G02: native input mapping Match ad spend with recorded intake stages Purpose and compatibility A blank file is an input scaffold, not a native export or completed mapping. Preserve the exact column names/order and input names. Populate only from the documented native acquisition or explicit manual evidence. Stop if a required input, permission, privacy condition or coverage requirement is missing. Do not replace an old prompt until the named inputs and field-level mapping are reviewed. These files do not authorize login, setup, imports, account changes, message sending, publication, test submissions or spending. Contract status: Requires distinct native-input templates or an explicit reviewed mapping; existing kit is not drop-in compatible Compatible without mapping: false Required inputs Spend -> native-spend-template.csv Exact columns: campaign_alias,period,currency,spend,source_ref Populate only from the recipe’s documented export or explicit manual evidence capture. Existing blanks and synthetic fixtures do not supply facts. Intake -> native-intake-template.csv Exact columns: lead_alias,campaign_alias,created_at,recorded_stage,stage_at,as_of,source_ref Populate only from the recipe’s documented export or explicit manual evidence capture. Existing blanks and synthetic fixtures do not supply facts. Scope -> native-scope-template.txt Required content: Full approved scope, source account aliases, date filters, date basis/timezone, as-of capture time, definitions, source-to-alias map provenance, matching rules, inspected/excluded records, permission/privacy limits, missing-data reasons, coverage and responsible reviewer. Include recipe-specific policies, versions and tests. Scope must be inside the AI workbook or pasted packet, not merely a separate unprovided file. Complete each required field from approved source evidence. Old files and reviewed mapping ads.csv Original first line: source_id,campaign_id,period,spend,currency,attribution_token attribution-review.csv Original first line: source_id,spend,unique_inquiries,booked_consults,confirmed_retained,unmatched_count,denominator,coverage_warning intake.csv Original first line: intake_alias,attribution_token,source_id,stage,stage_at scope.txt Original first line: G02: scope.txt stage-dictionary.csv Original first line: stage,approved_definition ads.csv -> Spend: verify campaign_id -> campaign_alias, period, currency and spend using the approved cross-tool map; add source_ref. Establish one observed row per campaign/period/currency and avoid multiplying spend when joining lead rows. intake.csv -> Intake: verify intake_alias -> lead_alias and campaign_alias through the existing approved attribution map. Verify stage -> recorded_stage and stage_at. Acquire created_at, as_of and source_ref separately. A current stage does not supply earlier stage timestamps. stage-dictionary.csv and scope.txt -> Scope: carry approved definitions, cohort, attribution window, timezone, currency and date basis. attribution-review.csv is an old output. Aggregate distinct verified leads before joining to Spend; do not invent identifiers or fuzzy-match people. How to perform the handoff 1. Keep original exports and raw evidence unchanged in restricted firm storage. Check actual source fields, dates, coverage, privacy and access before mapping. 2. Prepare the distinct native inputs above. Record every mapped field, derived interpretation, missing value and observed source reference in Scope. Identically named columns still require source/evidence validation. 3. Create a separate minimized analysis workbook or text packet. Name tables/sections exactly as listed. A CSV file does not itself create a named Excel table. 4. Include the full completed Scope in the same AI-visible workbook or pasted packet. Verify exclusions, denominator, matching rules and unknowns. Do not hide raw client data on another worksheet. 5. Obtain the responsible reviewer’s approval of the completed mapping and evidence coverage before using the native prompt. Keep all blocked items visible. Any later external action is a separately authorized human step. Acquisition and privacy requirements Use approved minimized administrative metadata and aliases only. Aliases alone do not guarantee anonymity. Keep untouched exports/screenshots, identifying source maps, full documents and sensitive narratives in restricted firm storage. A hidden worksheet is not a privacy boundary. Do not insert credentials, payment/tax identifiers, raw client documents or unsanitized review text. Unknown is not zero, false, completed or absent. Existing authorized access to the correct source account and records; no new login, credentials, installation or permission grant is included. Responsible lawyer/operations reviewer approves scope, definitions and any later action. AI optional; use only approved minimized data and retain originals separately. Aggregate spend alone cannot establish individual attribution. Existing CRM IDs/source capture and historical stage events may be absent. The live account, entitlement, exact headers, records and field coverage have not been observed. Recipe acquisition / manual mapping instructions Download scoped ad-spend data Location: Correct customer account > Campaigns statistics table > date/columns/segments > Download > Excel CSV or XLSX Display campaign identity, period, cost and selected measurement columns. Download the visible table after checking account, currency, timezone, dates and filters. Preserve native headers, totals and the source file. Verification: The download is aggregate advertising data, not a click-to-client ledger. Do not multiply each campaign spend by its number of lead rows. https://support.google.com/google-ads/answer/2404176?hl=en Get the actual Lawmatics rows Location: Reports > Custom Reports > existing matter report > eye/view icon > Export Use an existing authorized report, or have its owner prepare a targeted report with Source, Campaign, Created At, Converted At, Status, Stage and the exact existing attribution identifier if available. Record the agreed review period and matter scope, including which date field sets the range. Export the viewed report to CSV; large exports may arrive by email. Preserve headers and file unchanged. A report creation/save is a separate account write, not performed here. If no suitable report exists, use the documented Settings > Export > Export Matters route only in restricted storage, then minimize locally. Verification: A matter report may contain contact and matter fields. A contacts-only export omits matter fields. Date-created and date-converted scopes differ; exported grouping is not preserved. https://help.lawmatics.com/en/articles/10699961-exporting-custom-reports https://help.lawmatics.com/en/articles/10699766-exporting-data https://help.lawmatics.com/en/articles/10699953-custom-reporting-using-filters https://help.lawmatics.com/en/articles/10699957-custom-reporting-columns-grouping Make the checked, minimized handoff Location: Restricted original workbook > separate analysis workbook > Scope worksheet Staff verifies existing campaign/source identifiers and approved stage definitions. Aggregate distinct lead aliases by the approved attribution key and cohort first, then join to one Spend row per campaign/period/currency. Keep current-stage/as-of reporting separate from event-in-period counts; earlier stages require their real timestamped records. Never fuzzy-match names or reconstruct absent click IDs. Keep untouched original exports/screenshots and the identifying source map in restricted firm storage. Build a separate minimized analysis file; do not hide raw client data on another tab. Include the complete Scope/coverage note in the AI-visible workbook or prompt. Use aliases and administrative metadata only. Unknown is not zero, false, completed or absent. Verification: Every field has an observed source or an explicit missing reason; staff assignments are marked editorial, not native. https://support.microsoft.com/en-us/excel/merge-queries-power-query https://help.lawmatics.com/en/articles/10699957-custom-reporting-columns-grouping https://help.lawmatics.com/en/articles/10699953-custom-reporting-using-filters Do not proceed when - Missing existing cross-tool map, attribution window, comparable scope/currency or documented stage evidence. Scope template requirements Full approved scope, source account aliases, date filters, date basis/timezone, as-of capture time, definitions, source-to-alias map provenance, matching rules, inspected/excluded records, permission/privacy limits, missing-data reasons, coverage and responsible reviewer. Include recipe-specific policies, versions and tests. Scope must be inside the AI workbook or pasted packet, not merely a separate unprovided file. Old examples and validation limits Legacy synthetic examples and negative cases belong to their old prompts. They do not automatically test the native route and must not be fed into a new prompt without an explicit reviewed mapping and separately approved test design. These new files contain no synthetic values, source exports, account results or live-test evidence. Documentation-checked component path; proposed workflow, not tested Public official documentation checked 2026-10-15; no login, export, live query, import, installation, configuration, message or client workflow was executed. Local validation covers only exact scaffold schemas, placeholder presence, blank CSV rows and required warnings. It does not establish live account coverage, native export validity, successful integration or completed workflow tests.