Prepare a source-linked factual chronology

Practice relevance

Cross-practice idea · Useful supporting administrative method; no claim of practice-specific legal instructions.

Scope: Excel sort and staff-approved source documents; jurisdiction-neutral factual chronology, not evidence assessment.

The problem

Order supported events while keeping ambiguous dates and source conflicts visible.

Why it matters: A screenshot date, a message date and the time of an event may differ. Preserving the original timestamp, timezone and source locator prevents a neat timeline from hiding uncertainty or implying unsupported causation.

Sources & evidence

Proposed / not tested. The public source describes the problem. Documentation supports only the stated method components; no result from this recipe has been verified.

What’s been verified

Source methods and reported problems have been reviewed. We have not run the adapted workflow. The sample below describes expected behavior on synthetic data, not a customer result.

What to measure: In a synthetic pilot, count correctly found exceptions, false alarms, and unresolved inputs. No time or cost saving is assumed.

Pain evidence: Organization help ↗Organization help, 2024-08-22, older: a family-law paralegal describes organizing many texts, emails and photos, putting them in order and separating issues. This is a distinct output from S02's broken-link report even though the same firsthand account supports both.
Method: Sort data in Excel ↗Sort data in Excel documents multi-column sorting and warns that dates stored as text do not sort like real dates.

Source checked: October 15, 2026. Pain accounts are self-reported. Documentation supports components; this adapted recipe and prompt have not been tested. We wrote these prompts. The adapted workflow hasn’t been tested.

Suggested approach

Start when: Attorney requests a factual chronology

normalize supplied date metadata without overwriting originals and sort source-linked rows
Keep source references and report unknowns instead of filling gaps.
The responsible reviewer checks the report before any separately approved action.

Limits and review

The assistant drafts or reports only. Check source records and review the output before a human performs any separately approved send or change. No automatic legal decision, money movement, account connection or publication is included.

Who reviews it: Attorney/paralegal checks originals and timezones. Test day/month ambiguity, a daylight-saving transition and a screenshot whose capture date differs from the message date. The result is an index, not an evidentiary or legal conclusion.

What you need

Your firm-approved AI assistant · prepared files

Bounded source set, reviewer-approved neutral descriptions/topic tags and the meaning of each timestamp; Excel available for deterministic sorting.
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.
Use synthetic inputs first. Keep real data in firm-approved accounts and processing, with appropriate access, confidentiality and retention controls. Aliases alone do not anonymize records. Never paste credentials, API keys or unnecessary client details.

How to use

Documentation-verified component path; proposed adaptation, not tested

Before you start

File creation/modification/capture time is not necessarily event time. No universal forensic metadata export or causation determination is claimed.

Check access and setup

Actual account access, source versions/completeness, privacy approval and reviewer sign-off were not observed.

Capture factual date evidence from originals
Acrobat/Word/Outlook and local ledger · Open each source; PDF Select text; Outlook selected message Save as
For each included item, manually record source_id,version,exact timestamp string,stated timezone or offset,date_kind,document/page/message locator and owner-approved neutral description. Keep message dates, file timestamps and screenshot capture dates distinct. Leave missing or ambiguous dates unresolved.
Expected output
events working ledger with source references and date semantics; not an advertised product export.
Next step
Create a separate minimized TXT with one labelled row per event and the approved scope/policy.
Check before continuing
Do not infer a date from a filename or interpret ambiguous numeric dates. Capture all inclusion/exclusion decisions.
Step documentation 1 ↗Step documentation 2 ↗Step documentation 3 ↗
Load only the approved AI input
Acrobat PDF Spaces · Acrobat homepage > PDF Spaces > Create a PDF Space > upload files or Paste copied text > Add to PDF Space
Add the minimized factual event ledger and approved scope/date policy. 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.
Next step
Use the AI Assistant message field in this same space for the next prompt.
Check before continuing
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.
Step documentation 1 ↗Step documentation 2 ↗Step documentation 3 ↗
Run the bounded prompt and inspect citations
Acrobat AI Assistant · The PDF Space AI Assistant message field
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.
Acrobat AI Assistant promptReview only these approved factual metadata rows. Preserve original timestamp strings, date_kind and source locators. Propose a chronology using only unambiguous explicitly supplied dates and offsets; flag unknown timezone, daylight-saving ambiguity, conflicting dates or unclear date_kind separately. Use supplied neutral descriptions/topic tags only. Keep same-time entries distinct. Return source_id,original_timestamp,approved_sort_timestamp if supplied,description,source_locator,issue. Do not infer event dates, causation, credibility, legal relevance, missing events or deadlines.
Expected output
Draft chronology and date-ambiguity list retaining every included source row.
Next step
Save the checked draft as chronology-review.txt; carry source IDs, versions and reviewer corrections into the next review step.
Check before continuing
Human must approve any normalized sort timestamp; the AI proposal is not a forensic timestamp determination.
Step documentation 1 ↗
Sort the reviewed ledger
Excel · Data > Sort > Sort by approved_sort_timestamp > Oldest to Newest; Add Level for source_id
Copy the reviewed rows into Excel; retain original text dates separately. Use only reviewer-approved, consistently normalized timestamps for sorting. Keep unknown dates on an explicitly unresolved sheet; sort the entire row range, not one isolated column.
Expected output
Source-linked chronological index plus unresolved-date sheet.
Next step
Save the local workbook with the frozen input list and source map.
Check before continuing
Verify numeric/date cell types; same timestamps remain separate, and row count is conserved.
Step documentation 1 ↗
Human review and final handoff
Final human review
Responsible staff reviewer and lawyer/process owner · Local reviewed report beside the frozen source set
Lawyer/paralegal verifies the source references and date semantics before using the index.
Expected output
Reviewed factual chronology with uncertainty and coverage statement.
Next step
An index aids navigation; it makes no evidentiary or legal finding.
Check before continuing
All unresolved or unreadable evidence stays open. No inferred approval or external action follows from AI output.
Step documentation 1 ↗

What you’ll get

chronology.csv: source_id, original_timestamp, stated_timezone, normalized_time_if_supported, source_locator, neutral_description, approved_topic_tags, uncertainty, reviewer_question. Unknown dates remain unresolved.

Inputs and a sample test Synthetic example · not a measured result

Input files

events.csv: source_id, original_timestamp, stated_timezone, source_locator, neutral_description, approved_topic_tags, date_conflict_note
scope.txt: approved timestamp formats, source coverage and reviewer

Synthetic example

Synthetic inputs are included in the starter kit.
events.example.csv
scope.example.txt

Expected output

Known chronology: E1 and E4 both normalize to 2026-10-01T09:00:00Z, remain separate and retain source locators.
E2: day/month ambiguity stays unresolved.
E3: repeated DST local time lacks offset; do not guess a UTC instant.
E5: capture/message-date conflict stays in review despite parseable capture time. Do not treat screenshot capture as event time.
No invented events, chronology gaps, causation, credibility, or legal relevance.

Test a failure

Attorney/paralegal checks originals and timezones. Test day/month ambiguity, a daylight-saving transition and a screenshot whose capture date differs from the message date. The result is an index, not an evidentiary or legal conclusion.

Try with the sample files

Follow the tool steps above and use the inputs named in each step. Where provided, native-* files are blank scaffolds and NATIVE-INPUT-MAPPING explains their fields. Original examples and the optional full review prompt use a separate prepared-input schema. Keep them separate unless the mapping explicitly connects them. Downloading a kit does not connect accounts or prove the workflow works.

Download inputs and checklist 8 files

Instructions, blank templates and separate synthetic examples; these files do not install an automation. Blank templates still need verified source data.

Download starter kit All inputs, synthetic examples and review notes in one ZIP. No automation is installed.
Start here: get the sources and prepare the review Documentation-checked acquisition, explicit manual mapping, exact prompts and human review limits
events.csv Blank input template with exact recipe headers.
events.example.csv Separate synthetic fixture input. Do not mix these rows into real exports.
scope.txt Blank text input worksheet. Fill its fields with approved evidence; no default assumptions are supplied.
scope.example.txt Separate synthetic text input fixture; use with the example CSV files only.
Expected fixture findings Read-only expected output and failure conditions for the included synthetic input files.
Setup and review checklist Recipe-specific prerequisites, file mapping, prompt, setup steps, checklist and limits.

Optional full review prompt for prepared inputs

Prepared-input review prompt with Your firm-approved AI assistant · prepared files

Create a factual chronology from these approved metadata rows. Preserve original date strings and source locators. Normalize only unambiguous dates with supplied timezones; put ambiguous or conflicting dates in a separate review list. Sort known timestamps and keep same-time entries distinct. Use the supplied neutral descriptions and topic tags only. Do not infer causation, credibility, legal relevance, missing events or deadlines. Every row must retain a source citation.

INPUTS
events.csv: source_id, original_timestamp, stated_timezone, source_locator, neutral_description, approved_topic_tags, date_conflict_note
scope.txt: approved timestamp formats, source coverage and reviewer

OUTPUT
chronology.csv: source_id, original_timestamp, stated_timezone, normalized_time_if_supported, source_locator, neutral_description, approved_topic_tags, uncertainty, reviewer_question. Unknown dates remain unresolved.

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.

Proposed / not tested · editorial prompt. This prompt uses the original prepared-input schema shown in the sample test. Step prompts may use different tables. Follow NATIVE-INPUT-MAPPING where supplied; do not mix the original examples with native-step inputs without mapping and checking every field.

Read original method Read pain evidence