Foresee is an MCP server published by io.github.Foresee-Tech, hosted at agents.go-foresee.com. When last checked on 2026-11-21 it was working: it answers and lists its tools. It declares 2 tools, including quote_insurance, live_carrier_quotes.
Let AI assistants shop for home and auto insurance: compare quote estimates across every carrier.
126 connections through 5 shared values. Tap any node.
Inferred from the host name and headers: what a server runs on, not who runs it.
Purpose: generate instant, itemized quote estimates from the carriers Foresee supports, across the lines and states Foresee currently serves, in one call — the LIVE TODAY line at the end of this description names today's set. `lines` is REQUIRED and is ONE map: each key names a line to price (e.g. "auto", "renters", "home" — plain words are fine), each value is that line's coverage ask as actual numbers. A line Foresee doesn't quote in the user's state comes back under `skipped`: `lines` names each one and `message` is one sentence, written to be relayed to the user as-is, naming what Foresee does quote in that state. For auto the ask has four axes — `bi` (bodily-injury liability, per-person/ per-accident in $000s, e.g. "100/300"), `pd` (property-damage liability in $000s, e.g. 100), `coll_deductible` (collision deductible in dollars, e.g. 500) and `comp_deductible` (comprehensive deductible in dollars, e.g. 500); `um` and `medpay` are optional. A renters ask has four axes — `coverage_c` (personal-property/contents limit in dollars, e.g. 30000), `coverage_e` (personal liability in dollars, e.g. 100000), `coverage_f` (guest medical in dollars, e.g. 1000) and `deductible` (all-perils, in dollars, e.g. 500); `coverage_d` is optional. A home ask: `coverage_a` (the dwelling's replacement cost in dollars), `coverage_e` (e.g. 300000), `coverage_f` (e.g. 1000) and `aop_deductible` (all-other-perils deductible in dollars, e.g. 1000). There are no named coverage levels: pass exact numbers, the same ask in every state. An omitted OPTIONAL axis (`um`, `medpay`, `coverage_d`) keeps each carrier's own default — the quote's per-coverage lines show what was rated. Where the user's state puts more on every auto policy (its personal injury protection, a lawsuit option) and the ask doesn't name it, the quote prices the state's own and says so. Each line's `state_notes` is what the user's state means for these quotes — that, its legal minimum, the facts its law bars insurers from pricing on, a carrier that doesn't sell there — each note's `text` written to be relayed. Any numbers at or above the state's legal minimum work as the ask (an auto `bi`/`pd` below it prices nothing — no carrier may sell that policy — and comes back under `coverage_required` naming the minimum); each carrier's `price_ladder` prices every other rung, so a starting selection is easy to refine after the fact. An incomplete ask on a live line prices nothing and answers with `coverage_required` naming that line's own axes; an axis supplied with a value no carrier offers (`bi` "banana", a negative deductible) is refused the same way, naming the bad value and the format the axis takes. Each supported carrier is priced at the selection given; a carrier that doesn't offer an asked rung is priced at its nearest offered one and says so: its entry carries `rated_vs_asked` (per axis: `asked`, `rated`, and `coverage` "less"/"more" than asked; the dense text puts it on the `C` row as `rated`). That price is NOT like-for-like — state the rated limits next to it every time you show it (e.g. "$255/mo — 30/60 BI / $25k PD, the most this carrier offers, not the 100/300 / $100k you asked for"), and never let it headline or anchor a cheapest/spread claim without saying so. A carrier without a price appears in `failures`, on every line it was asked on — a carrier never silently vanishes from a line's results. Each entry's `by` says whose answer it is: `carrier` is the carrier's own (it doesn't sell the line in the state, isn't taking new customers, only quotes military families) — relay its `error` as written; `foresee` means Foresee couldn't get that quote — say exactly that, and never guess or add why. Priced results come back per line under `by_line`. Profile requirements:
None yet. Changes appear after a server's second daily check.
Squares are this server's values; dots are other servers sharing them. A shared address or publisher is a lead, not proof of a common operator.
Schema too large to show here (23,820 characters).
{
"name": "quote_insurance",
"title": "Instant insurance quote estimates",
"description": "Purpose: generate instant, itemized quote estimates from the carriers\n Foresee supports, across the lines and states Foresee currently serves,\n in one call — the LIVE TODAY line at the end of this description names\n today's set.\n\n `lines` is REQUIRED and is ONE map: each key names a line to price (e.g.\n \"auto\", \"renters\", \"home\" — plain words are fine), each value is that\n line's coverage ask as actual numbers. A line Foresee doesn't quote in\n the user's state comes back under `skipped`: `lines` names each one and\n `message` is one sentence, written to be relayed to the user as-is,\n naming what Foresee does quote in that state. For auto\n the ask has four axes — `bi` (bodily-injury liability, per-person/\n per-accident in $000s, e.g. \"100/300\"), `pd` (property-damage liability in\n $000s, e.g. 100), `coll_deductible` (collision deductible in dollars, e.g.\n 500) and `comp_deductible` (comprehensive deductible in dollars, e.g.\n 500); `um` and `medpay` are optional. A renters ask has four axes —\n `coverage_c` (personal-property/contents limit in dollars, e.g. 30000),\n `coverage_e` (personal liability in dollars, e.g. 100000), `coverage_f`\n (guest medical in dollars, e.g. 1000) and `deductible` (all-perils, in\n dollars, e.g. 500); `coverage_d` is optional. A home ask: `coverage_a`\n (the dwelling's replacement cost in dollars), `coverage_e` (e.g. 300000),\n `coverage_f` (e.g. 1000) and `aop_deductible` (all-other-perils\n deductible in dollars, e.g. 1000). There are no named coverage levels:\n pass exact numbers, the same ask in every state. An omitted OPTIONAL\n axis (`um`, `medpay`, `coverage_d`) keeps each carrier's own\n default — the quote's per-coverage lines show what was rated. Where the\n user's state puts more on every auto policy (its personal injury\n protection, a lawsuit option) and the ask doesn't name it, the quote\n prices the state's own and says so. Each line's `state_notes` is what\n the user's state means for these quotes — that, its legal minimum, the\n facts its law bars insurers from pricing on, a carrier that doesn't sell\n there — each note's `text` written to be relayed. Any\n numbers at or above the state's legal minimum work as the ask (an auto\n `bi`/`pd` below it prices nothing — no carrier may sell that policy — and\n comes back under `coverage_required` naming the minimum); each carrier's\n `price_ladder` prices every other rung, so a starting\n selection is easy to refine after the fact. An incomplete ask on a\n live line prices nothing and answers with `coverage_required` naming that\n line's own axes; an axis supplied with a value no carrier offers (`bi`\n \"banana\", a negative deductible) is refused the same way, naming the bad\n value and the format the axis takes. Each supported carrier is priced at\n the selection given; a carrier that doesn't offer an asked rung is priced\n at its nearest offered one and says so: its entry carries\n `rated_vs_asked` (per axis: `asked`, `rated`, and `coverage` \"less\"/\"more\"\n than asked; the dense text puts it on the `C` row as `rated`). That price is NOT\n like-for-like — state the rated limits next to it every time you show it\n (e.g. \"$255/mo — 30/60 BI / $25k PD, the most this carrier offers, not\n the 100/300 / $100k you asked for\"), and never let it headline or anchor\n a cheapest/spread claim without saying so. A carrier without a price\n appears in `failures`, on every line it was asked on — a carrier never\n silently vanishes from a line's results. Each entry's `by` says whose\n answer it is: `carrier` is the carrier's own (it doesn't sell the line\n in the state, isn't taking new customers, only quotes military families)\n — relay its `error` as written; `foresee` means Foresee couldn't get\n that quote — say exactly that, and never guess or add why. Priced\n results come back per line under `by_line`.\n\n Profile requirements:",
"inputSchema": {
"truncated": true,
"chars": 23820
},
"outputSchema": {
"type": "object",
"$defs": {
"SkippedLines": {
"type": "object",
"title": "SkippedLines",
"required": [
"lines",
"message"
],
"properties": {
"lines": {
"type": "array",
"items": {
"type": "string"
},
"title": "Lines"
},
"message": {
"type": "string",
"title": "Message"
}
},
"additionalProperties": true
},
"BundleSummary": {
"type": "object",
"title": "BundleSummary",
"properties": {
"lines": {
"anyOf": [
{
"type": "array",
"items": {
"type": "string"
}
},
{
"type": "null"
}
],
"title": "Lines",
"default": null
},
"savings": {
"anyOf": [
{
"type": "number"
},
{
"type": "null"
}
],
"title": "Savings",
"default": null
},
"bundle_total": {
"anyOf": [
{
"type": "number"
},
{
"type": "null"
}
],
"title": "Bundle Total",
"default": null
},
"standalone_total": {
"anyOf": [
{
"type": "number"
},
{
"type": "null"
}
],
"title": "Standalone Total",
"default": null
}
},
"additionalProperties": true
},
"LineQuoteSummary": {
"type": "object",
"title": "LineQuoteSummary",
"properties": {
"carriers": {
"anyOf": [
{
"type": "array",
"items": {
"$ref": "#/$defs/CarrierQuoteSummary"
}
},
{
"type": "null"
}
],
"title": "Carriers",
"default": null
},
"failures": {
"anyOf": [
{
"type": "array",
"items": {
"type": "object",
"additionalProperties": true
}
},
{
"type": "null"
}
],
"title": "Failures",
"default": null
},
"not_rated": {
"anyOf": [
{
"type": "array",
"items": {
"type": "object",
"additionalProperties": true
}
},
{
"type": "null"
}
],
"title": "Not Rated",
"default": null
},
"tighten_by": {
"anyOf": [
{
"type": "array",
"items": {
"type": "string"
}
},
{
"type": "null"
}
],
"title": "Tighten By",
"default": null
},
"assumptions": {
"anyOf": [
{
"type": "array",
"items": {
"type": "object",
"additionalProperties": true
}
},
{
"type": "null"
}
],
"title": "Assumptions",
"default": null
},
"input_flags": {
"anyOf": [
{
"type": "array",
"items": {
"type": "object",
"additionalProperties": true
}
},
{
"type": "null"
}
],
"title": "Input Flags",
"default": null
},
"state_notes": {
"anyOf": [
{
"type": "array",
"items": {
"type": "object",
"additionalProperties": true
}
},
{
"type": "null"
}
],
"title": "State Notes",
"default": null
},
"coverage_selection": {
"anyOf": [
{
"type": "object",
"additionalProperties": true
},
{
"type": "null"
}
],
"title": "Coverage Selection",
"default": null
}
},
"additionalProperties": true
},
"CarrierQuoteSummary": {
"type": "object",
"title": "CarrierQuoteSummary",
"properties": {
"carrier": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"title": "Carrier",
"default": null
},
"monthly": {
"anyOf": [
{
"type": "number"
},
{
"type": "null"
}
],
"title": "Monthly",
"default": null
},
"warnings": {
"anyOf": [
{
"type": "array",
"items": {
"type": "string"
}
},
{
"type": "null"
}
],
"title": "Warnings",
"default": null
},
"carrier_key": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"title": "Carrier Key",
"default": null
},
"rated_vs_asked": {
"anyOf": [
{
"type": "array",
"items": {
"type": "object",
"additionalProperties": true
}
},
{
"type": "null"
}
],
"title": "Rated Vs Asked",
"default": null
},
"carrier_quote_url": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"title": "Carrier Quote Url",
"default": null
},
"confidence_interval": {
"anyOf": [
{
"type": "object",
"additionalProperties": true
},
{
"type": "null"
}
],
"title": "Confidence Interval",
"default": null
}
},
"additionalProperties": true
}
},
"title": "QuoteToolResult",
"properties": {
"dense": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"title": "Dense",
"default": null
},
"error": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"title": "Error",
"default": null
},
"state": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"title": "State",
"default": null
},
"bundle": {
"anyOf": [
{
"type": "object",
"additionalProperties": {
"$ref": "#/$defs/BundleSummary"
}
},
{
"type": "null"
}
],
"title": "Bundle",
"default": null
},
"detail": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"title": "Detail",
"default": null
},
"by_line": {
"anyOf": [
{
"type": "object",
"additionalProperties": {
"$ref": "#/$defs/LineQuoteSummary"
}
},
{
"type": "null"
}
],
"title": "By Line",
"default": null
},
"message": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"title": "Message",
"default": null
},
"skipped": {
"anyOf": [
{
"$ref": "#/$defs/SkippedLines"
},
{
"type": "null"
}
],
"default": null
},
"serviceable": {
"anyOf": [
{
"type": "boolean"
},
{
"type": "null"
}
],
"title": "Serviceable",
"default": null
},
"presentation": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"title": "Presentation",
"default": null
},
"profile_required": {
"anyOf": [
{
"type": "object",
"additionalProperties": {
"type": "string"
}
},
{
"type": "null"
}
],
"title": "Profile Required",
"default": null
},
"coverage_required": {
"anyOf": [
{
"type": "object",
"additionalProperties": true
},
{
"type": "null"
}
],
"title": "Coverage Required",
"default": null
},
"example_arguments": {
"anyOf": [
{
"type": "object",
"additionalProperties": true
},
{
"type": "null"
}
],
"title": "Example Arguments",
"default": null
}
},
"additionalProperties": true
},
"annotations": {
"title": "Instant insurance quote estimates",
"readOnlyHint": true,
"openWorldHint": false,
"destructiveHint": false
}
}Purpose: confirm quote estimates on the carriers' own quote sites, via Foresee agents completing their real quote flows. IDEMPOTENT, keyed on the profile: the first call commissions the walks; calling again with the same profile collects progress and results instead of re-submitting anything — whatever the ask. A profile that has already been walked returns those results (the carriers are never asked twice): the envelope's ``coverage_selection`` names the ask the walk typed, and each quote carries the carrier's other recorded coverage options as ``variants``, so a new ask reads the same run. So call once to start, then re-call after a few minutes to collect; agents still working report their stage. Ask ONCE, before the first call: the consent disclosure below, the identity fields, and the questions listed at the end of this description under EVERY LINE and under the line being walked — all in one message, so the first commissioning call walks every carrier. A call made before consent submits nothing and answers ``authorization_required`` with the profile's ``needs``, for when you have not asked yet. No sign-in is required. The one hard requirement is the user's own consent, captured in-band: BEFORE the commissioning call, you MUST tell the user, plainly: Foresee will submit their details to the named carriers; the carriers may obtain their credit-based insurance score (a soft pull, with no impact on your credit score); and the carriers may contact them by email or phone. Then get their explicit go-ahead and pass their affirmation VERBATIM as ``user_authorization`` (e.g. "yes, go ahead"). The affirmation is stored as the durable consent record for the dispatch; without one the call is refused with ``authorization_required``. Foresee only collects quotes; it does not take payment or bind insurance. Collect the ``identity`` fields in chat. Nothing is filled in from anywhere else: what the walks type is what the call states. A ``missing_facts`` response is normal: carrier forms insist on facts (body style, purchase date, age first licensed…) that Foresee will not invent. Each ``needs`` entry carries the carrier (``scope``), the facts in the walk's own words (``need``), and ``fields[]`` — per fact, the ``ask`` beside the exact schema path to pass the answer under (``field``, e.g. ``auto.vehicles[].purchase_date``; ``identity.…`` paths go on ``identity``). Ask the user for exactly those facts, then call again with the answers merged in at those paths. A fact with no ``field`` has no profile home yet — relay that carrier's ask as unavailable rather than guessing a key. While any carrier waits on a fact the user can answer, nothing is submitted: the carriers already able to go are listed under ``ready`` and held, so every carrier is walked together. Only when the user cannot or will not answer, re-call with ``dispatch_ready_only=true`` to walk the ready ones now; that receipt is PARTIAL — follow its ``recover`` block: re-call with the new facts merged AND ``carriers`` set to exactly ``recover.carriers`` — a changed profile is a new dispatch, and an unscoped re-call would re-submit the already-walked carriers too. Unasserted MINOR facts are not asked: a form field that is really a claim nobody made (an anti-theft device, a defensive-driving course, a licence held abroad) is answered with the declared no-claim value — never a discount claim — and every one comes back in ``assumptions`` (``field`` + the ``assumed`` value submitted). Relay them with the results; if the user corrects one, re-call with the real
Schema too large to show here (27,386 characters).
{
"name": "live_carrier_quotes",
"title": "Live carrier quotes",
"description": "Purpose: confirm quote estimates on the carriers' own quote sites, via Foresee agents completing their real quote flows.\n\n IDEMPOTENT, keyed on the profile: the first call commissions the\n walks; calling again with the same profile collects progress and\n results instead of re-submitting anything — whatever the ask. A\n profile that has already been walked returns those results (the\n carriers are never asked twice): the envelope's\n ``coverage_selection`` names the ask the walk typed, and each quote\n carries the carrier's other recorded coverage options as\n ``variants``, so a new ask reads the same run. So call once to\n start, then re-call after a few minutes to collect; agents still\n working report their stage.\n\n Ask ONCE, before the first call: the consent disclosure below, the\n identity fields, and the questions listed at the end of this\n description under EVERY LINE and under the line being walked — all\n in one message, so the first commissioning call walks every carrier. A call made before\n consent submits nothing and answers ``authorization_required`` with\n the profile's ``needs``, for when you have not asked yet.\n\n No sign-in is required. The one hard requirement is the user's own\n consent, captured in-band: BEFORE the commissioning call, you MUST\n tell the user, plainly: Foresee will submit their details to the\n named carriers; the carriers may obtain their credit-based insurance\n score (a soft pull, with no impact on your credit score); and the\n carriers may contact them by email or phone. Then get their explicit\n go-ahead and pass their affirmation VERBATIM as ``user_authorization``\n (e.g. \"yes, go ahead\"). The affirmation is stored as the durable\n consent record for the dispatch; without one the call is refused with\n ``authorization_required``. Foresee only collects quotes; it does\n not take payment or bind insurance.\n\n Collect the ``identity`` fields in chat. Nothing is filled in from\n anywhere else: what the walks type is what the call states.\n\n A ``missing_facts`` response is normal: carrier forms insist on facts\n (body style, purchase date, age first licensed…) that Foresee will not\n invent. Each ``needs`` entry carries the carrier (``scope``), the\n facts in the walk's own words (``need``), and ``fields[]`` — per\n fact, the ``ask`` beside the exact schema path to pass the answer\n under (``field``, e.g. ``auto.vehicles[].purchase_date``;\n ``identity.…`` paths go on ``identity``). Ask the user for exactly\n those facts, then call again with the answers merged in at those\n paths. A fact with no ``field`` has no profile home yet — relay\n that carrier's ask as unavailable rather than guessing a key. While\n any carrier waits on a fact the user can answer, nothing is\n submitted: the carriers already able to go are listed under\n ``ready`` and held, so every carrier is walked together. Only when\n the user cannot or will not answer, re-call with\n ``dispatch_ready_only=true`` to walk the ready ones now; that\n receipt is PARTIAL — follow its ``recover`` block: re-call with the\n new facts merged AND ``carriers`` set to exactly\n ``recover.carriers`` — a changed profile is a new dispatch, and an\n unscoped re-call would re-submit the already-walked carriers too.\n\n Unasserted MINOR facts are not asked: a form field that is really a\n claim nobody made (an anti-theft device, a defensive-driving course,\n a licence held abroad) is answered with the declared no-claim value —\n never a discount claim — and every one comes back in ``assumptions``\n (``field`` + the ``assumed`` value submitted). Relay them with the\n results; if the user corrects one, re-call with the real",
"inputSchema": {
"truncated": true,
"chars": 27386
},
"outputSchema": {
"type": "object",
"$defs": {
"AgentStatusSummary": {
"type": "object",
"title": "AgentStatusSummary",
"properties": {
"line": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"title": "Line",
"default": null
},
"detail": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"title": "Detail",
"default": null
},
"fields": {
"anyOf": [
{
"type": "array",
"items": {
"type": "object",
"additionalProperties": {
"type": "string"
}
}
},
{
"type": "null"
}
],
"title": "Fields",
"default": null
},
"status": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"title": "Status",
"default": null
},
"carrier": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"title": "Carrier",
"default": null
},
"premium": {
"anyOf": [
{
"type": "number"
},
{
"type": "string"
},
{
"type": "null"
}
],
"title": "Premium",
"default": null
},
"declined": {
"anyOf": [
{
"type": "boolean"
},
{
"type": "null"
}
],
"title": "Declined",
"default": null
},
"carrier_key": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"title": "Carrier Key",
"default": null
},
"term_months": {
"anyOf": [
{
"type": "integer"
},
{
"type": "null"
}
],
"title": "Term Months",
"default": null
},
"eta_seconds_remaining": {
"anyOf": [
{
"type": "integer"
},
{
"type": "null"
}
],
"title": "Eta Seconds Remaining",
"default": null
}
},
"additionalProperties": true
}
},
"title": "DispatchResult",
"properties": {
"note": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"title": "Note",
"default": null
},
"error": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"title": "Error",
"default": null
},
"needs": {
"anyOf": [
{
"type": "array",
"items": {
"type": "object",
"additionalProperties": true
}
},
{
"type": "null"
}
],
"title": "Needs",
"default": null
},
"ready": {
"anyOf": [
{
"type": "array",
"items": {
"type": "string"
}
},
{
"type": "null"
}
],
"title": "Ready",
"default": null
},
"agents": {
"anyOf": [
{
"type": "array",
"items": {
"$ref": "#/$defs/AgentStatusSummary"
}
},
{
"type": "null"
}
],
"title": "Agents",
"default": null
},
"detail": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"title": "Detail",
"default": null
},
"status": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"title": "Status",
"default": null
},
"recover": {
"anyOf": [
{
"type": "object",
"additionalProperties": true
},
{
"type": "null"
}
],
"title": "Recover",
"default": null
},
"skipped": {
"anyOf": [
{
"type": "array",
"items": {
"type": "object",
"additionalProperties": true
}
},
{
"type": "null"
}
],
"title": "Skipped",
"default": null
},
"assumptions": {
"anyOf": [
{
"type": "array",
"items": {
"type": "object",
"additionalProperties": true
}
},
{
"type": "null"
}
],
"title": "Assumptions",
"default": null
},
"example_arguments": {
"anyOf": [
{
"type": "object",
"additionalProperties": true
},
{
"type": "null"
}
],
"title": "Example Arguments",
"default": null
},
"coverage_selection": {
"anyOf": [
{
"type": "object",
"additionalProperties": true
},
{
"type": "null"
}
],
"title": "Coverage Selection",
"default": null
},
"authorization_recorded": {
"anyOf": [
{
"type": "boolean"
},
{
"type": "null"
}
],
"title": "Authorization Recorded",
"default": null
}
},
"additionalProperties": true
},
"annotations": {
"title": "Live carrier quotes",
"readOnlyHint": false,
"openWorldHint": true,
"idempotentHint": true,
"destructiveHint": true
}
}Foresee quotes auto in CA today. Get personal lines insurance quote estimates. Start with quote_insurance. `lines` is REQUIRED — ONE map from line name in plain words (auto, renters, home…) to that line's coverage ask as actual numbers. State only numbers the result contains — never interpolate. Best results: quote in your FIRST reply — when coverage wasn't chosen, price the common starting point (bi "100/300", pd 100, coll_deductible 500, comp_deductible 500, medpay 5000) as an adjustable, declared assumption rather than asking first. A renters ask names coverage_c (contents limit), coverage_e (liability), coverage_f (guest medical) and deductible; a home ask names coverage_a (dwelling limit, at replacement cost), coverage_e, coverage_f and aop_deductible — all in dollars. A line that isn't live yet comes back under skipped with honest copy — relay it, never quote a different line instead. ZIP, age and (for auto) the vehicle's year/make/model are REQUIRED with no server fallback: when the user implied one ('Sacramento', 'mid-20s'), pass a concrete value and tell them the assumption. Other omitted profile fields come back as explicit declared assumptions to relay, so you'll rarely need follow-up questions before the first call; only when most of the required facts are missing, ask ONE short round of 2-4 (plus military_affiliation when it might apply — USAA quotes only military members, veterans, and their families), then call with everything known — the response's assumptions, profile_required and coverage_required name anything still open, so a second round of questions never beats a first quote. After presenting quotes, offer to refine: each line's tighten_by list names the missing facts that most move the price — ask the user for them and re-quote with the answers — and each carrier's price_ladder answers limit/deductible what-ifs with exact one-lever prices (deductibles follow the user's cash buffer, liability limits their assets); a combined change is a re-call with the new ask. live_carrier_quotes submits profile details to the carriers' own websites — the user's own details or a hypothetical/synthetic profile both work; explicit user authorization required. Ask ONE round before the first call — the consent disclosure, identity, and every question its description lists for the line — so every carrier is walked at once. The call is idempotent per profile + coverage selection: call it again with the same arguments to collect progress and results — a profile already walked returns those results without re-submitting to the carriers.
Names, descriptions and schemas were written by the server and are shown as data.
Shared addresses on big platforms (Cloudflare, Vercel and the like) put unrelated servers together; those are marked shared_infrastructure. A match is a pivot, not a link between operators.