Find missing call outcomes and loss reasons Get the source data and prepare the review Documentation-checked component path; proposed workflow, not tested WHAT WAS CHECKED Public official documentation and supplied candidate artifacts only. No product login, account exports, client data, installation, credential access, external writes, advertising spend, template imports or live tests. Proposed prompts do not prove a feature supports every requested field. Missing required source data blocks execution. BEFORE YOU START - 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. DATA ACQUISITION LIMITS - CallRail Excel is verified; universal staff disposition and Lawmatics loss-reason fields are not automatic. STOP IF - No approved outcome dictionary, no actual loss-reason configuration, or missing call classification evidence. KEEP THE ANALYSIS COPY SEPARATE 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. INPUT FORMAT LIMIT All capitalized analysis tables and alias fields are editorial contracts. Native exports retain real vendor headers; mapping is explicit. No blank starter template is evidence of available data. NATIVE REVIEW INPUTS version: 1 status: Requires distinct native-input templates or an explicit reviewed mapping; existing kit is not drop-in compatible compatibleWithoutMapping: False existingKitFilesInspected: - file: calls.csv firstLine: call_id,lead_alias,disposition_code,redacted_staff_note,owner_alias - file: closed-leads.csv firstLine: lead_alias,supplied_status,loss_reason_code - file: code-dictionary.csv firstLine: code,definition,allowed_stage - file: outcome-review.csv firstLine: record_id,missing_or_conflicting_code,supported_suggestion,source_note_ref,owner,review_status requiredNativeInputs: - name: Calls kind: editorial_table proposedDistinctTemplate: native-calls-template.csv columns: - call_alias - answer_state - staff_outcome_present - outcome_source - source_ref acquisitionRequirement: Populate only from the recipe’s documented export or explicit manual evidence capture. Existing blanks and synthetic fixtures do not supply facts. - name: Leads kind: editorial_table proposedDistinctTemplate: native-leads-template.csv columns: - lead_alias - status - loss_reason_present - source_ref acquisitionRequirement: Populate only from the recipe’s documented export or explicit manual evidence capture. Existing blanks and synthetic fixtures do not supply facts. - name: Scope kind: approved_text_section proposedDistinctTemplate: native-scope-template.txt requiredContent: 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. templateFilesCreatedByThisTask: False requiredGate: Kit owner must add the named inputs or document field-level mapping before replacing an existing kit prompt. Preserve the old kit contract; never rename headers without acquiring missing evidence. OPEN THE INPUT MAPPING GUIDE NATIVE-INPUT-MAPPING.txt Use the distinct native input scaffolds listed below. Complete them from the acquired, reviewed evidence and include every required scope section in the AI-visible packet. Existing synthetic examples exercise the original review prompt only. They are not acquired evidence or a test of this native chain. Calls: native-calls-template.csv Leads: native-leads-template.csv Scope: native-scope-template.txt STEP 1: Download the actual call log Tool: CallRail Open: Analytics > Activity > Calls > Call log > date/company filters > Edit Columns > Export > Excel Access needed: Existing authorized access and relevant plan/region feature; exact live subscription and permissions not tested. No setup or persistent access changes included. AI role: not_an_ai_step 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. Expected output: Native Excel log with actual selected columns and filter cover sheet. Use it next: Inspect native headers locally; separately capture Lead Qualification/Tags from the caller timeline if not present in the export. Check: 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. Documentation limit: The source verifies the component feature; workflow prompts, schemas, manual captures, checks and handoffs are proposed editorial adaptations. Source documentation: 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 STEP 2: Get the actual Lawmatics rows Tool: Lawmatics Open: Reports > Custom Reports > existing matter report > eye/view icon > Export Access needed: Existing authorized access and relevant plan/region feature; exact live subscription and permissions not tested. No setup or persistent access changes included. AI role: not_an_ai_step 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. Expected output: Native matter/contact-field rows; no promise of task history, audit history, destination IDs or custom fields that the firm never recorded. Use it next: Open in restricted Excel; compare rows to matter records before preparing aliases. Check: 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. Documentation limit: The source verifies the component feature; workflow prompts, schemas, manual captures, checks and handoffs are proposed editorial adaptations. Source documentation: 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 STEP 3: Make the checked, minimized handoff Tool: Excel / source-record reviewer Open: Restricted original workbook > separate analysis workbook > Scope worksheet Access needed: Existing authorized access and relevant plan/region feature; exact live subscription and permissions not tested. No setup or persistent access changes included. AI role: not_an_ai_step 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. Expected output: Calls(call_alias,answer_state,staff_outcome_present,outcome_source,source_ref); Leads(lead_alias,status,loss_reason_present,source_ref); Scope(outcome_rules,coverage) Use it next: Format each approved range as a named table. Carry source-row references and coverage into the analysis workbook. Check: Every field has an observed source or an explicit missing reason; staff assignments are marked editorial, not native. Documentation limit: The source verifies the component feature; workflow prompts, schemas, manual captures, checks and handoffs are proposed editorial adaptations. Source documentation: 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 STEP 4: Ask AI to inspect the checked inputs Tool: Excel Copilot, optional Open: Analysis workbook > Copilot icon at lower right > Chat only Access needed: Existing authorized access and relevant plan/region feature; exact live subscription and permissions not tested. No setup or persistent access changes included. AI role: downstream_application_ai Open the minimized workbook containing the named tables and Scope. Paste the exact prompt; if unavailable, perform the same rule checks manually. PASTE THIS PROMPT Inspect Calls, Leads and Scope. Flag missing staff call outcomes and Lost leads with no recorded approved loss-reason sub-status. Keep system answer_state separate from staff_outcome. List unknown/unsupported fields separately. Do not infer a reason from call duration, a missed call, transcript sentiment or case merits. Return alias,missing_field,source_ref,staff_question,reviewer_status=pending. Expected output: Two internal exception queues and missing-field list. Use it next: Copy checked results into a new Review sheet, retaining source references and unresolved blockers. Check: A no-answer event is not a loss reason; staff decides factual disposition. Documentation limit: The source verifies the component feature; workflow prompts, schemas, manual captures, checks and handoffs are proposed editorial adaptations. Source documentation: https://support.microsoft.com/en-us/excel/copilot/get-started-with-copilot-in-excel STEP 5: Human review and final action Tool: Responsible firm reviewer Open: Internal Review worksheet / review document Access needed: Existing authorized access and relevant plan/region feature; exact live subscription and permissions not tested. No setup or persistent access changes included. AI role: not_an_ai_step Staff checks cited calls/matters and supplies only outcomes they know. Keep unknown reasons unknown. Save the reviewed exception list. Expected output: Reviewed completeness list. Use it next: If separately approved, a human edits the original classification field/sub-status. Check: No recordings, transcripts, caller identities or client narratives enter downstream AI. Documentation limit: The source verifies the component feature; workflow prompts, schemas, manual captures, checks and handoffs are proposed editorial adaptations. Source documentation: https://support.callrail.com/hc/en-us/articles/5711366294285-Viewing-caller-timelines-with-visitor-tracking https://help.lawmatics.com/en/articles/10699805-matter-statuses ACCOUNT AND SOURCE CHECKS STILL NEEDED - The live account, entitlement, exact headers, records and field coverage have not been observed. USING THE FILES IN THIS KIT Use the exact files or source text named in the steps above. Native exports keep their own headers. The kit tables are editorial review worksheets; they are not a claim that a product exports those fields. Some routes use reviewed text directly or require additional original files. Never rename an unreviewed raw export to make it appear mapped. Keep expected-result files separate from inputs. The source account, actual data, prompts and end-to-end workflow were not tested. Any final communication, filing, permission change, payment or publication needs its own authorized human action. This guide performs none.