Rohan Sen Sharma (@nulltensor)

A 90% agent PR merge rate can still describe a weak engineering workflow

When a coding agent opens ten pull requests and reviewers merge eight, an 80% acceptance rate looks like a useful performance measure. It tells us that most submitted changes cleared review. It does n

Oct 9 · 7 min readnulltensor.hashnode.dev

Your customer support AI is probably going to fail in production!

We were looking to implement a customer support AI agent. Our customer experience (CX) team evaluated several products, with varying levels of confidence in their suitability. A support-AI demo can pr

Oct 7 · 8 min readnulltensor.hashnode.dev

Using AI to Investigate a Slow Query: Why Django icontains Skipped Our pg_trgm Index

We used AI to find out why Django's icontains filter was quietly bypassing our PostgreSQL pg_trgm trigram index while product searches slowed to several seconds. Django's icontains lookup performs a c

Oct 5 · 7 min readnulltensor.hashnode.dev

Loop Engineering in Practice: Six Feedback Loops for AI Coding Agents

This is loop engineering in practice: six feedback loops that turn an AI coding agent's corrections into lasting checks across the delivery pipeline. We were recently implementing a feature that allow

1Oct 3 · 7 min readnulltensor.hashnode.dev

Claude Skills vs MCP: What Each Does and When to Use Both

Claude Skills vs MCP comes down to what Claude knows versus what Claude can reach: a Skill teaches it a procedure, MCP connects it to external systems, and most real workflows use both. The Problem Ev

Oct 1 · 12 min readnulltensor.hashnode.dev

Rohan Sen Sharma

About

Available for

Rohan Sen Sharma's blogs

A 90% agent PR merge rate can still describe a weak engineering workflow

Your customer support AI is probably going to fail in production!

Using AI to Investigate a Slow Query: Why Django icontains Skipped Our pg_trgm Index

Loop Engineering in Practice: Six Feedback Loops for AI Coding Agents

Claude Skills vs MCP: What Each Does and When to Use Both

Rohan Sen Sharma

About

Available for

Rohan Sen Sharma's blogs

A 90% agent PR merge rate can still describe a weak engineering workflow

Your customer support AI is probably going to fail in production!

Using AI to Investigate a Slow Query: Why Django icontains Skipped Our pg_trgm Index

Loop Engineering in Practice: Six Feedback Loops for AI Coding Agents

Claude Skills vs MCP: What Each Does and When to Use Both

Rohan Sen Sharma

About

Available for

Rohan Sen Sharma's blogs

A 90% agent PR merge rate can still describe a weak engineering workflow

Your customer support AI is probably going to fail in production!

Using AI to Investigate a Slow Query: Why Django icontains Skipped Our pg_trgm Index

Loop Engineering in Practice: Six Feedback Loops for AI Coding Agents

Claude Skills vs MCP: What Each Does and When to Use Both

Search Hashnode

Rohan Sen Sharma

About

Available for

Rohan Sen Sharma's blogs

A 90% agent PR merge rate can still describe a weak engineering workflow

Your customer support AI is probably going to fail in production!

Using AI to Investigate a Slow Query: Why Django icontains Skipped Our pg_trgm Index

Loop Engineering in Practice: Six Feedback Loops for AI Coding Agents

Claude Skills vs MCP: What Each Does and When to Use Both