# jairzinhosantos/metaprompting-for-academic-deep-research architecture

> Architecture diagram of the GitHub repository jairzinhosantos/metaprompting-for-academic-deep-research, generated by GitDiagram from its file tree, README and a sample of source files (last updated 2026-09-22). It is an AI-made overview: check details against the source.

- Interactive diagram: https://gitdiagram.com/jairzinhosantos/metaprompting-for-academic-deep-research
- Repository: https://github.com/jairzinhosantos/metaprompting-for-academic-deep-research

## Overview

This repository packages a two-phase academic research workflow: a thinking model turns course context and constraints into an optimized research prompt, then a deep-research model uses it to discover and validate papers, formulate problems, and produce structured JSON. The README documents this workflow and its quality criteria; the repository tree provides the prompt files and example result, but no executable orchestration. Relationships shown are limited to those explicitly described in the README.

Main entry points: [`prompts/prompt_for_deep_research.prompt`](https://github.com/jairzinhosantos/metaprompting-for-academic-deep-research/blob/main/prompts/prompt_for_deep_research.prompt) (Research Prompt), [`results/output.json`](https://github.com/jairzinhosantos/metaprompting-for-academic-deep-research/blob/main/results/output.json) (Research Results), [`prompts/prompt_for_thinking_model.prompt`](https://github.com/jairzinhosantos/metaprompting-for-academic-deep-research/blob/main/prompts/prompt_for_thinking_model.prompt) (Thinking Prompt)

## Diagram (Mermaid)

```mermaid
flowchart TD

subgraph group_metaprompting["Prompt Optimization"]
  node_thinking["Thinking Model"]
end

subgraph group_research["Research Execution"]
  node_deep_research["Deep Research Model"]
  node_academic_databases[("Academic Databases")]
  node_quality_validation["Paper Validation"]
  node_problem_formulation["Problem Formulation"]
end

subgraph group_artifacts["Workflow Artifacts"]
  node_thinking_prompt["Thinking Prompt"]
  node_deep_prompt["Research Prompt"]
  node_structured_output["Research Results<br/>[output.json]"]
end

node_user(("Researcher"))

node_user -->|"submits context"| node_thinking
node_thinking_prompt -->|"guides analysis"| node_thinking
node_thinking -->|"generates prompt"| node_deep_prompt
node_user -->|"submits prompt"| node_deep_research
node_deep_prompt -->|"specifies research"| node_deep_research
node_deep_research -->|"searches papers"| node_academic_databases
node_academic_databases -->|"returns candidates"| node_deep_research
node_deep_research -->|"validates papers"| node_quality_validation
node_deep_research -->|"formulates problems"| node_problem_formulation
node_deep_research -->|"structures results"| node_structured_output
node_structured_output -->|"delivers results"| node_user

click node_thinking_prompt "https://github.com/jairzinhosantos/metaprompting-for-academic-deep-research/blob/main/prompts/prompt_for_thinking_model.prompt"
click node_deep_prompt "https://github.com/jairzinhosantos/metaprompting-for-academic-deep-research/blob/main/prompts/prompt_for_deep_research.prompt"
click node_structured_output "https://github.com/jairzinhosantos/metaprompting-for-academic-deep-research/blob/main/results/output.json"

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_thinking toneBlue
class node_deep_research,node_academic_databases,node_quality_validation,node_problem_formulation toneAmber
class node_thinking_prompt,node_deep_prompt,node_structured_output toneMint
class node_user toneIndigo
```

## Components

### Prompt Optimization

- **Thinking Model**

### Research Execution

- **Deep Research Model**
- **Academic Databases**
- **Paper Validation**
- **Problem Formulation**

### Workflow Artifacts

- [Thinking Prompt](https://github.com/jairzinhosantos/metaprompting-for-academic-deep-research/blob/main/prompts/prompt_for_thinking_model.prompt): `prompts/prompt_for_thinking_model.prompt`
- [Research Prompt](https://github.com/jairzinhosantos/metaprompting-for-academic-deep-research/blob/main/prompts/prompt_for_deep_research.prompt): `prompts/prompt_for_deep_research.prompt`
- [Research Results](https://github.com/jairzinhosantos/metaprompting-for-academic-deep-research/blob/main/results/output.json): `results/output.json`

### Other components

- **Researcher**

## Connections

- Researcher → Thinking Model: submits context
- Thinking Prompt → Thinking Model: guides analysis
- Thinking Model → Research Prompt: generates prompt
- Researcher → Deep Research Model: submits prompt
- Research Prompt → Deep Research Model: specifies research
- Deep Research Model → Academic Databases: searches papers
- Academic Databases → Deep Research Model: returns candidates
- Deep Research Model → Paper Validation: validates papers
- Deep Research Model → Problem Formulation: formulates problems
- Deep Research Model → Research Results: structures results
- Research Results → Researcher: delivers results