Locate transcript excerpts with verified original page-and-line references
Get the source data and prepare the review

Documentation-verified component path; proposed adaptation, not tested

WHAT WAS CHECKED
Official public documentation checked 2026-10-15; no account, source-data acquisition, prompt run or end-to-end workflow was tested. Menus/features are vendor-documented; prompts, field maps and human gates are editorial adaptations. No actual client work, account login, installation, connection, external write or site edit occurred.

BEFORE YOU START
- Actual authorized transcript PDF or faithful typed transcript, source/version IDs, lawyer-approved topic list and a reviewer who can read original printed page/line numbers.
- Existing firm-approved Acrobat Studio, AI Assistant add-on, or another plan including Acrobat AI; online services/cloud storage, language and region must be permitted. No purchase, login or connection is part of this verification. The manual route works without AI.
- Preserve original evidence unchanged in restricted storage. Use synthetic material first. Prepare a separate, explicitly approved minimized AI input; aliases alone do not anonymize narrative or attachments. Do not upload raw originals or an alias key merely because another tab/file is sanitized.

DATA ACQUISITION LIMITS
- AI citation numbers and PDF page indexes are not transcript page/line citations. A transcript without trustworthy original coordinates blocks final citation output.

WHEN THIS CAN RUN
Blocked until actual sources, permissions and required human approvals are supplied; no real inputs were available in this verification.

STEP 1: Acquire and map the actual transcript
Tool: Acrobat desktop
Open: Open transcript > page navigation and Select text
Access needed: See recipe prerequisites; exact account entitlement and permissions not observed.

Preserve the actual transcript unchanged and record source/version, page count, draft/final/errata status and the approved search scope. Use an explicitly approved bounded transcript PDF or faithful typed transcript for the first AI search; do not manually identify all relevant pages first. A synthetic/public transcript is the pilot default. If privacy approval excludes a full transcript, staff must supply a bounded approved excerpt set and label that reduced coverage. Do not invent original page or line numbers.

Expected output: Actual approved bounded transcript source, topic list and scope/version manifest; original coordinate map may be incomplete until candidate hits are checked.
Use it next: Load the approved transcript source and topics first; locate candidates, then verify original page/line coordinates for those hits locally.
Check: Page-number collisions, rough drafts, errata and missing line numbers stay explicit; exact locator may be null.
Documentation limit: Sources support named component capabilities. Capture fields, prompts and review requirements are the proposed adaptation, not promised native export columns.
Source documentation:
https://helpx.adobe.com/acrobat/using/reusing-pdf-content.html
https://helpx.adobe.com/acrobat/desktop/get-started/learn-the-basics/navigation.html

STEP 2: Load only the approved AI input
Tool: Acrobat PDF Spaces
Open: Acrobat homepage > PDF Spaces > Create a PDF Space > upload files or Paste copied text > Add to PDF Space
Access needed: See recipe prerequisites; exact account entitlement and permissions not observed.

Add the explicitly approved bounded transcript PDF or faithful typed transcript, topic terms and source/scope/version manifest. Include any already verified coordinate map, but do not fabricate one before candidate search. Use clear source/version labels and verify the Files panel. Do not add originals that have not separately been cleared for Adobe processing.

Expected output: Visible approved source set in the PDF Space; no account integration is implied.
Use it next: Use the AI Assistant message field in this same space for the next prompt.
Check: Confirm every named source is actually loaded and readable. PDF Spaces supports up to 100 files, 100 MB and 600 pages per file; unsupported/password-protected/handwritten material blocks affected extraction.
Documentation limit: Sources support named component capabilities. Capture fields, prompts and review requirements are the proposed adaptation, not promised native export columns.
Source documentation:
https://helpx.adobe.com/acrobat/desktop/explore-pdf-spaces/create-pdf-spaces.html
https://helpx.adobe.com/acrobat/desktop/explore-pdf-spaces/supported-formats-limitations.html
https://helpx.adobe.com/acrobat/desktop/explore-pdf-spaces/pdf-spaces-faq.html

STEP 3: Run the bounded prompt and inspect citations
Tool: Acrobat AI Assistant
Open: The PDF Space AI Assistant message field
Access needed: See recipe prerequisites; exact account entitlement and permissions not observed.

Paste the prompt below. Open each source-number citation, check it, and use Copy to transfer the answer into a new local Word document or text file. Correct errors using the originals before reliance.

PASTE THIS PROMPT
Locate candidate excerpts for the supplied topic list using only these transcript sources. Return topic_id,transcript_id,version,candidate quotation,source block,PDF page,original printed page,start_line,end_line and uncertainty. Use original page/line values only when supplied and verified; otherwise set them null. Include nearby question/answer context and distinguish speaker labels. Do not invent coordinates, re-number lines, summarize testimony as established fact, determine credibility or legal relevance, or change a transcript. A candidate hit requires human original-page verification.

Expected output: Candidate excerpt list with supported coordinates or nulls and context.
Use it next: Save the checked draft as transcript-excerpt-review.docx; carry source IDs, versions and reviewer corrections into the next review step.
Check: Open the actual original page for every hit; verify literal quote, speaker, page, line span and any errata.
Documentation limit: Sources support named component capabilities. Capture fields, prompts and review requirements are the proposed adaptation, not promised native export columns.
Source documentation:
https://helpx.adobe.com/acrobat/desktop/use-acrobat-ai/generative-ai-features/ai-get-answers.html

STEP 4: Human review and final handoff
Tool: Responsible staff reviewer and lawyer/process owner
Open: Local reviewed report beside the frozen source set
Access needed: See recipe prerequisites; exact account entitlement and permissions not observed.

Reviewer manually searches the original using a distinctive phrase, reads the full question/answer, and writes verified original page:line spans into the local list. Mark unverified coordinates unresolved. Only now complete the coordinate map for verified hits, retaining PDF index separately from printed page and original line span. Unknown coordinates remain null.

Expected output: Verified locator list for lawyer review, with coverage and version.
Use it next: Lawyer decides whether and how an excerpt may be used; no quote is inserted into a filing automatically.
Check: All unresolved or unreadable evidence stays open. No inferred approval or external action follows from AI output.
Documentation limit: Sources support named component capabilities. Capture fields, prompts and review requirements are the proposed adaptation, not promised native export columns.
Source documentation:
https://helpx.adobe.com/acrobat/desktop/use-acrobat-ai/generative-ai-features/ai-get-answers.html

ACCOUNT AND SOURCE CHECKS STILL NEEDED
- Actual account access, source versions/completeness, privacy approval and reviewer sign-off were not 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.
