Skip to content
Hrushiekesh Reddy Kanjula

Blog

Weekly updates

Thoughts on AI workflows, tooling, and large-scale engineering — written by me, with AI.

June 2, 2026

·

~4 min read

·engineering

Stop Applying Tape: RCCA in Agentic Debugging

AI agents are good at finding something that works. They are terrible at finding out why something broke. That is a discipline problem — and manufacturing solved it sixty years ago.

engineeringai-agentsdebuggingroot-cause-analysissoftware-engineering

May 26, 2026

·

~7 min read

·essay

The Hidden Tax on Your AI: Context Windows, Skills, and the Cost of Attention

Every skill you load, every message you send, every document you attach quietly eats into the same fixed budget. Here's what happens when that budget runs out — and how to spend it wisely.

aicontext-windowtokenizationcost-optimizationskillsproductivitydeveloper-tools

May 25, 2026

·

~7 min read

·engineering

Running Multiple AI Agents in Parallel Without Destroying Your Codebase

Two AI agents writing to the same file simultaneously is a data corruption event. Here is the file-locking orchestration layer that makes parallel AI development safe and fast.

aimulti-agentengineeringarchitecturelanggraphparallel-execution

May 18, 2026

·

~7 min read

·essay

Governing AI Agents: Why Your LLM Needs a Constitution

Giving an LLM access to your codebase without governance constraints is like hiring a contractor and handing them the master key on day one. Here is the governance framework that keeps multi-agent AI development safe and productive.

aimulti-agentllmgovernanceengineeringarchitecture

May 11, 2026

·

~6 min read

·essay

AI Literacy: Knowing When to Prompt and When to Architect

The highest-leverage AI skill in 2026 is not writing better prompts. It is knowing which problems need a prompt and which need a full architectural design. Here is the line I draw.

aiengineeringarchitecturellmproductivityessay

May 4, 2026

·

~6 min read

·engineering

Rotation Heuristics in SMT Assembly: Why We Still Guess, and How IPC-2581 Fixes It

A 180-degree rotation error on a polarized capacitor causes a short circuit. A three-tier heuristic system catches most of them. The IPC-2581 standard would make the whole problem obsolete.

smtmanufacturingpythonipc-2581heuristicspcb

April 27, 2026

·

~7 min read

·engineering

Simulating Physics in Python: Vacuum Nozzle Validation for SMT Assembly

Every component on a PCB has a physical body width. Every nozzle has an outer diameter. If the nozzle is too large, it drops the part. Here is the 1,600-line async pipeline that validates this at scale.

pythonasynciomanufacturingsmtphysicsvalidation

April 20, 2026

·

~6 min read

·engineering

Closed-Loop Manufacturing: Cross-Linking AOI and SMT Machine Telemetry

An optical defect and the machine event that caused it happen minutes apart and live in separate databases. Time-windowing SQL joins close the loop — here is how.

sqlmanufacturinganalyticsaoismtdata-engineering

April 13, 2026

·

~7 min read

·engineering

The SQL Window Function That Saved Our Defect Attribution

SMT machines log generic errors milliseconds before they log the component that caused them. A forward-fill CTE using SQL window functions bridges that gap — here is exactly how it works.

sqlsqlitewindow-functionsmanufacturingdata-engineeringanalytics

April 6, 2026

·

~7 min read

·engineering

From Raw Machine Logs to Predictive Maintenance: Time-Series Analytics in SMT

Raw machine telemetry tells you what happened. Time-series analytics tells you what is about to happen. Here is how First-Pass Yield, rolling defect rates, and SQL-driven root cause analysis work together.

pythonsqltime-seriesanalyticsmanufacturingpredictive-maintenance

March 30, 2026

·

~6 min read

·engineering

Parsing Nested XML from Flying Probe Testers into a Relational Database

Flying Probe Tester XML files are massive, nested, and namespace-unstable. Here is the three-table relational schema and defensive parsing strategy that tames them.

pythonxmlsqlitemanufacturingtestingdata-engineering

March 23, 2026

·

~6 min read

·engineering

Fuzzy Matching AOI Defect Data to Your Component Library

AOI machines generate defect reports with part numbers that almost match your library. Here is the dynamic parsing and fuzzy matching system that bridges that gap.

pythonfuzzy-matchingaoimanufacturinginspectiondata-engineering

March 16, 2026

·

~6 min read

·engineering

Parsing the Unparseable: Adaptive BOM Ingestion for Customer Spreadsheets

Customers send spreadsheets that look nothing alike. Hardcoded column indices fail on day two. Here is the four-step heuristic pipeline that handles anything.

pythondata-engineeringexcelbomheuristicsmanufacturing

March 9, 2026

·

~7 min read

·engineering

Normalizing 20,000 Components: The Data Pipeline Behind SMT Assembly Intelligence

A 10kΩ resistor has at least eight names in the wild. Here is how a regex-driven normalization engine turns manufacturing chaos into a canonical data layer.

pythondata-engineeringmanufacturingregexsmtbom

March 2, 2026

·

~6 min read

·engineering

Taming a 1,200-Line Python Function: State Management in Async Desktop Apps

When your Python backend and JavaScript frontend share state across async WebSocket calls, things fall apart fast. Here is the architecture that fixed it.

pythonasyncstate-managementeelarchitecturemanufacturing

February 23, 2026

·

~6 min read

·engineering

Why I Chose Eel Over Electron for a Factory-Floor Desktop App

PyQt was too limiting, Electron was too bloated. Eel let me build a glassmorphism dashboard on constrained edge hardware — and I almost feel bad about how well it worked.

pythoneelelectronguiedge-computingmanufacturing

February 16, 2026

·

~6 min read

·engineering

SQLite in Production: WAL Mode and Concurrency on the Factory Edge

Everyone told me SQLite wasn't a real production database. Then I enabled WAL mode, handled concurrent MES workloads, and stopped worrying.

sqlitepythonedge-computingdatabasemanufacturingconcurrency

February 9, 2026

·

~6 min read

·engineering

Why I Killed My 240KB Excel Macro and Built a Full-Stack MES Instead

Every manufacturing team has that one Excel macro — the one nobody touches. Here's why I finally killed ours and what I built instead.

pythonmanufacturingfull-stacksmtmesvba

February 2, 2026

·

~5 min read

·engineering

Python Async Programming: asyncio, aiohttp, and When to Actually Use It

asyncio is not a magic speed-up — it's a precise tool for a specific problem. Here's what it actually does, when it wins, and when it costs you more than it's worth.

pythonasyncioaiohttpconcurrencyengineering

January 26, 2026

·

~7 min read

·essay

The Agentic Trio: Using Claude Code, Cursor, and Google Antigravity Together

I spent months running Claude Code, Cursor, and Google Antigravity 2.0 side-by-side on real projects. Here's what the combined agentic stack actually looks like — and where it breaks.

claude-codecursorgoogle-antigravityagentic-workflowengineeringai-tools

January 19, 2026

·

~4 min read

·essay

Welcome to My Engineering Blog

An intro to this space — what I'll be writing about, how the blog is generated, and what the assembly hub is.

engineeringportfolioclaude-api