atomic_elements_prompt.txt

<start>
>>> OBJECTIVE <<<
This prompt aims to construct an exhaustive list of atomic actions that will get the user to their desired outcome (provided by the user).
---
>>> INPUT <<<
Before beginning the generation phases, we define the ideal completed summary of the user's desired outcome (~300 words)  
This acts as the [goal state] for our analysis and is provided below:  
[Here, insert the complete, polished narrative summary from the user on what their desired outcome is from the model - formatted like an abstract/short introduction to a scientific paper]
Label this section: [BEGIN - TARGET NARRATIVE SUMMARY] ... [END TARGET NARRATIVE SUMMARY]
---
>>> GENERATION PHASES <<<
This component of the prompt will perform two prompting strategies sequentially: Graph of Thought (GOT) and Recursive Chain-of-Thought (rCoT). Both aim to generate the narrative structure step-by-step, but from different angles.
-
## Graph of Thought (GOT) - Backward Reasoning
Prompt:'''
Using a Graph of Thought (GOT) approach, starting with the provided *[TARGET NARRATIVE SUMMARY]*, work backward to decompose it into essential subgoals required to achieve this outcome. Construct a graph where: 
- Nodes represent these subgoals (key narrative elements).
- Edges show dependencies between them, illustrating the logical order needed to build the complete story.
Focus on revealing the [means] to reach the final narrative structure.
'''
-
## Chain-of-Thought (rCoT) - Recursive Forward Reasoning
Prompt:'''
Employ a rCoT method, starting with the first [means] generated in the graph from the GOT approach.
1. Level 0 (Root Prompt): Set the stage using focusing on the overall narrative goal as a high-level subproblem.
2. Recursive Breakdown: At each subsequent level, generate a new CoT prompt that addresses a sub-problem derived directly from the previous level's output. This recursive process continues until you reach steps representing single, atomic actions.
Each rCoT prompt should result in an output readily integrable into a sentence or paragraph of the final narrative.
3. Stopping Condition: The recursion stops when prompts deal with granular tasks that are essentially single logical steps.
'''
---
>>> EXAMPLE <<<
## Problem Statement (P) and Hierarchical Structure (H)
## Problem Statement (P): A compelling scientific narrative detailing the discovery, characterization, validation, impact, and future directions of a novel enzyme capable of efficiently breaking down plastic waste into biodegradable compounds.
## Hierarchical Structure (H):
- Level 1: Foundation & Eureka Moment (Introduce the problem, research context, and discovery)
         - a) Global plastic pollution crisis and need for solutions
         - b) Enzyme isolation and initial hypothesis validation
- Level 2: Characterization & Validation (Properties, experiments)
         - a) In-depth enzyme analysis (efficiency, substrate specificity, stability)
         - b) Experimental validation of degradation capabilities on various plastics.
-(Subsequent Levels 3 onward): Further breakdown as per the rCoT process described above.
---
>>> INSTRUCTIONS <<<
1. Perform GOT (backward insight) to obtain graph structure [nodes, edges] and the [means] by which this brings the problem-solving process closer to the goal.
2. Use rCOT (recursive structure) on the [means] that serve to link the plan described in graph structure [nodes,edges].
3. Producing an exhaustive list of tasks, sub-tasks, sub-tasks of sub-tasks, etc in (H) that detail how (P) can be achieved. These are the [STEPS].
---
>>> FINAL OUTPUT <<<
A step-by-step plan to get from problem to solution in bullet-point format.
Each step is specific and precise - representing an atomic thought or action. It cannot be decomposed further. 
---
>>> FORMATTING <<<
## CHAT FORMAT
ASSISTANT: What would you like step-by-step instructions for?
USER: The end-state of my desired outcome is …
---
'''
User Input: {{input}}
Input:      [GOAL STATE]
Plan:       [STEPS]
'''
---
<end>