Liran Tal's Blog

Build a private, mobile-first Hermes Agent using Matrix Synapse, Element, end-to-end encryption, Tailscale Serve, and separate Proxmox LXC containers.

A hands-on guide to the files, schemas, workflows, governance, and maintenance routines behind an AI-assisted second brain.

How a plain-Markdown knowledge graph becomes a durable context layer, operating system, and compounding productivity tool for AI-assisted work.

I disclosed a Gemini CLI prompt injection where invisible Unicode tag characters in SKILL.md caused the agent to run a hidden command.

A practical pattern for turning a fragile Codex state migration into a reusable skill with backups, process ownership, validation, and a terminal helper.

A practical guide to turning a custom macOS terminal setup into portable, reviewable dotfiles with chezmoi, Homebrew Bundle, zsh modules, Starship, and a public-safe repository workflow.

Explore DevRel in 2026: how coding agents, AI builders, X-first communities, DevRel engineering, and product-centric advocacy are reshaping the field.

LLMs and coding agents amplify developer capability but they do not substitute for it.

Prompt injection is not a bug you patch but an architectural limit baked into how LLMs process language.

Microsoft's Agent Package Manager brings package.json-style manifests and lockfiles to Claude Skills, MCP servers, and other agent artifacts, with hands-on recipes and sharp edges we hit in practice (collections path, meta-packages, security).

Hands-on walkthrough: wire Fastify to load .env files, validate environment variables with JSON Schema, and expose config on the server instance, using the dotenv-org/examples Fastify reference PR as the source of truth.

How to wire a Cursor stop hook that runs pnpm lint and pnpm build after every agent turn, returns followup_message with captured output on failure, and avoids silent breakage from Cursor's bundled Node on PATH—plus loop limits, debug toggles, and when to…

An LLM Security Scanning and Review is a strong assist but a weeak gate.

How to use Jest fake timers, advance time safely in tests, and pair timer control with mocks and spies without flaky or misleading assertions.

A step-by-step walkthrough of building a benchmarking framework for AI coding agents using the Claude Agent SDK, including architecture decisions, scoring strategies, and code examples.

Examples of agentic growthhacking tactics using bots and AI, as well as strategies for sourcing user pain points on social media platforms.

If you're starting out as a new author, you're going to need all the help you can get.

The following is a reference implementation and architecture for secure direct browser uploads to Cloudflare R2 using pre-signed URLs generated by a Hono application on Cloudflare Workers.

A comprehensive guide to implementing secure file uploads using Cloudflare R2 and Hono, including common pitfalls and best practices

For those familiar with RESTful HTTP architecture, would it make sense to describe the Model Context Protocol (MCP) in a similar way?

How do you securely integrate a new MCP Server into Cursor or other agentic workflows?

How to evaluate and categorize security threats and risks associated with Model Code Protocol (MCP) in light of recent security incidents.

A breakdown of the Cursor + Jira MCP 0-Click attack, how it was exploited, and why developers are at the center of it all.

The Model Context Protocol (MCP) is gaining traction in the AI community, and with its rise comes a wave of security research.

How agent-rules open source project is helping create consistent and deterministic security in AI coding assistants.

Ever wanted to automate the process of evaluating hundreds of conference Call for Papers (CFP) submissions?

Agentic marketing is going to be the next marketing transformation that product marketers and growth teams need to embrace to stay ahead of the curve.

Learn how to enhance your Node.js CLI applications using the built-in `util.parseArgs` API.

Model Content Protocol (MCP) servers can be a security nightmare if not handled properly.

Learn how to enhance the security of your MCP server configurations by using the latest `ls-mcp` tool to detect and categorize credential risks in environment variables.

A step-by-step guide to training a neural network to solve an ASCII maze using JavaScript and brain.js.

The Qodo AI team has introduced the Package Health Reviewer, a new feature in their agents repository that automates the health assessment of third-party open-source packages using Snyk Advisor.

A practical guide to building a simple computer vision project in Python using Ultralytics YOLO for object detection and Supervision for annotation.

If you're in Developer Relations and you haven't yet adapted your practices to the post-GPT era, you might be missing out on the next big thing in developer tools.

A guide on securely loading Google Cloud Storage credentials in Node.js applications using various methods.

Ok so how do DevRel practitioners optimize for engagement on X (Twitter) when they post new products, announcements and other stories?

How zero-trust environments can leverage AI agents and agentic workflows without compromising security and trust.

Explore the 5 pillars of Augmented Agentic Software Development to enhance your AI coding workflows.

Agentic coding assistants in the forms of IDE extensions are becoming increasingly popular among developers but they're likely just a milestone in the evolution of LLM-powered software engineering which will truly be AI-native.

Model Context Protocol (MCP) is a great protocol but if your company is built around it as the core product, you're not gonna make it.

Running agentic AI workflows with the Qodo Command CLI is a powerful way to automate tasks but what's even cooler is that you can also automate the whole fine-tuning of the agentic workflow process itself USING THE AGENT!

Getting a security report for security vulnerabilities and misconfiguration issues of your GitHub project is a good start but can we leverage AI to also remediate all of these issues automatically through agentic workflow?

Learn how to set up a TV sleep timer using Home Assistant automation, Helpers, and Automations to manage your TV's power state easily.

Demystifying the 3 dimensions of cookie-based authentication: CORS, SameSite, and CSRF.

Gamified learning is a great way to engage developers and teach them new skills.

You're probably facing some DevRel failures or marketing failures.

Learn how to build powerful command-line apps without a single third-party dependency using Node.js core modules.

Practical and hands-on guide to getting started with Neural Networks in JavaScript using the Brain.js library to build a simple neural network to predict if a number is even or odd and more.

Developer Advocates and Engineers can leverage Generative AI to speed up their work and make them more productive.

Building with Large Language Models (LLMs) requires context and metadata.