SRSelf Rep Ready

Guides›AI & verification

Original framework · v4.2

Litigation Communication Posture Analyser

An upload-only framework for measuring who sounds like they control the evidentiary record—and who sounds like they need the other side to fix a problem for them.

It measures posture, not legal merit

The core question

Who is controlling the evidentiary battlefield?

A strong communicator tends to set the facts, cite the record and state a position. A weaker posture tends to follow the opponent’s structure, rely on inference and ask the opponent to explain or act. The analyser turns those differences into a transparent score with visible counts, examples, ratios and working.

A confident letter can still be legally wrong. A defensive letter can still be legally correct. The score describes the communication posture of one letter; it does not decide the case.

Why this is different
Most AI feedback says a letter is “strong,” “professional” or “persuasive” without defining those words. This framework requires the model to show its work across eight named measures, exclude non-advocacy material and separate record-based assertions from inference. A reader can disagree with the score because the reasoning is visible.

The eight-metric model

LHDS 10%

Legal hedge density

Substantive uncertainty language per 100 words.

DRS 15%

Declarative ratio

Direct statements compared with dependent or conditional sentences.

PES 5%

Paragraph economy

Average paragraph length after non-body material is removed.

ACS 5%

Argument concentration

Main propositions per estimated page, with a compound-proposition test.

ARR 15%

Assertion to request ratio

How often the writer states rather than asks the opponent to act.

CRS 15%

Concession rate

Substantive ground given away or accusations softened.

RRS 15%

Reactivity ratio

A five-level classification of who is setting the narrative agenda.

ERS 20%

Evidentiary reliance

Specific record-based assertions compared with inference and concern.

The weighted result places the letter in one of five posture bands: Dominant, Strong, Contested, Defensive or Weak. Evidence and narrative posture carry the most weight; style carries the least.

Copy the complete v4.2 analyser

This is the upload-only version. It accepts properly uploaded PDF or DOCX legal correspondence and refuses pasted text or other document types. The exclusions, thresholds, formula and required output structure are part of the invention—copy the complete prompt rather than extracting only the scoring table.

Litigation Communication Posture Analyser — v4.2

Download the complete prompt as a text file

Use one clean correspondence document

  1. Copy the complete prompt into a fresh AI chat.
  2. Wait for the analyser’s exact ready message.
  3. Upload one PDF or DOCX letter. Do not paste its text.
  4. Confirm the file is legal correspondence—not an affidavit, pleading, order, submission or evidence bundle.
  5. Read the metric counts and examples before looking at the composite score.
  6. Run a second time if needed and compare the working. Variation is information about the model’s reliability.
Do not score the whole case

The unit of analysis is the advocacy body of one letter. Letterhead, signatures, annexures, schedules, metadata and reproduced evidence are excluded. Combining different document types produces a misleading result.

A score is a lens, not a verdict

  • It does not assess whether the law is correct.
  • It does not predict who will win or whether a settlement will occur.
  • It does not prove confidence, motive or truth.
  • Its thresholds and weights are authored heuristics, not a validated clinical or legal scale.
  • Different AI models—or repeated runs—may classify sentences differently.
  • A low score may reflect a legitimate need to request information.
  • A high score may reflect overconfidence unsupported by the underlying case.

The useful question is not simply “What number did it receive?” It is: Which counted features produced the number, and do those classifications survive human checking?

Original framework published by Self Rep Ready. Version 4.2 is an experimental communication-analysis heuristic, not legal advice and not a validated predictor of litigation outcomes. Review uploaded material for confidentiality and court restrictions before using any AI service. Last reviewed: September 2026.