Observed congressional language, rendered as two cited automated composites.

Automated measurement. Composite prose is generated from claims selected and counted by code.

OnScript · 2026-08-24

Observed congressional language on 2026-08-24, rendered as two cited automated composites.

Democrats

Measurement: 51 publications were observed for the Democratic party on 2026-08-24.

Composite state: generated_verified

Across 51 statements today, no message rose to the level of a shared position among us. We note only that the phrase to make sure was the most synchronized language of the day, appearing 6 times, first recorded in our corpus from Juan Ciscomani (R-AZ).

A composite voice, machine-composed from the day’s measured phrases. No member spoke these exact sentences; the quoted spans are verbatim (see receipts).

generator: sonnet_direct · model: claude-sonnet-5 · verifier: passed

No talking point cleared the 3-member threshold today — nothing to cite.

Republicans

Measurement: 38 publications were observed for the Republican party on 2026-08-24.

Composite state: withheld_no_eligible_claim

Today 38 of us released statements. No phrase was shared by 3 or more of us today.

A composite voice, machine-composed from the day’s measured phrases. No member spoke these exact sentences; the quoted spans are verbatim (see receipts).

voice: deterministic template (not a language model) · verifier: passed

No talking point cleared the 3-member threshold today — nothing to cite.

How this is counted

Participation in eligible message claims

Each measure keeps one count unit from numerator through denominator.

D

  • Office participation: 0 offices of 44 offices. Window: party-day 2026-08-24. Method: participation-measures-v1.
  • Publication participation: 0 publications of 51 publications. Window: party-day 2026-08-24. Method: participation-measures-v1.
  • Document-family participation: 0 document families of 50 document families. Window: party-day 2026-08-24. Method: participation-measures-v1.

R

  • Office participation: 0 offices of 30 offices. Window: party-day 2026-08-24. Method: participation-measures-v1.
  • Publication participation: 0 publications of 38 publications. Window: party-day 2026-08-24. Method: participation-measures-v1.
  • Document-family participation: 0 document families of 38 document families. Window: party-day 2026-08-24. Method: participation-measures-v1.

These two bases differ. Office counts come from the day's eligible caucus offices in the nightly symmetry audit; publication counts come from the day's source publications. A joint release is one publication and can carry several offices, so the two never have to agree.

Nightly symmetry audit: nightly symmetry audit. Every distilled claim above is citation-backed.

Repeated phrase observations

This table lists repeated phrase observations, ranked by how many members used the same exact phrase. It is not filtered to coordinated messages, so it can include official names, procedural formulas, and biographical phrasing, not only messages. The sparkline is the phrase's 14-day trajectory.

Each party’s own most-synchronized phrases, ranked within the party so the larger caucus can’t fill the table — every count travels with its caucus denominator.

D repeated phrases

  1. 6 of 257 (2.3%) to make sure Phrase trend14 observations; peak 8 members.
  2. 4 of 257 (1.6%) american people deserve Phrase trend14 observations; peak 4 members.
  3. 4 of 257 (1.6%) a real impact Phrase trend14 observations; peak 4 members.
  4. 4 of 257 (1.6%) end in sight Phrase trend14 observations; peak 4 members.
  5. 4 of 257 (1.6%) recruitment and retention Phrase trend14 observations; peak 4 members.
  6. 4 of 257 (1.6%) and the american people Phrase trend14 observations; peak 4 members.
  7. 4 of 257 (1.6%) support they need Phrase trend14 observations; peak 6 members.
  8. 4 of 257 (1.6%) the trump administration’s Phrase trend14 observations; peak 5 members.
  9. 3 of 257 (1.2%) come home and how dod plans
  10. 3 of 257 (1.2%) exploited and left without supplies recourse

R repeated phrases

  1. 4 of 271 (1.5%) to make sure Phrase trend14 observations; peak 8 members.
  2. 3 of 271 (1.1%) need to make Phrase trend14 observations; peak 3 members.
  3. 3 of 271 (1.1%) the next generation Phrase trend14 observations; peak 9 members.
  4. 3 of 271 (1.1%) resources they need Phrase trend14 observations; peak 4 members.
  5. 3 of 271 (1.1%) proud to support Phrase trend14 observations; peak 5 members.

Each table is one party measured against that party's own caucus, so row counts are not comparable across the two. Differences in how much each party publishes are measured in the nightly symmetry audit, not here. See the nightly symmetry audit.