fix: reword

README.md

@@ -15,7 +15,7 @@ pinned: false
 
 </div>
 
-> Planning AI is a tool designed to process and analyse responses to local government planning applications. It uses advanced natural language processing techniques to summarise and categorise feedback, providing insights into public opinion on proposed developments.
+> Planning AI is a tool designed to process and analyse responses to local government policy documents. It uses advanced natural language processing techniques to summarise and categorise feedback, providing insights into public opinion on proposed developments.
 
 ```mermaid
 %%{init: {'flowchart': {'curve': 'linear'}}}%%

planning_ai/chains/prompts/fix_hallucination.txt

@@ -1,4 +1,4 @@
-You are tasked with summarising a response to a planning application proposed by South Cambridgeshire Council. Below, we have provided an **incorrect summary** of the response, along with an **explanation** detailing why the summary is incorrect. Your job is to generate a **correct** summary based solely on the original response provided, avoiding the errors highlighted in the explanation.
+You are tasked with summarising a response to a policy document proposed by South Cambridgeshire Council. Below, we have provided an **incorrect summary** of the response, along with an **explanation** detailing why the summary is incorrect. Your job is to generate a **correct** summary based solely on the original response provided, avoiding the errors highlighted in the explanation.
 
 - **Incorrect Summary**:
   {summary}

planning_ai/documents/introduction.txt

@@ -1 +1 @@
-This report was produced using a generative pre-trained transformer (GPT) large-language model (LLM) to produce a summary of all responses to the related planning application. This model automatically reviews every response in detail, and extracts key information to inform decision making. This document first consolidates this information into a single-page executive summary, highlighting areas of particular interest to consider, and the broad consensus of responses. Figures generated from responses then give both a geographic and statistical overview, highlighting any demographic imbalances in responses. The document then extracts detailed information from responses, grouped by theme and policy. In this section we incorporate citations which relate with the 'Summary Responses' document, to increase transparency.
+This report was produced using a generative pre-trained transformer (GPT) large-language model (LLM) to produce a summary of all responses to the related policy document. This model automatically reviews every response in detail, and extracts key information to inform decision making. This document first consolidates this information into a single-page executive summary, highlighting areas of particular interest to consider, and the broad consensus of responses. Figures generated from responses then give both a geographic and statistical overview, highlighting any demographic imbalances in responses. The document then extracts detailed information from responses, grouped by theme and policy. In this section we incorporate citations which relate with the 'Summary Responses' document, to increase transparency.