G07: native input mapping
Find missing call outcomes and loss reasons

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
Calls -> native-calls-template.csv
Exact columns: call_alias,answer_state,staff_outcome_present,outcome_source,source_ref
Populate only from the recipe’s documented export or explicit manual evidence capture. Existing blanks and synthetic fixtures do not supply facts.

Leads -> native-leads-template.csv
Exact columns: lead_alias,status,loss_reason_present,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
calls.csv
Original first line: call_id,lead_alias,disposition_code,redacted_staff_note,owner_alias

closed-leads.csv
Original first line: lead_alias,supplied_status,loss_reason_code

code-dictionary.csv
Original first line: code,definition,allowed_stage

outcome-review.csv
Original first line: record_id,missing_or_conflicting_code,supported_suggestion,source_note_ref,owner,review_status

calls.csv -> Calls: create call_alias from a checked call reference. disposition_code can support staff_outcome_present only if the approved dictionary and actual recorded classification establish that meaning. Acquire answer_state, outcome_source and source_ref from observed evidence. Do not send redacted_staff_note to AI merely because its filename suggests redaction.
closed-leads.csv -> Leads: verify lead_alias and supplied_status before recording status. Establish loss_reason_present from the actual maintained field and approved code dictionary; blank, unavailable and absent are different states. Add source_ref.
code-dictionary.csv -> Scope: carry the approved outcome/loss definitions and permitted stages. outcome-review.csv is an old output, not new source evidence. Do not invent a Calls-to-Leads join.

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.
CallRail Excel is verified; universal staff disposition and Lawmatics loss-reason fields are not automatic.
The live account, entitlement, exact headers, records and field coverage have not been observed.

Recipe acquisition / manual mapping instructions
Download the actual call log
Location: Analytics > Activity > Calls > Call log > date/company filters > Edit Columns > Export > Excel
Select the reviewed companies and dates. Include only displayed administrative call classification fields needed for the check. Choose Excel, not Excel with transcriptions. Retain the filter cover sheet and raw workbook.
Verification: Do not rename Answered into a staff disposition or a qualified lead into a retained client. Date-based communication retention is capped at 25 months in current docs.
https://support.callrail.com/hc/en-us/articles/5711277622029-Export-Call-log
https://support.callrail.com/hc/en-us/articles/5711366294285-Viewing-caller-timelines-with-visitor-tracking

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 Status and the actual Sub-status used for loss reasons, plus a safe record locator. Record Lost matters in the selected 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
Create Calls from observed call metadata and Leads from the Lawmatics export. Use the firm’s approved outcome vocabulary. If CallRail has no recorded disposition field/tag or the integration lacks a cross-reference, check calls separately rather than invent a join. 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/10699805-matter-statuses
https://support.callrail.com/hc/en-us/articles/5711366294285-Viewing-caller-timelines-with-visitor-tracking


Do not proceed when
- No approved outcome dictionary, no actual loss-reason configuration, or missing call classification 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.
