# Amit Shafnir
> DevSecOps Engineer & AI Expert

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

## Expertise
- DevSecOps: CI/CD pipeline security, infrastructure as code, automated compliance
- AI Engineering: Autonomous agents, LLM integration, AI-powered automation
- Cloud Security: AWS, GCP, Kubernetes security, zero-trust architecture
- Automation: End-to-end workflow automation, ChatOps, self-healing systems

## Links
- Website: https://shafnir.com
- Projects: https://shafnir.com/projects
- Blog: https://shafnir.com/blog
- LinkedIn: https://linkedin.com/in/amitshafnir
- GitHub: https://github.com/shafnir
- Email: amit@shafnir.com

## Projects
- [SecOps AI Agent](https://shafnir.com/projects/secops-ai-agent): Autonomous agent connected to Slack, GitHub, Jira, and internal APIs. Handles access requests, validates user groups, generates Terraform, and opens PRs.
- [Security News Agent](https://shafnir.com/projects/security-news-agent): 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](https://shafnir.com/projects/ai-content-pipeline): 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](https://shafnir.com/projects/app-exposure-map): 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)?](https://shafnir.com/blog/agent-client-protocol): 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](https://shafnir.com/blog/stop-building-god-mode-agents): Why right-sized AI agents with validators beat one monolithic agent with all the permissions. Architecture patterns for secure, high-quality agent systems.

## Optional
- Full details: https://shafnir.com/llms-full.txt
- Per-page markdown: https://shafnir.com/index.md
- Blog post markdown: https://shafnir.com/blog/{slug}.md
- Location: Modiin, Israel