Swamy Talam
Principal Architect ( Data & AI) Over 22 yrs. of experience in IT. Global Delivery Models.
Saturday, July 26, 2025
Friday, July 25, 2025
Service Now AI Agent
Business App ( CMDB ) - will also take care heigene
ensure A2A protocol working
Workflow
KB articles as Agents
Tool
Thursday, July 24, 2025
MCP Vs A2A
A2A and the Model Context Protocol (MCP) are complementary standards for building robust agentic applications:
- MCP (Model Context Protocol): Connects agents to tools, APIs, and resources with structured inputs/outputs. Think of it as the way agents access their capabilities.
- A2A (Agent2Agent Protocol): Facilitates dynamic, multimodal communication between different agents as peers. It's how agents collaborate, delegate, and manage shared tasks.
langGrpah Open Agent Framework
- No different from Azurre AI Foundry or AWS bedrock or GCP Agent garden
- Supports only parallel execution of Tasks
- No suppor for Context Memory
- Suports native connectors
- Available in Private cloud
Information Systems Security Agent ( Multi Agent)
Agentic AI-powered security automation framework that performs:
-
Threat modeling (using STRIDE, OWASP Top 10),
-
Risk assessment (using DREAD/FAIR models),
-
Architecture parsing (from diagrams or IaC),
-
Compliance mapping (to NIST, ISO, SOC2),
-
Live Azure infrastructure auditing (e.g., VNet, NSG, Key Vaults, Route Tables),
-
Automated remediation planning (with suggested fixes),
-
Audit-ready reporting (in PDF or dashboard format),
-
ServiceNow integration (for CMDB, tickets, approvals).
Build this using a multi-agent system (LangGraph or Azure AI Foundry Agents) coordinated by a Supervisor Agent, with contextual memory (e.g., Azure AI Search or Weaviate). Include:
-
A system architecture diagram,
-
A step-by-step description of each agent's function and AI implementation,
-
An ROI analysis per agent (quantifying time/money saved),
-
A PowerPoint presentation summarizing all components,
-
A PNG diagram of the architecture, and
-
Exportable formats (PowerPoint, draw.io, or PlantUML if needed).
Monday, June 23, 2025
How to Create Agent in Azure AI Foundry
https://learn.microsoft.com/en-us/azure/ai-foundry/agents/overview?context=%2Fazure%2Fai-foundry%2Fcontext%2Fcontext
import os from azure.ai.projects import AIProjectClient from azure.identity import DefaultAzureCredential from azure.ai.agents.models import CodeInterpreterTool # Create an Azure AI Client from an endpoint, copied from your Azure AI Foundry project. # You need to login to Azure subscription via Azure CLI and set the environment variables project_endpoint = os.environ["PROJECT_ENDPOINT"] # Ensure the PROJECT_ENDPOINT environment variable is set # Create an AIProjectClient instance project_client = AIProjectClient( endpoint=project_endpoint, credential=DefaultAzureCredential(), # Use Azure Default Credential for authentication api_version="latest", ) code_interpreter = CodeInterpreterTool() with project_client: # Create an agent with the Bing Grounding tool agent = project_client.agents.create_agent( model=os.environ["MODEL_DEPLOYMENT_NAME"], # Model deployment name name="my-agent", # Name of the agent instructions="You are a helpful agent", # Instructions for the agent tools=code_interpreter.definitions, # Attach the tool ) print(f"Created agent, ID: {agent.id}") # Create a thread for communication thread = project_client.agents.threads.create() print(f"Created thread, ID: {thread.id}") # Add a message to the thread message = project_client.agents.messages.create( thread_id=thread.id, role="user", # Role of the message sender content="What is the weather in Seattle today?", # Message content ) print(f"Created message, ID: {message['id']}") # Create and process an agent run run = project_client.agents.runs.create_and_process(thread_id=thread.id, agent_id=agent.id) print(f"Run finished with status: {run.status}") # Check if the run failed if run.status == "failed": print(f"Run failed: {run.last_error}") # Fetch and log all messages messages = project_client.agents.messages.list(thread_id=thread.id) for message in messages: print(f"Role: {message.role}, Content: {message.content}") # Delete the agent when done project_client.agents.delete_agent(agent.id) print("Deleted agent")
Sunday, September 15, 2024
Run Llama 3 on your laptop
Ollama is a convenient platform for the local development of open-source AI models.
Why should you use open-source AI? \
But they come with 4 major problems:
Data Privacy. When “talking” to GPT-4 you always send your data to the OpenAI server. For most companies, this is the #1 reason NOT to use AI.
Cost. The best-performing LLMs are expensive, especially for high-volume applications.
Dependency. Using GPT-4 or Claude means you rely on OpenAI or Anthropic. Most businesses prefer independence.
Limited Customization. Every business has unique needs and problems. Custom solutions are crucial for many. But customizing the biggest models is possible only through Prompt Engineering.
Getting the Simple Response
Now it’s time to test our model. Let’s ask a simple question to see how it works.
import ollama
model = "llama3"
response = ollama.chat(
model=model,
messages=[
{"role": "user", "content": "What's the capital of Poland?"}
]
)
print(response["message"]["content"])
## Prints: The capital of Poland is Warsaw (Polish: Warszawa).
import ollama
to use Ollama APImodel = "llama3
to define the model we want to useollama.chat()
to get the response. We used 2 parameters:
-model
that we defined before
-messages
where we keep the list of messages
To get the response, we dig in the response
object for ["message"]["content"]
.
Sunday, February 18, 2024
OLTP and OLAP
Tuesday, February 13, 2024
test
Monday, January 29, 2024
Cyber Security Standards - Risk Based Framework
Purpose
- The Risk Based Framework (RBF) is a risk classification system developed by the Enterprise Cyber Security (ECS) department of the Cyber Risk Management team.
- ECS policy is intended to protect the firm in an evolving threat landscape, regardless of changes in technology or business practices.
- Even if specific terminology or scenarios are not part of the text, it is expected that you will exercise sound reasoning and judgment to adhere to the intent of stated requirements, practices, and implementations in both letter and spirit.
Scope
- All systems that are listed in the IT Service Manager (ITSM) application (e.g., ServiceNow), are required to have an RBF classification.
- All systems where the lifecycle stage is ‘Concept’, ‘Acquisition/Development’, or ‘Retired’ are not in scope.