Securing the AI-native developer.
I'm Barath. I build secure-by-default platforms and shift-left guardrails for engineering teams in the LLM era — and write about what it's teaching me along the way.
Things I'm proud of
A few projects that capture how I think about products, AI, and shipping.
Project Netra
Shift-left security guardrails for AI coding assistants.
Adobe Cyber Trail (ACT)
Cross-functional security telemetry, turned into action.
Secure Blocks
Reusable, secure-by-default service building blocks.
Small AI experiments, in public
Half-finished things I'm using to learn. Each one a tiny answer to a question I had.
Ask Me Anything
A small AI grounded on my writing, projects, and notes.
Threat Model Assistant
First-pass STRIDE on a feature spec — speeds the human review.
Prompt Playground
Test, version, and share prompts side-by-side across models.
Semantic Search
Search across posts, projects, and resources by meaning.
GitHub Pulse
Live look at what I'm shipping this week.
Learning Log
What I'm reading, watching, and chewing on.
Latest from the journal
Notes, essays, and weekly logs from working in public.
What I'm exploring this week
Small experiments, half-thoughts, and links worth your time.
Shift-left, but for AI coding assistants
Notes on what changes (and what doesn't) when ~14K developers start writing code with an LLM in the loop.
Threat modeling, faster — with an LLM in the loop
A practical pattern for using an LLM to bootstrap STRIDE without giving up the parts that need a human.
A community space for AI builders
A growing collection of tools I use, prompts I trust, and resources I'd send to a friend starting out.
Cursor
Editor with first-class AI. The fastest loop for refactors and PR-sized changes.
AI CodingClaude Code
CLI agent that pairs well with security-focused workflows and large repos.
AI CodingClaude
Default model for thinking out loud, drafting, and security review prose.
ModelsLangGraph
Coordinator/worker patterns and deterministic checkpoints for agent flows.
AI FrameworksGot a tool I should add?
The hub is curated — I only add things I'd actually recommend. If something belongs here, send it over.
AI notes from the edge.
Once a month: tools worth using, experiments I'm running, and short essays on building with AI. No fluff, no recap of news you already saw.
Free. Unsubscribe anytime. No spam.