UpstageAI/Solar-Pro4-Cookbook

UpstageAI/Solar-Pro4-Cookbook

Language: Python

License: MIT

Stars: 0

Forks: 0

Open issues: 0

Created: 2026-07-31T07:39:20Z

Pushed: 2026-08-05T22:02:15Z

Default branch: main

Fork: no

Archived: no

README:

Solar Agent Cookbook

Production-tested system prompts for building agents on Solar. Each agent in this repository is a single agent.md file you can copy into any OpenAI-compatible client, together with real outputs it produced, so you can see exactly what you will get before writing a line of code.

Every published artifact here (spreadsheets, reports, slide decks, games, simulations, dashboards) was generated by `solar-pro4` through the included runner (one simulation, weather-island, is retained from solar-open2 after repeated pro4 attempts failed its browser gate; each output's run-meta.json records the exact model), with pass criteria in a checklist. Nothing is hand-edited. When a generation falls short, we regenerate and promote the best run.

About the model. Solar Pro 4 is Upstage's flagship model, specialized for agentic use. It is particularly strong at document-based work, coding, and business-related tasks, supports a 512K context length with full English, Korean, and Japanese coverage, and offers a reasoning mode. Exactly the profile this cookbook exercises: office documents, games and dashboards, and tool-calling agent loops.

Getting started

You need a Solar API key (create one at console.upstage.ai/api-keys) and Python 3.

pip install requests
export UPSTAGE_API_KEY=your_key

cd solar-agent-cookbook
python3 runner/run.py --agent simulation-builder \
--task simulation-builder/golden/01-aquarium/task.md \
--out /tmp/aquarium-run

This sends the agent's system prompt and the task to solar-pro4, saves the generated file to /tmp/aquarium-run/, and writes a run-meta.json describing the run. Open the resulting aquarium.html in your browser and you should see a living aquarium.

Prefer notebooks? [quickstart.ipynb](solar-agent-cookbook/quickstart.ipynb) walks through the same flow with plain API calls, including the tool-calling loop, with executed outputs you can read before running anything. And any OpenAI-compatible client works: put the contents of agent.md in the system message, your task in the user message, and call model solar-pro4.

Capability guides

Short, single-purpose notebooks in [capabilities/](capabilities/), each isolating one prompting technique with a baseline-versus-improved measurement on real solar-pro4 output. Read them before building the equivalent capability into an agent or skill.

| Guide | What you learn | Technique | |---|---|---| | [parameters](capabilities/parameters/) | Pick the right reasoning_effort, temperature, top_p, max_tokens, stream settings | defaults + ranges + live effect demos | | [classification](capabilities/classification/) | Route Korean inquiries into 6 support labels | label definitions + few-shot + output contract + abstain rule | | [summarization](capabilities/summarization/) | Keep a press-release summary faithful and on-format | format contract + faithfulness rules + extract-then-summarize | | [structured-extraction](capabilities/structured-extraction/) | Turn Korean emails into validated JSON | schema-in-prompt + null rule + validate-and-retry loop | | [translation](capabilities/translation/) | Lock business terminology across a translation | glossary injection + structure/number rules + tone control |

Agents

Every preview below is a real, unedited solar-pro4 output committed in this repository.

| | | | |:---:|:---:|:---:| | [](solar-agent-cookbook/excel-agent/) | [](solar-agent-cookbook/doc-agent/) | [](solar-agent-cookbook/ppt-agent/) | | excel-agent: site-evaluation workbook | doc-agent: feasibility report | ppt-agent: board-approval deck | | [](solar-agent-cookbook/simulation-builder/) | [](solar-agent-cookbook/game-builder/) | [](solar-agent-cookbook/frontend-artifact/) | | simulation-builder: deep-sea aquarium | game-builder: neon breakout roguelite | frontend-artifact: finance dashboard |

| Agent | What it builds | Run mode | |---|---|---| | [excel-agent](solar-agent-cookbook/excel-agent/) | Excel workbooks computed from input data, with formatting and a verification pass | loop | | [doc-agent](solar-agent-cookbook/doc-agent/) | Word reports whose numbers are pulled from upstream data, never re-derived | loop | | [ppt-agent](solar-agent-cookbook/ppt-agent/) | PowerPoint decks with charts and speaker notes on every slide | loop | | [game-builder](solar-agent-cookbook/game-builder/) | Complete, playable browser games in one HTML file | oneshot | | [simulation-builder](solar-agent-cookbook/simulation-builder/) | Self-running animated simulations (physics, nature scenes) in one HTML file | oneshot | | [frontend-artifact](solar-agent-cookbook/frontend-artifact/) | Practical single-file web UIs such as dashboards and internal tools | oneshot | | [research-agent](solar-agent-cookbook/research-agent/) | Research briefs where every claim carries a citation, like the committed [model brief](solar-agent-cookbook/research-agent/golden/01-model-brief/outputs/brief.md) | loop |

The three office agents are designed to chain. The workbook's checkpoint files feed the report, and both feed the deck, so numbers stay consistent across all three documents by contract rather than by luck.

Skills

Skills live in [solar-skills/](solar-skills/): reusable capabilities any agent can load, each shipped with a golden run as proof.

| Skill | What it does | Golden proof | |---|---|---| | [document-qa](solar-skills/document-qa/) | Reads documents through [Upstage Document...