diff --git a/Procfile b/Procfile
index 94d4e4ba..3a610dbd 100644
--- a/Procfile
+++ b/Procfile
@@ -1 +1 @@
-web: sh setup.sh && streamlit run evo_prophet/app.py
\ No newline at end of file
+web: sh setup.sh && streamlit run prediction_prophet/app.py
\ No newline at end of file
diff --git a/README.md b/README.md
index 7429b99a..a59c3973 100644
--- a/README.md
+++ b/README.md
@@ -1,4 +1,4 @@
-# evo.prophet
+# Prediction Prophet
 ![](./content/banner_hires.png)
 
 ---
@@ -9,7 +9,7 @@
 
 ## Welcome!
 
-evo.prophet is an agent that specializes in making informed predictions, based on web research. To try it yourself head to [predictionprophet.ai](https://predictionprophet.ai) or build and run from source following these [setup instructions](#setup).
+Prediction Prophet is an agent that specializes in making informed predictions, based on web research. To try it yourself head to [predictionprophet.ai](https://predictionprophet.ai) or build and run from source following these [setup instructions](#setup).
 
 ## Need Help?
 
@@ -17,13 +17,13 @@ Join our [Discord community](https://discord.gg/k7UCsH3ps9) for support and disc
 
 [![Join us on Discord](https://invidget.switchblade.xyz/k7UCsH3ps9)](https://discord.com/invite/k7UCsH3ps9)
 
-If you have questions or encounter issues, please don't hesitate to [create a new issue](https://github.com/polywrap/evo.prophet/issues/new) to get support.
+If you have questions or encounter issues, please don't hesitate to [create a new issue](https://github.com/polywrap/predictionprophet/issues/new) to get support.
 
 
 ## How It Works
 ![](./content/diagram.png)
 
-To elaborate further, given a question like `"Will Twitter implement a new misinformation policy before the 2024 elections?"`, evo.prophet will:  
+To elaborate further, given a question like `"Will Twitter implement a new misinformation policy before the 2024 elections?"`, Prophet will:  
 
 1. Generate `n` web search queries and re-ranks them using an LLM call, selecting only the most relevant ones
 2. Search the web for each query, using [Tavily](https://tavily.com/)
@@ -31,14 +31,14 @@ To elaborate further, given a question like `"Will Twitter implement a new misin
 4. Use Langchain's `RecursiveCharacterTextSplitter` to split the content of all pages into chunks and create embeddings. All chunks are stored with the content as metadata.
 5. Iterate over the queries selected on step `1` and vector search for the most relevant chunks created in step `4`.
 6. Aggregate all relevant chunks and prepare a report.
-7. Make a prediction using multi-agent debate.
+7. Make a prediction.
 
 ## Setup
 
 ### Installation
 
 1. Clone the repository 
-    > `git clone https://github.com/polywrap/evo.prophet`
+    > `git clone https://github.com/polywrap/predictionprophet`
 2. Copy the `.env.template` file and rename it to `.env`.  
     > `cp .env.template .env`
 3. Find the line that says OPENAI_API_KEY=, and add your unique [OpenAI](https://openai.com/) API Key  
@@ -67,7 +67,7 @@ poetry run research "Will Twitter implement a new misinformation policy before t
 ### Front-End
 
 ```bash
-poetry run streamlit run ./evo_prophet/app.py
+poetry run streamlit run ./prediction_prophet/app.py
 ```
 
 ## Possible Future Improvements
diff --git a/mypy.ini b/mypy.ini
index d43012d1..ab0c8c47 100644
--- a/mypy.ini
+++ b/mypy.ini
@@ -1,6 +1,6 @@
 [mypy]
 python_version = 3.10
-files = evo_prophet/, scripts/, tests/
+files = prediction_prophet/, scripts/, tests/
 plugins = pydantic.mypy
 warn_redundant_casts = True
 warn_unused_ignores = True
diff --git a/evo_prophet/__init__.py b/prediction_prophet/__init__.py
similarity index 100%
rename from evo_prophet/__init__.py
rename to prediction_prophet/__init__.py
diff --git a/evo_prophet/app.py b/prediction_prophet/app.py
similarity index 89%
rename from evo_prophet/app.py
rename to prediction_prophet/app.py
index 793e6842..738d9986 100644
--- a/evo_prophet/app.py
+++ b/prediction_prophet/app.py
@@ -1,7 +1,7 @@
 import time
 from typing import cast
-from evo_prophet.benchmark.agents import _make_prediction
-from evo_prophet.functions.is_predictable_and_binary import is_predictable_and_binary
+from prediction_prophet.benchmark.agents import _make_prediction
+from prediction_prophet.functions.is_predictable_and_binary import is_predictable_and_binary
 from prediction_market_agent_tooling.benchmark.utils import (
     OutcomePrediction
 )
@@ -9,12 +9,12 @@
 import streamlit as st
 from prediction_market_agent_tooling.tools.utils import secret_str_from_env
 from langchain.text_splitter import RecursiveCharacterTextSplitter
-from evo_prophet.functions.create_embeddings_from_results import create_embeddings_from_results
-from evo_prophet.functions.generate_subqueries import generate_subqueries
-from evo_prophet.functions.prepare_report import prepare_report
-from evo_prophet.functions.rerank_subqueries import rerank_subqueries
-from evo_prophet.functions.scrape_results import scrape_results
-from evo_prophet.functions.search import search
+from prediction_prophet.functions.create_embeddings_from_results import create_embeddings_from_results
+from prediction_prophet.functions.generate_subqueries import generate_subqueries
+from prediction_prophet.functions.prepare_report import prepare_report
+from prediction_prophet.functions.rerank_subqueries import rerank_subqueries
+from prediction_prophet.functions.scrape_results import scrape_results
+from prediction_prophet.functions.search import search
 
 def research(
     goal: str,
@@ -98,13 +98,13 @@ def research(
     st.stop()
 
 st.set_page_config(layout="wide")
-st.title("Evo Prophet")
+st.title("Prediction Prophet")
 st.write('Ask any yes-or-no question about a future outcome')
 
 with st.sidebar:
-    st.title('Evo Prophet')
+    st.title('Prediction Prophet')
     st.markdown("A web3 agent by [Polywrap](https://www.polywrap.io/)")
-    st.image('https://raw.githubusercontent.com/polywrap/evo.prophet/main/content/banner_hires.png')
+    st.image('https://raw.githubusercontent.com/polywrap/predictionprophet/main/content/banner_hires.png')
     
     st.markdown('#')
     openai_api_key = SecretStr(st.text_input("OpenAI API Key", type="password", key="open_ai_key"))
@@ -115,7 +115,7 @@ def research(
     st.markdown('#')
     st.markdown('#')
     st.markdown('-------')
-    st.caption('View the source code on our [github](https://github.com/polywrap/evo.prophet)')
+    st.caption('View the source code on our [github](https://github.com/polywrap/predictionprophet)')
     st.caption('Join our [discord](https://discord.gg/3ebYCjXbg7)')
     
 
diff --git a/evo_prophet/autonolas/__init__.py b/prediction_prophet/autonolas/__init__.py
similarity index 100%
rename from evo_prophet/autonolas/__init__.py
rename to prediction_prophet/autonolas/__init__.py
diff --git a/evo_prophet/autonolas/research.py b/prediction_prophet/autonolas/research.py
similarity index 99%
rename from evo_prophet/autonolas/research.py
rename to prediction_prophet/autonolas/research.py
index 27c8c9e6..53d4794e 100644
--- a/evo_prophet/autonolas/research.py
+++ b/prediction_prophet/autonolas/research.py
@@ -15,7 +15,7 @@
 from enum import Enum
 from bs4 import BeautifulSoup, NavigableString
 from googleapiclient.discovery import build
-from evo_prophet.functions.parallelism import THREADPOOL
+from prediction_prophet.functions.parallelism import THREADPOOL
 
 import requests
 from requests import Session
@@ -29,10 +29,10 @@
 from langchain_openai import OpenAIEmbeddings
 
 from dateutil import parser
-from evo_prophet.functions.utils import check_not_none
+from prediction_prophet.functions.utils import check_not_none
 from prediction_market_agent_tooling.tools.utils import secret_str_from_env
-from evo_prophet.functions.cache import persistent_inmemory_cache
-from evo_prophet.functions.parallelism import par_map
+from prediction_prophet.functions.cache import persistent_inmemory_cache
+from prediction_prophet.functions.parallelism import par_map
 from pydantic.types import SecretStr
 from prediction_market_agent_tooling.gtypes import secretstr_to_v1_secretstr
 
diff --git a/evo_prophet/benchmark/__init__.py b/prediction_prophet/benchmark/__init__.py
similarity index 100%
rename from evo_prophet/benchmark/__init__.py
rename to prediction_prophet/benchmark/__init__.py
diff --git a/evo_prophet/benchmark/agents.py b/prediction_prophet/benchmark/agents.py
similarity index 86%
rename from evo_prophet/benchmark/agents.py
rename to prediction_prophet/benchmark/agents.py
index b2bfbedc..6b49afaa 100644
--- a/evo_prophet/benchmark/agents.py
+++ b/prediction_prophet/benchmark/agents.py
@@ -7,23 +7,23 @@
     Prediction,
 )
 from datetime import datetime
-from evo_prophet.autonolas.research import EmbeddingModel
-from evo_prophet.autonolas.research import make_prediction, get_urls_from_queries
-from evo_prophet.autonolas.research import research as research_autonolas
-from evo_prophet.functions.evaluate_question import is_predictable
-from evo_prophet.functions.rephrase_question import rephrase_question
-from evo_prophet.functions.research import research as research_evo
-from evo_prophet.functions.search import search
-from evo_prophet.functions.utils import url_is_older_than
-from evo_prophet.models.WebSearchResult import WebSearchResult
+from prediction_prophet.autonolas.research import EmbeddingModel
+from prediction_prophet.autonolas.research import make_prediction, get_urls_from_queries
+from prediction_prophet.autonolas.research import research as research_autonolas
+from prediction_prophet.functions.evaluate_question import is_predictable
+from prediction_prophet.functions.rephrase_question import rephrase_question
+from prediction_prophet.functions.research import research as prophet_research
+from prediction_prophet.functions.search import search
+from prediction_prophet.functions.utils import url_is_older_than
+from prediction_prophet.models.WebSearchResult import WebSearchResult
 from unittest.mock import patch
-from evo_prophet.functions.search import search
+from prediction_prophet.functions.search import search
 from prediction_market_agent_tooling.benchmark.utils import (
     OutcomePrediction,
     Prediction,
 )
 from pydantic.types import SecretStr
-from evo_prophet.autonolas.research import Prediction as LLMCompletionPredictionDict
+from prediction_prophet.autonolas.research import Prediction as LLMCompletionPredictionDict
 
 def _make_prediction(
     market_question: str,
@@ -144,16 +144,16 @@ def side_effect(*args: t.Any, **kwargs: t.Any) -> list[str]:
             ]
             return results_filtered
     
-        with patch('evo_prophet.autonolas.research.get_urls_from_queries', side_effect=side_effect, autospec=True):
+        with patch('prediction_prophet.autonolas.research.get_urls_from_queries', side_effect=side_effect, autospec=True):
             return self.predict(market_question)
 
 
-class EvoAgent(AbstractBenchmarkedAgent):
+class PredictionProphetAgent(AbstractBenchmarkedAgent):
     def __init__(
         self,
         model: str,
         temperature: float = 0.0,
-        agent_name: str = "evo",
+        agent_name: str = "prediction_prophet",
         use_summaries: bool = False,
         use_tavily_raw_content: bool = False,
         max_workers: t.Optional[int] = None,
@@ -173,7 +173,7 @@ def is_predictable_restricted(self, market_question: str, time_restriction_up_to
         return result
     
     def research(self, market_question: str) -> str:
-        return research_evo(
+        return prophet_research(
             goal=market_question,
             model=self.model,
             use_summaries=self.use_summaries,
@@ -190,7 +190,7 @@ def predict(self, market_question: str) -> Prediction:
                 temperature=self.temperature,
             )
         except ValueError as e:
-            print(f"Error in EvoAgent's predict: {e}")
+            print(f"Error in PredictionProphet's predict: {e}")
             return Prediction()
 
     def predict_restricted(
@@ -204,7 +204,7 @@ def side_effect(*args: t.Any, **kwargs: t.Any) -> list[tuple[str, WebSearchResul
             ]
             return results_filtered
     
-        with patch('evo_prophet.functions.research.search', side_effect=side_effect, autospec=True):
+        with patch('prediction_prophet.functions.research.search', side_effect=side_effect, autospec=True):
             return self.predict(market_question)
 
 class RephrasingOlasAgent(OlasAgent):
@@ -249,6 +249,6 @@ def research(self, market_question: str) -> str:
 AGENTS = [
     OlasAgent,
     RephrasingOlasAgent,
-    EvoAgent,
+    PredictionProphetAgent,
     QuestionOnlyAgent,
 ]
diff --git a/evo_prophet/deployment/models.py b/prediction_prophet/deployment/models.py
similarity index 94%
rename from evo_prophet/deployment/models.py
rename to prediction_prophet/deployment/models.py
index dba650bd..dda0989c 100644
--- a/evo_prophet/deployment/models.py
+++ b/prediction_prophet/deployment/models.py
@@ -1,7 +1,7 @@
 import pytz
 from decimal import Decimal
 from datetime import datetime, timedelta
-from evo_prophet.benchmark.agents import EvoAgent, OlasAgent, EmbeddingModel
+from prediction_prophet.benchmark.agents import PredictionProphetAgent, OlasAgent, EmbeddingModel
 from prediction_market_agent_tooling.benchmark.agents import AbstractBenchmarkedAgent
 from prediction_market_agent_tooling.markets.agent_market import AgentMarket
 from prediction_market_agent_tooling.markets.manifold.manifold import ManifoldAgentMarket
@@ -75,8 +75,8 @@ def answer_binary_market(self, market: AgentMarket) -> bool:
         return binary_answer
     
 
-class DeployableAgentER_EvoGPT3(DeployableAgentER):
-    agent = EvoAgent(model="gpt-3.5-turbo-0125")
+class DeployableAgentER_PredictionProphetGPT3(DeployableAgentER):
+    agent = PredictionProphetAgent(model="gpt-3.5-turbo-0125")
 
 
 class DeployableAgentER_OlasEmbeddingOA(DeployableAgentER):
diff --git a/evo_prophet/functions/__init__.py b/prediction_prophet/functions/__init__.py
similarity index 100%
rename from evo_prophet/functions/__init__.py
rename to prediction_prophet/functions/__init__.py
diff --git a/evo_prophet/functions/cache.py b/prediction_prophet/functions/cache.py
similarity index 100%
rename from evo_prophet/functions/cache.py
rename to prediction_prophet/functions/cache.py
diff --git a/evo_prophet/functions/create_embeddings_from_results.py b/prediction_prophet/functions/create_embeddings_from_results.py
similarity index 94%
rename from evo_prophet/functions/create_embeddings_from_results.py
rename to prediction_prophet/functions/create_embeddings_from_results.py
index 75d6728b..94a99b33 100644
--- a/evo_prophet/functions/create_embeddings_from_results.py
+++ b/prediction_prophet/functions/create_embeddings_from_results.py
@@ -9,7 +9,7 @@
 import os
 from langchain_openai import OpenAIEmbeddings
 from langchain.vectorstores.chroma import Chroma
-from evo_prophet.models.WebScrapeResult import WebScrapeResult
+from prediction_prophet.models.WebScrapeResult import WebScrapeResult
 from langchain.text_splitter import RecursiveCharacterTextSplitter
 from pydantic.types import SecretStr
 from prediction_market_agent_tooling.tools.utils import secret_str_from_env
diff --git a/evo_prophet/functions/debate_prediction.py b/prediction_prophet/functions/debate_prediction.py
similarity index 98%
rename from evo_prophet/functions/debate_prediction.py
rename to prediction_prophet/functions/debate_prediction.py
index a42cfc95..f2d63eba 100644
--- a/evo_prophet/functions/debate_prediction.py
+++ b/prediction_prophet/functions/debate_prediction.py
@@ -4,7 +4,7 @@
 from prediction_market_agent_tooling.benchmark.utils import (
     Prediction,
 )
-from evo_prophet.benchmark.agents import completion_prediction_json_to_pydantic_model
+from prediction_prophet.benchmark.agents import completion_prediction_json_to_pydantic_model
 from pydantic import SecretStr
 from langchain.schema.output_parser import StrOutputParser
 from langchain_openai import ChatOpenAI
diff --git a/evo_prophet/functions/evaluate_question.py b/prediction_prophet/functions/evaluate_question.py
similarity index 93%
rename from evo_prophet/functions/evaluate_question.py
rename to prediction_prophet/functions/evaluate_question.py
index 529eeacd..61c2615c 100644
--- a/evo_prophet/functions/evaluate_question.py
+++ b/prediction_prophet/functions/evaluate_question.py
@@ -1,8 +1,8 @@
 import json
-from evo_prophet.autonolas.research import clean_completion_json
+from prediction_prophet.autonolas.research import clean_completion_json
 from langchain_openai import ChatOpenAI
 from langchain.prompts import ChatPromptTemplate
-from evo_prophet.functions.cache import persistent_inmemory_cache
+from prediction_prophet.functions.cache import persistent_inmemory_cache
 from pydantic.types import SecretStr
 from prediction_market_agent_tooling.tools.utils import secret_str_from_env
 from prediction_market_agent_tooling.gtypes import secretstr_to_v1_secretstr
diff --git a/evo_prophet/functions/generate_subqueries.py b/prediction_prophet/functions/generate_subqueries.py
similarity index 100%
rename from evo_prophet/functions/generate_subqueries.py
rename to prediction_prophet/functions/generate_subqueries.py
diff --git a/evo_prophet/functions/is_predictable_and_binary.py b/prediction_prophet/functions/is_predictable_and_binary.py
similarity index 93%
rename from evo_prophet/functions/is_predictable_and_binary.py
rename to prediction_prophet/functions/is_predictable_and_binary.py
index 748a608f..f7f0f734 100644
--- a/evo_prophet/functions/is_predictable_and_binary.py
+++ b/prediction_prophet/functions/is_predictable_and_binary.py
@@ -1,8 +1,8 @@
 import json
-from evo_prophet.autonolas.research import clean_completion_json
+from prediction_prophet.autonolas.research import clean_completion_json
 from langchain_openai import ChatOpenAI
 from langchain.prompts import ChatPromptTemplate
-from evo_prophet.functions.cache import persistent_inmemory_cache
+from prediction_prophet.functions.cache import persistent_inmemory_cache
 from pydantic.types import SecretStr
 from prediction_market_agent_tooling.tools.utils import secret_str_from_env
 from prediction_market_agent_tooling.gtypes import secretstr_to_v1_secretstr
diff --git a/evo_prophet/functions/parallelism.py b/prediction_prophet/functions/parallelism.py
similarity index 100%
rename from evo_prophet/functions/parallelism.py
rename to prediction_prophet/functions/parallelism.py
diff --git a/evo_prophet/functions/prepare_report.py b/prediction_prophet/functions/prepare_report.py
similarity index 95%
rename from evo_prophet/functions/prepare_report.py
rename to prediction_prophet/functions/prepare_report.py
index d5adc8f6..281378c4 100644
--- a/evo_prophet/functions/prepare_report.py
+++ b/prediction_prophet/functions/prepare_report.py
@@ -4,8 +4,8 @@
 from langchain_openai import ChatOpenAI
 from langchain.prompts import ChatPromptTemplate
 from langchain.schema.output_parser import StrOutputParser
-from evo_prophet.functions.cache import persistent_inmemory_cache
-from evo_prophet.functions.utils import trim_to_n_tokens
+from prediction_prophet.functions.cache import persistent_inmemory_cache
+from prediction_prophet.functions.utils import trim_to_n_tokens
 from prediction_market_agent_tooling.tools.utils import secret_str_from_env
 from prediction_market_agent_tooling.gtypes import secretstr_to_v1_secretstr
 from pydantic.types import SecretStr
diff --git a/evo_prophet/functions/rephrase_question.py b/prediction_prophet/functions/rephrase_question.py
similarity index 95%
rename from evo_prophet/functions/rephrase_question.py
rename to prediction_prophet/functions/rephrase_question.py
index fc040ca7..4d31121c 100644
--- a/evo_prophet/functions/rephrase_question.py
+++ b/prediction_prophet/functions/rephrase_question.py
@@ -2,7 +2,7 @@
 import tiktoken
 from pydantic import BaseModel
 from langchain_openai import ChatOpenAI
-from evo_prophet.autonolas.research import clean_completion_json
+from prediction_prophet.autonolas.research import clean_completion_json
 from langchain.prompts import ChatPromptTemplate
 
 
diff --git a/evo_prophet/functions/rerank_results.py b/prediction_prophet/functions/rerank_results.py
similarity index 100%
rename from evo_prophet/functions/rerank_results.py
rename to prediction_prophet/functions/rerank_results.py
diff --git a/evo_prophet/functions/rerank_subqueries.py b/prediction_prophet/functions/rerank_subqueries.py
similarity index 100%
rename from evo_prophet/functions/rerank_subqueries.py
rename to prediction_prophet/functions/rerank_subqueries.py
diff --git a/evo_prophet/functions/research.py b/prediction_prophet/functions/research.py
similarity index 88%
rename from evo_prophet/functions/research.py
rename to prediction_prophet/functions/research.py
index 1971ae4c..4ab5f003 100644
--- a/evo_prophet/functions/research.py
+++ b/prediction_prophet/functions/research.py
@@ -1,13 +1,13 @@
 import logging
 
 from langchain.text_splitter import RecursiveCharacterTextSplitter
-from evo_prophet.functions.create_embeddings_from_results import create_embeddings_from_results
-from evo_prophet.functions.generate_subqueries import generate_subqueries
-from evo_prophet.functions.prepare_report import prepare_report, prepare_summary
-from evo_prophet.models.WebScrapeResult import WebScrapeResult
-from evo_prophet.functions.rerank_subqueries import rerank_subqueries
-from evo_prophet.functions.scrape_results import scrape_results
-from evo_prophet.functions.search import search
+from prediction_prophet.functions.create_embeddings_from_results import create_embeddings_from_results
+from prediction_prophet.functions.generate_subqueries import generate_subqueries
+from prediction_prophet.functions.prepare_report import prepare_report, prepare_summary
+from prediction_prophet.models.WebScrapeResult import WebScrapeResult
+from prediction_prophet.functions.rerank_subqueries import rerank_subqueries
+from prediction_prophet.functions.scrape_results import scrape_results
+from prediction_prophet.functions.search import search
 from pydantic.types import SecretStr
 
 def research(
diff --git a/evo_prophet/functions/scrape_results.py b/prediction_prophet/functions/scrape_results.py
similarity index 54%
rename from evo_prophet/functions/scrape_results.py
rename to prediction_prophet/functions/scrape_results.py
index 624eb727..b94b95dd 100644
--- a/evo_prophet/functions/scrape_results.py
+++ b/prediction_prophet/functions/scrape_results.py
@@ -1,7 +1,7 @@
-from evo_prophet.models.WebScrapeResult import WebScrapeResult
-from evo_prophet.functions.web_search import WebSearchResult
-from evo_prophet.functions.web_scrape import web_scrape
-from evo_prophet.functions.parallelism import par_map
+from prediction_prophet.models.WebScrapeResult import WebScrapeResult
+from prediction_prophet.functions.web_search import WebSearchResult
+from prediction_prophet.functions.web_scrape import web_scrape
+from prediction_prophet.functions.parallelism import par_map
 
 
 def scrape_results(results: list[WebSearchResult]) -> list[WebScrapeResult]:
diff --git a/evo_prophet/functions/search.py b/prediction_prophet/functions/search.py
similarity index 95%
rename from evo_prophet/functions/search.py
rename to prediction_prophet/functions/search.py
index 251114f9..de4a9b93 100644
--- a/evo_prophet/functions/search.py
+++ b/prediction_prophet/functions/search.py
@@ -1,6 +1,6 @@
 import requests
 import typing as t
-from evo_prophet.functions.web_search import WebSearchResult, web_search
+from prediction_prophet.functions.web_search import WebSearchResult, web_search
 from concurrent.futures import ThreadPoolExecutor, as_completed
 from pydantic.types import SecretStr
 
diff --git a/evo_prophet/functions/summarize.py b/prediction_prophet/functions/summarize.py
similarity index 100%
rename from evo_prophet/functions/summarize.py
rename to prediction_prophet/functions/summarize.py
diff --git a/evo_prophet/functions/utils.py b/prediction_prophet/functions/utils.py
similarity index 97%
rename from evo_prophet/functions/utils.py
rename to prediction_prophet/functions/utils.py
index 133909af..81243bff 100644
--- a/evo_prophet/functions/utils.py
+++ b/prediction_prophet/functions/utils.py
@@ -3,7 +3,7 @@
 from datetime import datetime
 from typing import NoReturn, Type, TypeVar, Optional
 from googleapiclient.discovery import build
-from evo_prophet.functions.cache import persistent_inmemory_cache
+from prediction_prophet.functions.cache import persistent_inmemory_cache
 
 T = TypeVar("T")
 
diff --git a/evo_prophet/functions/web_scrape.py b/prediction_prophet/functions/web_scrape.py
similarity index 95%
rename from evo_prophet/functions/web_scrape.py
rename to prediction_prophet/functions/web_scrape.py
index 355541ce..005d41b8 100644
--- a/evo_prophet/functions/web_scrape.py
+++ b/prediction_prophet/functions/web_scrape.py
@@ -4,7 +4,7 @@
 from bs4 import BeautifulSoup
 from requests import Response
 import tenacity
-from evo_prophet.functions.cache import persistent_inmemory_cache
+from prediction_prophet.functions.cache import persistent_inmemory_cache
 
 
 @tenacity.retry(stop=tenacity.stop_after_attempt(3), wait=tenacity.wait_fixed(1), reraise=True)
diff --git a/evo_prophet/functions/web_search.py b/prediction_prophet/functions/web_search.py
similarity index 88%
rename from evo_prophet/functions/web_search.py
rename to prediction_prophet/functions/web_search.py
index c2f86d20..bb131b91 100644
--- a/evo_prophet/functions/web_search.py
+++ b/prediction_prophet/functions/web_search.py
@@ -4,8 +4,8 @@
 from pydantic.types import SecretStr
 
 from prediction_market_agent_tooling.tools.utils import secret_str_from_env
-from evo_prophet.models.WebSearchResult import WebSearchResult
-from evo_prophet.functions.cache import persistent_inmemory_cache
+from prediction_prophet.models.WebSearchResult import WebSearchResult
+from prediction_prophet.functions.cache import persistent_inmemory_cache
 
 
 @tenacity.retry(stop=tenacity.stop_after_attempt(3), wait=tenacity.wait_fixed(1), reraise=True)
diff --git a/evo_prophet/main.py b/prediction_prophet/main.py
similarity index 85%
rename from evo_prophet/main.py
rename to prediction_prophet/main.py
index e67495b1..29dfdfa9 100644
--- a/evo_prophet/main.py
+++ b/prediction_prophet/main.py
@@ -3,9 +3,9 @@
 import click
 import time
 from dotenv import load_dotenv
-from evo_prophet.functions.debate_prediction import make_debated_prediction
+from prediction_prophet.functions.debate_prediction import make_debated_prediction
 from langchain_community.callbacks import get_openai_callback
-from evo_prophet.functions.research import research as evo_research
+from prediction_prophet.functions.research import research as prophet_research
 from prediction_market_agent_tooling.benchmark.utils import (
     OutcomePrediction
 )
@@ -40,7 +40,7 @@ def research(
     start = time.time()
     
     with get_openai_callback() as cb:
-      report = evo_research(goal=prompt, use_summaries=False, model="gpt-4-0125-preview")
+      report = prophet_research(goal=prompt, use_summaries=False, model="gpt-4-0125-preview")
     
     end = time.time()
     
@@ -66,7 +66,7 @@ def predict(prompt: str, path: str | None = None) -> None:
         else:
             logger = logging.getLogger("research")
             logger.setLevel(logging.INFO)
-            report = evo_research(goal=prompt, model="gpt-4-0125-preview", use_summaries=False, logger=logger)
+            report = prophet_research(goal=prompt, model="gpt-4-0125-preview", use_summaries=False, logger=logger)
         
         prediction = make_debated_prediction(prompt=prompt, additional_information=report)
 
diff --git a/evo_prophet/models/WebScrapeResult.py b/prediction_prophet/models/WebScrapeResult.py
similarity index 100%
rename from evo_prophet/models/WebScrapeResult.py
rename to prediction_prophet/models/WebScrapeResult.py
diff --git a/evo_prophet/models/WebSearchResult.py b/prediction_prophet/models/WebSearchResult.py
similarity index 100%
rename from evo_prophet/models/WebSearchResult.py
rename to prediction_prophet/models/WebSearchResult.py
diff --git a/pyproject.toml b/pyproject.toml
index 0f3194f0..97f13021 100644
--- a/pyproject.toml
+++ b/pyproject.toml
@@ -1,5 +1,5 @@
 [tool.poetry]
-name = "evo_prophet"
+name = "prediction_prophet"
 version = "0.1.10"
 description = ""
 authors = ["Nestor Amesty <nestor@polywrap.io>"]
@@ -42,8 +42,8 @@ pyautogen = "^0.2.19"
 mypy = "^1.8.0"
 
 [tool.poetry.scripts]
-research= "evo_prophet.main:research"
-predict= "evo_prophet.main:predict"
+research= "prediction_prophet.main:research"
+predict= "prediction_prophet.main:predict"
 
 [build-system]
 requires = ["poetry-core"]
diff --git a/scripts/agent_app.py b/scripts/agent_app.py
index 310c4194..bdba6355 100644
--- a/scripts/agent_app.py
+++ b/scripts/agent_app.py
@@ -9,7 +9,7 @@
 from enum import Enum 
 from prediction_market_agent_tooling.benchmark.utils import get_markets, MarketSource
 from prediction_market_agent_tooling.benchmark.agents import AbstractBenchmarkedAgent
-from evo_prophet.benchmark.agents import AGENTS
+from prediction_prophet.benchmark.agents import AGENTS
 
 SENTINTEL = object()
 
diff --git a/scripts/benchmark.py b/scripts/benchmark.py
index 46563aee..d156da45 100644
--- a/scripts/benchmark.py
+++ b/scripts/benchmark.py
@@ -5,9 +5,9 @@
 from prediction_market_agent_tooling.benchmark.benchmark import Benchmarker
 from prediction_market_agent_tooling.benchmark.utils import MarketSource, get_markets, MarketFilter, MarketSort
 
-from evo_prophet.autonolas.research import EmbeddingModel
-from evo_prophet.benchmark.agents import EvoAgent, OlasAgent, QuestionOnlyAgent
-from evo_prophet.functions.cache import ENABLE_CACHE
+from prediction_prophet.autonolas.research import EmbeddingModel
+from prediction_prophet.benchmark.agents import PredictionProphetAgent, OlasAgent, QuestionOnlyAgent
+from prediction_prophet.functions.cache import ENABLE_CACHE
 
 
 def main(
@@ -59,31 +59,31 @@ def main(
                 agent_name="olas_gpt-3.5-turbo-0125_openai-embeddings",
                 embedding_model=EmbeddingModel.openai,
             ),
-            EvoAgent(
+            PredictionProphetAgent(
                 model="gpt-3.5-turbo-0125",
                 max_workers=max_workers,
-                agent_name="evo_gpt-3.5-turbo-0125_summary",
+                agent_name="prediction_prophet_gpt-3.5-turbo-0125_summary",
                 use_summaries=True,
             ),
-            EvoAgent(
+            PredictionProphetAgent(
                 model="gpt-3.5-turbo-0125",
                 max_workers=max_workers,
-                agent_name="evo_gpt-3.5-turbo-0125",
+                agent_name="prediction_prophet_gpt-3.5-turbo-0125",
             ),
-            EvoAgent(
+            PredictionProphetAgent(
                 model="gpt-3.5-turbo-0125",
                 max_workers=max_workers,
-                agent_name="evo_gpt-3.5-turbo-0125_summary_tavilyrawcontent",
+                agent_name="prediction_prophet_gpt-3.5-turbo-0125_summary_tavilyrawcontent",
                 use_summaries=True,
                 use_tavily_raw_content=True,
             ),
-            EvoAgent(
+            PredictionProphetAgent(
                 model="gpt-3.5-turbo-0125",
                 max_workers=max_workers,
-                agent_name="evo_gpt-3.5-turbo-0125_tavilyrawcontent",
+                agent_name="prediction_prophet_gpt-3.5-turbo-0125_tavilyrawcontent",
                 use_tavily_raw_content=True,
             ),
-            # EvoAgent(model="gpt-4-0125-preview", max_workers=max_workers, agent_name="evo_gpt-4-0125-preview"),  # Too expensive to be enabled by default.
+            # PredictionProphetAgent(model="gpt-4-0125-preview", max_workers=max_workers, agent_name="prediction_prophet_gpt-4-0125-preview"),  # Too expensive to be enabled by default.
         ],
         cache_path=cache_path,
         only_cached=only_cached,
diff --git a/scripts/compare_manual_scrap_vs_tavily_raw_content.py b/scripts/compare_manual_scrap_vs_tavily_raw_content.py
index 02b0c33c..c5b0e9e7 100644
--- a/scripts/compare_manual_scrap_vs_tavily_raw_content.py
+++ b/scripts/compare_manual_scrap_vs_tavily_raw_content.py
@@ -1,7 +1,7 @@
 import streamlit as st
 from dotenv import load_dotenv
-from evo_prophet.functions.web_search import web_search
-from evo_prophet.functions.scrape_results import scrape_results
+from prediction_prophet.functions.web_search import web_search
+from prediction_prophet.functions.scrape_results import scrape_results
 
 load_dotenv()
 st.set_page_config(layout="wide")
diff --git a/scripts/compare_search_results.py b/scripts/compare_search_results.py
index e6cb7d88..f9a76548 100644
--- a/scripts/compare_search_results.py
+++ b/scripts/compare_search_results.py
@@ -7,8 +7,8 @@
 from urllib.parse import urlparse
 from collections import defaultdict
 from prediction_market_agent_tooling.benchmark.utils import get_markets, MarketSource
-from evo_prophet.functions.web_search import web_search
-from evo_prophet.autonolas.research import safe_get_urls_from_query
+from prediction_prophet.functions.web_search import web_search
+from prediction_prophet.autonolas.research import safe_get_urls_from_query
 
 ENGINES: dict[str, t.Callable[[str, int], list[str]]] = {
     "tavily": lambda q, limit: [x.url for x in web_search(q, max_results=limit)],
diff --git a/scripts/deploy.py b/scripts/deploy.py
index 35cf3032..2e423410 100644
--- a/scripts/deploy.py
+++ b/scripts/deploy.py
@@ -4,7 +4,7 @@
 from git import Repo
 from datetime import datetime
 from prediction_market_agent_tooling.markets.markets import MarketType
-from evo_prophet.deployment.models import DeployableAgentER, DeployableAgentER_EvoGPT3, DeployableAgentER_OlasEmbeddingOA
+from prediction_prophet.deployment.models import DeployableAgentER, DeployableAgentER_PredictionProphetGPT3, DeployableAgentER_OlasEmbeddingOA
 from prediction_market_agent_tooling.config import APIKeys
 from prediction_market_agent_tooling.gtypes import private_key_type, DatetimeWithTimezone
 from prediction_market_agent_tooling.tools.web3_utils import verify_address
@@ -12,7 +12,7 @@
 
 
 DEPLOYABLE_AGENTS = [
-    DeployableAgentER_EvoGPT3,
+    DeployableAgentER_PredictionProphetGPT3,
     DeployableAgentER_OlasEmbeddingOA
 ]
 
@@ -40,7 +40,7 @@ def deploy(
     chosen_agent_class: t.Type[DeployableAgentER] = [agent for agent in DEPLOYABLE_AGENTS if agent.__name__ == deployable_agent_name][0]
     
     chosen_agent_class().deploy_gcp(
-        repository=f"git+https://github.com/polywrap/evo.prophet.git@{Repo('.').active_branch.name}",
+        repository=f"git+https://github.com/polywrap/predictionprophet.git@{Repo('.').active_branch.name}",
         market_type=market_type,
         api_keys=APIKeys(
             BET_FROM_ADDRESS=verify_address(bet_from_address),
diff --git a/scripts/measure_memory.py b/scripts/measure_memory.py
index 6ab87a5d..fdde575f 100644
--- a/scripts/measure_memory.py
+++ b/scripts/measure_memory.py
@@ -1,6 +1,6 @@
 import time
 import typer
-from evo_prophet.benchmark.agents import AGENTS
+from prediction_prophet.benchmark.agents import AGENTS
 
 
 def main(sleep: int = 120) -> None:
diff --git a/tests/test_benchmark.py b/tests/test_benchmark.py
index 22b83d1a..397ab7cc 100644
--- a/tests/test_benchmark.py
+++ b/tests/test_benchmark.py
@@ -1,8 +1,8 @@
 import json
 
 import prediction_market_agent_tooling.benchmark.benchmark as bm
-from evo_prophet.autonolas.research import clean_completion_json
-from evo_prophet.benchmark.agents import completion_prediction_json_to_pydantic_model
+from prediction_prophet.autonolas.research import clean_completion_json
+from prediction_prophet.benchmark.agents import completion_prediction_json_to_pydantic_model
 
 
 def test_parse_result_str_to_json() -> None:
diff --git a/tests/test_evaluate_question.py b/tests/test_evaluate_question.py
index 87ec8c66..cfefe6f6 100644
--- a/tests/test_evaluate_question.py
+++ b/tests/test_evaluate_question.py
@@ -1,5 +1,5 @@
 import pytest
-from evo_prophet.functions.evaluate_question import is_predictable
+from prediction_prophet.functions.evaluate_question import is_predictable
 
 
 @pytest.mark.parametrize("question, answerable", [