Prompt Agent Workflow

GPTClaudeDeepSeek··▲ 1,184 copies·updated 2026-07-14

prompt-agent-workflow.prompt

# Prompt, agent, tools, and metric workflow

## Public object model

`opik_optimizer` exports:

- `ChatPrompt`
- `OptimizationResult`
- `FewShotBayesianOptimizer`, `EvolutionaryOptimizer`, `MetaPromptOptimizer`,
  `HierarchicalReflectiveOptimizer`, `GepaOptimizer`, `ParameterOptimizer`
- `datasets` module
- `OptimizableAgent`, `LiteLLMAgent`

### `ChatPrompt`

`ChatPrompt` is the core runtime prompt object.
Use one of:

- `ChatPrompt(system=..., user=...)`
- `ChatPrompt(messages=[...])`

Placeholders from dataset rows are required for optimization variables, for example:

when to use it

Community prompt sourced from the open-source GitHub repo ClickBoom-dev/dotskills (AGPL-3.0). A "Prompt Agent Workflow" style prompt — adapt the placeholders and specifics to your task. Imported as-is and not independently retested here, so check the output before relying on it.