# highsierralabs/laconic_tests architecture

> Architecture diagram of the GitHub repository highsierralabs/laconic_tests, generated by GitDiagram from its file tree, README and a sample of source files (last updated 2026-09-26). It is an AI-made overview: check details against the source.

- Interactive diagram: https://gitdiagram.com/highsierralabs/laconic_tests
- Repository: https://github.com/highsierralabs/laconic_tests
- Video tour (about a minute): https://gitdiagram.com/highsierralabs/laconic_tests/video

## Overview

Laconic_tests is an empirical study of whether a short LLM instruction reduces verbosity without losing decision-critical content. The workflow applies the directive to scored prompts across three models and modes, preserves their transcripts, normalizes replies, and compares response length and retained rubric items; results are summarized and visualized. The graph includes the documented human-scoring and adaptation branches. Source sampling confirms transcript parsing and figure generation; scoring relationships follow the README and docs descriptions rather than inspected scoring implementation.

Main entry points: [`scripts/parse_transcripts.py`](https://github.com/highsierralabs/laconic_tests/blob/main/scripts/parse_transcripts.py) (Transcript parser), [`directive/laconic_v2.md`](https://github.com/highsierralabs/laconic_tests/blob/main/directive/laconic_v2.md) (Laconic directive), [`prompts/round2_prompts.md`](https://github.com/highsierralabs/laconic_tests/blob/main/prompts/round2_prompts.md) (Scored prompts), [`data/raw`](https://github.com/highsierralabs/laconic_tests/tree/main/data/raw) (Raw transcripts)

## Diagram (Mermaid)

```mermaid
flowchart TD

subgraph group_experiment["Experiment design"]
  node_directive["Laconic directive<br/>[laconic_v2.md]"]
  node_prompts["Scored prompts<br/>[round2_prompts.md]"]
end

subgraph group_corpus["Response corpus"]
  node_raw["Raw transcripts"]
  node_parser["Transcript parser"]
  node_responses["Normalized replies"]
  node_wordcounts["Word counts<br/>[word_counts.csv]"]
end

subgraph group_evaluation["Scoring and analysis"]
  node_rubric["Scoring rubric<br/>[scoring.md]"]
  node_item_scores["Item scores<br/>[scores_items.csv]"]
  node_response_scores["Response scores"]
  node_summary["Study summary<br/>[summary.md]"]
  node_figures["Study figures"]
end

subgraph group_reuse["Reuse"]
  node_adaptation["Adaptation guidance<br/>[adapting.md]"]
end

node_researcher(("Researcher"))
node_models{{"LLM models"}}
node_scorers(("Human scorers"))

node_researcher -->|"selects"| node_directive
node_researcher -->|"selects"| node_prompts
node_directive -->|"instructs"| node_models
node_prompts -->|"prompts"| node_models
node_models -->|"produce transcripts"| node_raw
node_raw -->|"reads"| node_parser
node_parser -->|"writes replies"| node_responses
node_parser -->|"writes counts"| node_wordcounts
node_responses -->|"present for scoring"| node_scorers
node_rubric -->|"guides scoring"| node_scorers
node_scorers -->|"record item judgments"| node_item_scores
node_scorers -->|"record response judgments"| node_response_scores
node_item_scores -->|"feeds retention plot"| node_figures
node_wordcounts -->|"feeds word plots"| node_figures
node_researcher -.->|"consults"| node_adaptation

click node_directive "https://github.com/highsierralabs/laconic_tests/blob/main/directive/laconic_v2.md"
click node_prompts "https://github.com/highsierralabs/laconic_tests/blob/main/prompts/round2_prompts.md"
click node_raw "https://github.com/highsierralabs/laconic_tests/tree/main/data/raw"
click node_parser "https://github.com/highsierralabs/laconic_tests/blob/main/scripts/parse_transcripts.py"
click node_responses "https://github.com/highsierralabs/laconic_tests/tree/main/data/responses"
click node_wordcounts "https://github.com/highsierralabs/laconic_tests/blob/main/results/word_counts.csv"
click node_rubric "https://github.com/highsierralabs/laconic_tests/blob/main/docs/scoring.md"
click node_item_scores "https://github.com/highsierralabs/laconic_tests/blob/main/results/scores_items.csv"
click node_response_scores "https://github.com/highsierralabs/laconic_tests/blob/main/results/scores_response.csv"
click node_summary "https://github.com/highsierralabs/laconic_tests/blob/main/results/summary.md"
click node_figures "https://github.com/highsierralabs/laconic_tests/tree/main/figures"
click node_adaptation "https://github.com/highsierralabs/laconic_tests/blob/main/docs/adapting.md"

classDef toneNeutral fill:#f8fafc,stroke:#334155,stroke-width:1.5px,color:#0f172a
classDef toneBlue fill:#dbeafe,stroke:#2563eb,stroke-width:1.5px,color:#172554
classDef toneAmber fill:#fef3c7,stroke:#d97706,stroke-width:1.5px,color:#78350f
classDef toneMint fill:#dcfce7,stroke:#16a34a,stroke-width:1.5px,color:#14532d
classDef toneRose fill:#ffe4e6,stroke:#e11d48,stroke-width:1.5px,color:#881337
classDef toneIndigo fill:#e0e7ff,stroke:#4f46e5,stroke-width:1.5px,color:#312e81
classDef toneTeal fill:#ccfbf1,stroke:#0f766e,stroke-width:1.5px,color:#134e4a
class node_directive,node_prompts toneBlue
class node_raw,node_parser,node_responses,node_wordcounts toneAmber
class node_rubric,node_item_scores,node_response_scores,node_summary,node_figures toneMint
class node_adaptation toneRose
class node_researcher,node_models,node_scorers toneIndigo
```

## Components

### Experiment design

- [Laconic directive](https://github.com/highsierralabs/laconic_tests/blob/main/directive/laconic_v2.md): `directive/laconic_v2.md`
- [Scored prompts](https://github.com/highsierralabs/laconic_tests/blob/main/prompts/round2_prompts.md): `prompts/round2_prompts.md`

### Response corpus

- [Raw transcripts](https://github.com/highsierralabs/laconic_tests/tree/main/data/raw): `data/raw`
- [Transcript parser](https://github.com/highsierralabs/laconic_tests/blob/main/scripts/parse_transcripts.py): `scripts/parse_transcripts.py`
- [Normalized replies](https://github.com/highsierralabs/laconic_tests/tree/main/data/responses): `data/responses`
- [Word counts](https://github.com/highsierralabs/laconic_tests/blob/main/results/word_counts.csv): `results/word_counts.csv`

### Scoring and analysis

- [Scoring rubric](https://github.com/highsierralabs/laconic_tests/blob/main/docs/scoring.md): `docs/scoring.md`
- [Item scores](https://github.com/highsierralabs/laconic_tests/blob/main/results/scores_items.csv): `results/scores_items.csv`
- [Response scores](https://github.com/highsierralabs/laconic_tests/blob/main/results/scores_response.csv): `results/scores_response.csv`
- [Study summary](https://github.com/highsierralabs/laconic_tests/blob/main/results/summary.md): `results/summary.md`
- [Study figures](https://github.com/highsierralabs/laconic_tests/tree/main/figures): `figures`

### Reuse

- [Adaptation guidance](https://github.com/highsierralabs/laconic_tests/blob/main/docs/adapting.md): `docs/adapting.md`

### Other components

- **Researcher**
- **LLM models**
- **Human scorers**

## Connections

- Researcher → Laconic directive: selects
- Researcher → Scored prompts: selects
- Laconic directive → LLM models: instructs
- Scored prompts → LLM models: prompts
- LLM models → Raw transcripts: produce transcripts
- Raw transcripts → Transcript parser: reads
- Transcript parser → Normalized replies: writes replies
- Transcript parser → Word counts: writes counts
- Normalized replies → Human scorers: present for scoring
- Scoring rubric → Human scorers: guides scoring
- Human scorers → Item scores: record item judgments
- Human scorers → Response scores: record response judgments
- Item scores → Study figures: feeds retention plot
- Word counts → Study figures: feeds word plots
- Researcher → Adaptation guidance: consults