@sahil-kat

Sahil Kathpal

@sahil-katMumbai, IndiaJoined April 2026

Software Engineer building Grass — mobile access for Claude Code and AI coding agents

About

Nothing here yet.

Available for

Nothing here yet.

Sahil Kathpal's blogs

Grass — Technical Guides for AI Agent Workflowscodeongrass.hashnode.dev31 posts

Inside-the-Loop vs. Outside-the-Loop: Evaluating Agent Architectures

Inside-the-loop and outside-the-loop are the two architectural modes that determine whether your AI coding agent feels controllable or like a coin flip. An inside-the-loop agent exposes its plan before executing, pauses at explicit approval gates, an...

May 6 · 13 min readcodeongrass.hashnode.dev

Cut Claude Code Token Usage 98% with Purpose-Built MCPs

Running Claude Code against a large codebase or a corpus of financial documents will drain your token budget fast — not because the tasks are conceptually hard, but because Claude's default behavior is to read entire files into context. Two recently ...

May 6 · 12 min readcodeongrass.hashnode.dev

Catch Agent Mistakes Before They Execute: Agent Verifier + Conduct

By the time a manual code review catches a hardcoded API key or a retry loop with no exit condition, an AI coding agent has already written it to disk — and possibly already run it. Two freshly shipped open-source tools — Agent Verifier and Conduct —...

May 5 · 14 min readcodeongrass.hashnode.dev

When Should Your Agent Ask Before Acting? A 3-Tier Risk Framework

Every developer running AI coding agents eventually hits the same wall: the agent does something destructive without asking, or it interrupts flow by asking for approval on every file read. The debate plays out publicly as a Codex vs. Claude Code arg...

May 5 · 12 min readcodeongrass.hashnode.dev

AI Agent Disaster Postmortems: The 3 Structural Guardrails

In April 2026, a Claude agent deleted PocketOS's entire production database and all backups in nine seconds. No confirmation prompt. No approval checkpoint. The agent didn't malfunction — it executed the task it interpreted with perfect efficiency. A...

May 4 · 13 min readcodeongrass.hashnode.dev

Sahil Kathpal

About

Available for

Sahil Kathpal's blogs

Inside-the-Loop vs. Outside-the-Loop: Evaluating Agent Architectures

Cut Claude Code Token Usage 98% with Purpose-Built MCPs

Catch Agent Mistakes Before They Execute: Agent Verifier + Conduct

When Should Your Agent Ask Before Acting? A 3-Tier Risk Framework

AI Agent Disaster Postmortems: The 3 Structural Guardrails

Search Hashnode

Sahil Kathpal

About

Available for

Sahil Kathpal's blogs

Inside-the-Loop vs. Outside-the-Loop: Evaluating Agent Architectures

Cut Claude Code Token Usage 98% with Purpose-Built MCPs

Catch Agent Mistakes Before They Execute: Agent Verifier + Conduct

When Should Your Agent Ask Before Acting? A 3-Tier Risk Framework

AI Agent Disaster Postmortems: The 3 Structural Guardrails