In this part we will implement the core of the agent.
Overview
Our Agent will be fully open source and will be able to run on any machine that has ollama installed.
Implementation Details
- We utilize Ollama to host our AI model.
- Our agent runs on the gemma3:27b model.
Agent Code
Explanation
In the code snippet below, we implement a trading AI agent that:
- Polls continuously for fresh news and market data. (simulated for illustration purposes)
- Processes a JSON input containing a news transcript, headlines, and ticker data.
- Uses a carefully crafted system prompt (system_message_2) to guide its response structure.
- Checks a memory record to ensure duplicate notifications are not sent.
- Outputs a JSON-formatted response with actionable instructions, such as notifying the user or pushing new entries into its memory.
This design demonstrates how an agent can deliver timely updates while avoiding redundancy, ensuring that notifications are both meaningful and non-intrusive.
Code
import json
import ollama
import time
from datetime import datetime
system_message = """You are a Trading AI Agent.
Your Purpose is to assist the User
Try to exand his cognition
Do not annoy the user with dupplicate notifications just notify once for each event
Your inputs:
You will get JSON as input
You will get the following structured Data into your context window:
{
"memory": <Array of simple strings>
"news_transcript" : <transcribed Speech from news livestream for example bloomberg,MSNBC etc>
"news_headlines" : <news headlines>
"tickers" : <overview over current prices>
}
Your Output:
Response in JSON in the format:
{
"action": <>,
"message_for_the_user": <>
}
You can choose between the following actions:
Examples of single actions:
{ "action": "notify_user", "message": <here information you want to provide for the user. IMPORTANT: always save a memory that you notified about an event> }
{ "action": "push_to_memory", "memory": <a string of what you want to remember> },
Examples of final responses:
{
"actions": [
{ "action": "push_to_memory", "memory": "I have notified the user about -> Job reports on friday april 5 2025" },
{ "action": "notify_user", "message": "Job reports on friday april 5 2025" }
]
}
When there is no meaningful action nessasary at the moment just return a empty actions array
{
"actions": []
}
"""
system_message_2 = """You are a Trading AI Agent.
Your Purpose is to assist the User with trading insights.
Try to expand his cognition without being intrusive.
Do not just take for granted whats in the news
Always do your own research
IMPORTANT - NOTIFICATION RULES:
1. Before sending any notification, check your memory array THOROUGHLY
2. If your memory contains ANY reference to already notifying the user about a specific event, DO NOT notify again
3. Use semantic matching to identify duplicate events (not just exact text matches)
4. For each event, store a structured memory entry: "NOTIFIED:[event_type]:[key_entity]:[date]"
Example: "NOTIFIED:speech:trump-tariffs:april-2"
5. Always check for this standardized memory pattern before sending notifications
Your inputs:
You will get JSON as input with the following structured data:
{
"memory": <Array of simple strings>
"news_transcript" : <transcribed Speech from news livestream for example bloomberg,MSNBC etc>
"news_headlines" : <news headlines>
"tickers" : <overview over current prices>
}
Your Output:
Response in JSON in the format:
{
"actions": [
{ "action": "notify_user", "message": <information for user> },
{ "action": "push_to_memory", "memory": <structured memory entry using the NOTIFIED format> }
]
}
When there is no meaningful action necessary or if an event has ALREADY been notified about, return an empty actions array:
{
"actions": []
}
Allowed Actions are
{ "action": "notify_user", "message": <here information you want to provide for the user. IMPORTANT: always save a memory that you notified about an event> }
{ "action": "push_to_memory", "memory": <a string of what you want to remember> },
"""
context_window = """
transcribed Speech from Bloomberg livestream:
We will see that donald trump will talk about tarrifs on wednesday April seconds
overview over current prices:
Bitcoin: 65000
SPX: 2000
QQQ: 345345
bloomberg news headlines:
- President Trump about to anounce tarrifs on autos
"""
memory = []
context_window_json = {
"memory": memory,
"news_transcript" : "We will see that donald trump will talk about tarrifs on wednesday April seconds",
"news_headlines" : ["President Trump about to anounce tarrifs on autos"],
"tickers" : {
"Bitcoin": 65000,
"SPX": 2000,
"QQQ": 345345
}
}
for i in range(0,200):
print('-----------------------------------')
print('-----------------------------------')
print('-----------------------------------')
print('-----------------------------------')
print('-----------------------------------')
print('-----------------------------------')
print('start new agent run')
print('-----------------------------------')
print('current Agent Memory')
print(memory)
print('-----------------------------------')
start_time = datetime.utcnow().timestamp()
response = ollama.chat(
model='gemma3:27b',
format="json",
messages=[
{
'role': 'system',
'content': system_message_2,
},
{
'role': 'user',
'content': json.dumps(context_window_json, indent=2),
}]
)
end_time = datetime.utcnow().timestamp()
print('-----------------------------------')
print('response took', end_time - start_time)
print('input:')
print(json.dumps(context_window_json, indent=2))
print('output:')
print(response['message']['content'])
print('-----------------------------------')
response_as_json = json.loads(response['message']['content'])
# verify answer structure
if not 'actions' in response_as_json.keys():
print('malformed answer - no actions key -> SKIP')
continue
if not (type(response_as_json['actions']) is list):
print(type(response_as_json['actions']))
print('malformed answer - actions not a list -> SKIP')
continue
# process structured answer
for action_object in response_as_json['actions']:
# verify action structure
#TODO: check if action type is dict
#TODO: check if action has key "action"
#TODO: check if action exist in allowed actions
if action_object['action'] == "push_to_memory":
memory.append(action_object['memory'])
# prepare next context_window_json
context_window_json['memory'] = memory
time.sleep(0.1)
This article should be for now just a demonstration of the concept of feeding the agent with news data and market data. In a future part we will connect the agent in a more sophisticated way to the news broadcast and other data sources.
DISCLAIMER: The provided code does not present a production-ready setup regarding security and stability.
All code presented in this tutorial is used at your own risk.
Consider always performing security audits before putting any code in production.
Furthermore, none of the parts of the tutorials or code content should be considered as financial advice.
Always consult a professional investment advisor before making any investment decisions.
At CorticalFlow expanding the cognitive ability of the user is our mission.
- Check out our Website CorticalFlow
- Follow us on Twitter @CorticalFlow
- Check out our GitHub CorticalFlow
- Check out our YouTube CorticalFlow