# Amit Shafnir — DevSecOps Engineer & AI Expert

I architect security systems and build autonomous AI agents that protect, detect, and automate at scale.

Location: Modiin, Israel
Email: amit@shafnir.com
Website: https://shafnir.com
LinkedIn: https://linkedin.com/in/amitshafnir
GitHub: https://github.com/shafnir

---

## Expertise & Skills

### DevSecOps
- CI/CD pipeline security and hardening
- Infrastructure as code (Terraform, CloudFormation)
- Automated compliance and policy enforcement
- Container security and Kubernetes hardening
- Secret management and rotation

### AI Engineering
- Autonomous AI agent development
- LLM integration and prompt engineering
- AI-powered security automation
- RAG systems and knowledge bases

### Cloud Security
- AWS and GCP security architecture
- Zero-trust network design
- Cloud-native security tooling
- Incident response automation

### Automation
- End-to-end workflow automation
- ChatOps and Slack bot development
- Self-healing infrastructure
- Monitoring and observability

---

## Projects

### SecOps AI Agent
URL: https://shafnir.com/projects/secops-ai-agent
Markdown: https://shafnir.com/projects/secops-ai-agent.md
Status: production
Technologies: AWS_BEDROCK, AGENTCORE, TERRAFORM, PYTHON, STRANDS_SDK

Autonomous agent connected to Slack, GitHub, Jira, and internal APIs. Handles access requests, validates user groups, generates Terraform, and opens PRs.

### Security News Agent
URL: https://shafnir.com/projects/security-news-agent
Markdown: https://shafnir.com/projects/security-news-agent.md
Status: production
Technologies: N8N, POSTGRES, AI_AGENT, SLACK

Autonomous intelligence pipeline that monitors security news RSS feeds, classifies vulnerabilities with AI, cross-references organizational SBOM data, and delivers real-time Slack alerts when packages are affected.

### AI Content Pipeline
URL: https://shafnir.com/projects/ai-content-pipeline
Markdown: https://shafnir.com/projects/ai-content-pipeline.md
Status: production
Technologies: N8N, AI_AGENT, FREEPIK_FLUX, GOOGLE_SHEETS, RSS

Automated content pipeline built on n8n that monitors cybersecurity RSS feeds, filters articles with an AI agent, generates Hebrew LinkedIn posts with AI-created images via Freepik Flux, and logs everything to Google Sheets.

### App Exposure Map
URL: https://shafnir.com/projects/app-exposure-map
Markdown: https://shafnir.com/projects/app-exposure-map.md
Status: legacy
Technologies: PYTHON, VITE, F5_WAF, TUFIN, JENKINS, BITBUCKET_SERVER

On-prem security visibility tool that maps source code to public exposure by chaining Checkpoint NAT rules, F5 iRules, Jenkins deployments, and Bitbucket repos, enabling risk-based prioritization of vulnerability findings.

---

## Blog Posts

### What Is the Agent Client Protocol (ACP)?
Published: 2026-04-05
Tags: ai-agents, developer-tools, protocols

ACP lets any AI coding agent work in any editor. What it does, how it works, and why it matters for everyone writing code with AI.

### Stop Building God-Mode Agents
Published: 2026-04-07
Tags: ai-agents, security, architecture, devsecops

Why right-sized AI agents with validators beat one monolithic agent with all the permissions. Architecture patterns for secure, high-quality agent systems.

---

## Per-Page Markdown Endpoints

- Homepage: https://shafnir.com/index.md
- Projects: https://shafnir.com/projects.md
- Individual projects: https://shafnir.com/projects/{slug}.md
- Blog posts: https://shafnir.com/blog/{slug}.md

### Blog Post Markdown URLs

- What Is the Agent Client Protocol (ACP)?: https://shafnir.com/blog/agent-client-protocol.md
- Stop Building God-Mode Agents: https://shafnir.com/blog/stop-building-god-mode-agents.md