START WITH THE PRODUCT STEPS
Read START-HERE.txt first. It states the actual source acquisition, access/privacy limits, manual field mapping and exact next prompt. The original file templates and synthetic examples below are supporting review aids. Some paths need separately supplied documents or source text; a blank worksheet is not a native export or completed integration.

S25: Locate transcript excerpts with verified original page-and-line references
Starter kit
Status: Proposed / not tested

PURPOSE
Attorney provides a bounded list of topics/terms and approved transcripts → search locally, collect exact excerpts with surrounding questions/answers and verify printed transcript coordinates → review-only excerpt locator with unresolved search/OCR gaps.

PREREQUISITES
1. Synthetic/public or expressly approved deidentified text for the pilot; original transcript ID/version and distinction between printed transcript page and PDF page; approved terms/topics; locally exported search results; staff-verified original page/line fields. Real confidential transcripts stay in firm-approved storage and processing. Condensed four-up PDFs require explicit manual coordinate verification.
2. Synthetic files first. Real use requires firm-approved access, privacy, processing terms, retention controls, export coverage and a named reviewer.
3. Prepare any required original files or rendered evidence separately. This kit does not configure accounts, connectors or live actions.

FILES AND FORMATS
topics.csv: topic_id, approved_topic, approved_terms
transcripts.csv: transcript_id, version, original_locator, layout, coordinate_review_owner
search-hits.csv: hit_id, topic_id, transcript_id, version, exact_excerpt, surrounding_question_answer, printed_page, line_start, line_end, pdf_page, coordinate_status, truncation_flag, ocr_flag, source_locator
scope.txt: search method, search coverage and missing-hit limitations

Files without .example are blank input worksheets; CSV templates contain headers only. .example files contain invented records for the dry run. Text input .txt files contain blank labeled fields. Use the original base filename when supplying an example to the prompt, or explicitly map the example filename to that input. CSV files are UTF-8 with comma delimiters, quoted fields where needed, and CRLF row endings. Preserve identifiers as text when importing into Excel. Blank means missing or unresolved, never a zero or a pass. Multi-value fields use a pipe only where the fixture scope says so.

SETUP AND DRY RUN
1. Copy this kit to an approved working folder. Keep examples separate from any real exports. Do not upload client, privileged, personal, credential or financial-account data to an unapproved service.
2. Read the .example text policy/scope files and all .example.csv inputs together. They define this fixture only. For a real pilot, fill the blank templates from approved exports without changing headers and obtain approved policy values.
3. Use native read-only exports, exact joins and arithmetic for deterministic checks. This kit includes no executable automation, OAuth setup, live-action instructions or importable Make blueprint.
4. Give only the approved prepared inputs to a firm-approved text assistant and use the recipe prompt below. Keep source IDs, source row numbers and unresolved evidence visible.
5. Compare the proposed result with expected-fixture-result.txt. Verify every listed issue and that the prompt invents no missing evidence. The expected file describes assertions, not a performed workflow run.
6. Have the named reviewer check source evidence and record remaining questions before any separately authorized action.

RECIPE PROMPT
Organize these approved transcript search hits under only the supplied topics. Preserve exact wording, transcript ID/version, printed page and line references, separate PDF page locator and surrounding question/answer context. Never invent missing lines or silently fix OCR. Flag every unverified coordinate and possible truncated answer. Do not assess witness credibility, decide legal relevance, generate testimony or suggest that unreturned hits prove absence. This is a locator for attorney review, not a substitute for reading the transcript.

INPUTS
topics.csv: topic_id, approved_topic, approved_terms
transcripts.csv: transcript_id, version, original_locator, layout, coordinate_review_owner
search-hits.csv: hit_id, topic_id, transcript_id, version, exact_excerpt, surrounding_question_answer, printed_page, line_start, line_end, pdf_page, coordinate_status, truncation_flag, ocr_flag, source_locator; scope.txt: search method, search coverage and missing-hit limitations

OUTPUT
excerpt-locator.csv: hit_id, topic_id, transcript_id, version, exact_excerpt, surrounding_question_answer, printed_page, line_start, line_end, pdf_page, coordinate_status, truncation_flag, ocr_flag, source_locator. No credibility or legal-relevance judgment.

Use only these synthetic or firm-approved inputs and preserve source row/page IDs. Keep missing or conflicting evidence unresolved. Return a draft for the named reviewer. Do not send messages, connect accounts, change records or permissions, move money, or make legal decisions. Keep source files unchanged. List missing prerequisites before continuing.

REVIEW CHECKLIST
[ ] Headers match the exact input schema and the export covers the stated scope
[ ] Synthetic example files were used alone for the first dry run
[ ] Every output finding retains its original source ID/row/page reference
[ ] Missing keys, contradictions, unavailable originals and ambiguous dates remain unresolved
[ ] Every expected fixture finding is present; no live action or unsupported result is claimed
[ ] Responsible reviewer checks the original records before a real deployment

RECIPE-SPECIFIC REVIEW
Attorney/paralegal verifies every excerpt against the original and reviews adequate context. Test a four-up PDF, an answer spanning pages, a negated phrase and OCR corruption. Distinct from S01 institutional knowledge retrieval and citation QA of already-written drafts.

VALIDATION
Exact CSV header order, field counts, serialized round-trip values and fixture semantics were checked during kit preparation. This does not test OCR, a vendor integration, a model response or end-to-end reliability. All data and identifiers are synthetic. Dates are fixed fixture dates, not current monitoring results.
