• Understand the evolution from LLMs to agentic AI and how autonomous agents fit into real-world AppSec workflows.
• Learn the core building blocks of AI Agents, including tool calling, reasoning workflows, short-term and long-term memory, MCP, vector databases, and RAG grounding.
• See how document-driven and code-driven threat modeling agents are built using ingested artifacts, diagram interpretation, framework mapping, and security-oriented code profiling.

• Build agents with tool integrations, reasoning loops, and memory persistence using practical agent SDK patterns.
• Connect agents to MCP servers over stdio and SSE, and ground outputs with vector databases such as ChromaDB using RAG.
• Create threat modeling workflows that ingest architecture documents, analyze diagrams with VLMs, map threats to STRIDE and MITRE ATT&CK, and derive contextual findings from source code abstractions and attack surfaces.

• Learn how AI Agents perform static and dynamic security testing by combining code reconnaissance, taint-style analysis, browser-driven application exploration, and contextual exploitation.
• Understand how SAST agents identify technology stacks, entry points, authentication flows, sensitive data paths, and source-to-sink vulnerabilities.
• Explore how DAST agents use Playwright MCP, runtime interaction, attack mapping, payload generation, and confirmed-result reporting to automate application testing.

• Build SAST agents that scan repositories, map attack surfaces, trace input to dangerous sinks, classify vulnerabilities, and generate code-aware remediation output.
• Build DAST agents that autonomously walk applications, discover routes and input surfaces, generate context-aware attack payloads, and validate findings based on runtime evidence.
• Produce actionable security reports with evidence packaging, taint-flow descriptions, CWE mapping, exploitability scoring, and payload-backed vulnerability confirmation.

• Learn how Agents operate against live infrastructure by auditing Kubernetes environments through MCP-exposed cluster tooling rather than direct API integration.
• Understand how agents assess cluster visibility, RBAC posture, network isolation, workload hardening, and secret handling using reasoning-driven workflows.
• See how autonomous security agents turn raw cluster state, configuration data, and logs into contextual infrastructure security findings.

• Deploy and use Kubernetes MCP-based workflows that expose callable tools such as resource retrieval, describe operations, log analysis, and schema inspection.
• Build agents that detect dangerous Role and ClusterRole permissions, missing NetworkPolicies, unrestricted pod communication, insecure pod security contexts, and privileged container configurations.
• Implement Kubernetes audit reporting that identifies insecure secret usage, weak workload hardening, and data protection gaps such as missing encryption-at-rest checks.

• Understand how autonomous Agents expand into AWS identity, infrastructure, and data security assessment using MCP-connected cloud audit agents.
• Learn how security automation scales through repeatable agent workflows for IAM review, privilege simulation, storage auditing, and network exposure analysis.
• See how human oversight is preserved while agents handle repetitive cloud security assessment tasks with controlled execution boundaries and evidence-backed outputs.

• Build AWS audit agents that identify users without MFA, stale access keys, wildcard permissions, and shadow-admin privilege paths using IAM-focused MCP tooling.
• Implement cloud scanners that review S3 public access and encryption posture, and detect EC2 Security Group exposure on high-risk administrative ports.
• Design scalable autonomous security workflows that convert cloud configuration evidence into structured findings, severity-based prioritization, and actionable remediation outputs.

‍