrete_item\", \"results_attribution\"],\n  \"sort\": \"materiality\",\n  \"min_materiality_score\": 0.5,\n  \"detail\": \"standard\",\n  \"limit\": 40\n}\n```\n\n**Legal and one-off items** — Do not require `impact: [\"negative\"]`. Dropping a named lawsuit is often `legal` and `positive`. Big charges sometimes land in `discrete_item`, not `legal`.\n```json\n{\n  \"change_categories\": [\"legal\", \"discrete_item\"],\n  \"sort\": \"materiality\",\n  \"min_materiality_score\": 0.7,\n  \"detail\": \"standard\",\n  \"limit\": 20\n}\n```\n\n**One release, deep read** — Ticker + the fiscal year and quarter of that release. The prior period is the previous quarter (INTU FY26 Q4 vs Q3). Floor `0` when you want everything in one filing.\n```json\n{\n  \"symbols\": [\"INTU\"],\n  \"fiscal_year\": 2026,\n  \"fiscal_quarter\": 4,\n  \"min_materiality_score\": 0,\n  \"detail\": \"standard\",\n  \"limit\": 40\n}\n```\n\n**Watchlist** — Up to 8 tickers. `materiality` puts the biggest changes first (including older ones); `timestamp` puts the newest first.\n```json\n{\n  \"symbols\": [\"NVDA\", \"INTU\", \"WMT\", \"DE\"],\n  \"start_timestamp\": \"2026-06-01T00:00:00Z\",\n  \"sort\": \"materiality\",\n  \"min_materiality_score\": 0.5,\n  \"detail\": \"standard\",\n  \"limit\": 30\n}\n```\n\n---\n\n## Response detail\n\nDefault is `full`. `detail` only drops fields. Price does not change.\n\n| Level | What you get |\n|-------|----------------|\n| `essential` | Ticker, when it published, fiscal period, kind, category, summary. No quotes. |\n| `standard` | That plus company name, both quotes, scores, impact, prior period, and the SEC URLs |\n| `full` | That plus `cik` and extra source fields (`document_type`, fiscal period on the source) |\n\nUse **`standard`** with an LLM — the quotes are already there. Use `essential` when you only need the one-line summary. Use `full` when a machine needs `cik` or the extra source fields.\n\nAt `standard`, `source_metadata` is null. The URL is still on the source.\n\n---\n\n## What you get back\n\nEach item is one change. Default `limit` is 10 (max 100). Default `min_materiality_score` is **0.4**.\n\n| Field | Notes |\n|-------|-------|\n| `symbol` / `company_name` / `cik` | `cik` only at `full` |\n| `timestamp` | When we recorded the change. **Time filters use this.** |\n| `source_timestamp` | When the company published the current release. Returned, not filtered. |\n| `fiscal_year` / `fiscal_quarter` | Period the **current** release is about. Quarter is null on a full-year report. |\n| `prior_fiscal_year` / `prior_fiscal_quarter` | The previous release. `fiscal_quarter=4` is Q4 vs Q3, not the full year. |\n| `change_kind` | `added` / `removed` / `modified` |\n| `change_category` | What kind of disclosure changed |\n| `summary` | One sentence. Trust the quote if they disagree. |\n| `current_quote` / `prior_quote` | The sentence in that release. Null on a removal / addition. |\n| `materiality_score` | `0-.2` reword; `.2-.4` weak; `.4-.6` mod; `.6-.8` high; `.8-1` must-read |\n| `impact` | Whether the wording change itself reads better or worse for the company — not a price call |\n| `current_source` / `prior_source` | Always both, with a URL to each release |\n\n`added` has `current_quote` only. `removed` has `prior_quote` only — read it. `modified` has both.\n\n---\n\n## Filters and sort\n\nFilters combine with AND. Values inside a list are OR. Tickers are case-insensitive, max 8. Categories max 8. A category that is not in the list is rejected.\n\n| Param | Notes |\n|-------|-------|\n| `start_timestamp` / `end_timestamp` | On `timestamp`. `end_timestamp: null` means now. A future end is treated as now. A future start is rejected. |\n| `symbols` + `fiscal_year` + `fiscal_quarter` | One release. Year alone returns every pair in that year. |\n| `change_kinds` | `added` / `removed` / `modified` |\n| `change_categories` | See **Categories** |\n| `impact` | `positive` / `negative` / `neutral`. Do not filter on this alone — the same kind of change can be positive at one company and negative at another. |\n| `min_materiality_score` | Inclusive. Default **0.4** skips rewording and weak rows. Pass `0` to turn the floor off. |\n\n| `sort` | Order |\n|-------|--------|\n| `timestamp` (default) | Newest first |\n| `materiality` | Highest score first, then newest |\n\n---\n\n## Categories\n\nCategory is *what changed*, not whether it is good news. Taking a named lawsuit out of the risk list is often `legal` or `risk`, `removed`, and `positive`.\n\n| Category | Use for |\n|----------|---------|\n| `metric_definition` | How a non-GAAP or adjusted metric is calculated |\n| `disclosed_metric` | A named highlight they started, stopped, or renamed |\n| `reporting_structure` | Segments or what is in the report |\n| `guidance_basis` | Assumptions behind the outlook — not a raise or a cut |\n| `policy` | Tariffs, tax rules, regulation |\n| `discrete_item` | Impairments, charges, restructuring, one-offs |\n| `legal` | Lawsuits and other legal actions |\n| `capital_action` | Buybacks, financing, deals, spins |\n| `risk` / `catalyst` | A threat vs an upcoming event. Good or bad does not pick the label. |\n\n`accounting_policy`, `control_and_audit`, `concentration`, and `compensation` rarely return rows here. Empty on those is not “the company is clean.”\n\n`product` and `catalyst` can flood a list that includes drug or chip names. Skip `business_description` and low-scoring `results_attribution` unless you asked for them.\n\n---\n\n## Workflow\n\nChains worth more than a single call.\n\n**Earnings-night read on one name**\n1. `list_changes` — ticker + that release’s fiscal year and quarter, floor `0`. Everything that moved in the language.\n2. `list_guidance` — same ticker, for the figures the wording sits around.\n3. `list_guidance_outcomes` — how the period that just closed scored against the guide they set a quarter ago.\n4. Wire for how the tape read it; your own web search for the sell-side take.\n\n**Comparability break → fix the model**\n1. `list_changes` — `metric_definition` and `reporting_structure`, market-wide, floor 0.7.\n2. Read `prior_quote` against `current_quote` for the old and new basis, and note the fiscal period the change takes effect.\n3. `list_guidance` — whether the outlook is now stated on the new basis. A guide that looks cut can just be re-based.\n4. Restate history before comparing anything across that boundary, and re-check any screen that ranks on the affected metric.\n\n**Theme exposure across the market**\n1. `list_changes` — theme categories, `sort: \"materiality\"`, no tickers. Who is talking about it and how it hit them.\n2. Group the tickers that come back; the same theme appears under several categories.\n3. `identify_stakeholders` — the full winner/loser map, beyond the filers who happened to word it into a release.\n4. `list_guidance` — whether any of them put the theme into the outlook basis, which is where it becomes a number.\n\n**Quiet de-risking sweep**\n1. `list_changes` — `change_kinds: [\"removed\"]`, floor 0.5, no tickers.\n2. Read `prior_quote` on each. Removal means they stopped saying it, not that the underlying item resolved.\n3. Wire or your own web search — confirm whether the case settled, the KPI moved into a table, or the risk simply went unmentioned.\n\n**Leave it running**\n`create_alert` with `path: \"/v0/filings/list_changes\"`, same filters minus timestamps. `metric_definition` + `reporting_structure` at a high floor is a low-noise, high-value inbox; pin `detail` and `min_materiality_score`.\n\n---\n\n## Combine with\n\n- **`list_guidance`** — The outlook and how it was revised. Same ticker; match fiscal year / quarter to the report period on the guidance source (`source_metadata`, which needs `list_guidance` at `full`).\n- **Wire** — The headline.\n- **Alerts** — Alertable. Threshold counts changes; the alert owns the window. See **Workflow**. Wire remains the headline monitor.\n\n---\n\n## Limitations\n\n- Not every listed company is in the data.\n- An empty list can mean nothing matched, the floor is too high, or that release is not in yet. Do not treat it as “nothing changed.”\n- Rows show up a few minutes after the release. Then nothing until the next earnings press release.\n- No keyword search. Use categories and read the summaries.\n- `removed` often means they stopped highlighting something, not that they stopped reporting it.\n- One theme can appear under more than one category.\n\n---\n\n## FAQ\n\n**Why did a 0.6 floor miss HD’s IEEPA guidance-basis change?**  \nIt is 0.56. Default 0.4 is safer if you care about outlook assumptions.\n\n**I filtered to the press-release time and got nothing.**  \nTime filters use `timestamp` (when we recorded it), not `source_timestamp` (when they published). INTU’s release is `20:02:29Z`; the rows show up at `20:04:20Z`.\n\n**Does `removed` mean they stopped reporting the number?**  \nNo. They may have stopped highlighting it. The figure can still be in a table. Deere no longer *names* the FTC suit — that is not the same as the case ending.\n"
}