AI & Engineering · 16 min
The Renderer Nobody Has Used Since 2023
A hands-on guide to Google's Open Knowledge Format on a JS/TS monorepo: bundle layout, a scaffold script, CI wiring, and outcomes after three months.
AI & Engineering
19 posts
AI & Engineering · 11 min
Your Vector Database Is Lying to You About Multi-Hop
Dense retrieval hits a proven geometric ceiling on multi-hop questions and fails silently — similarity scores stay confident even when the evidence is missing.
AI & Engineering · 10 min
Your Evals Have No Tests
A green eval suite isn't evidence your agent works — it's the absence of evidence. Mutation testing shows you exactly how blind your evals really are.
AI & Engineering · 7 min
A GenAI Project That Delivered Measurable Business Impact
A GenAI project succeeds or fails on whether you can name the business metric it moved — and prove it. The architecture is the price of entry, not the win.
AI & Engineering · 7 min
Data Governance for GenAI in Regulated Industries
In regulated, multi-tenant GenAI, governance isn't a constraint on the build — it's what decides whether you can ship. Design it into the first diagram.
AI & Engineering · 4 min
I gave AI sudo access to my legacy Node.js app while I was at lunch. It fixed 12 bugs.
A self-healing feedback loop: tail the logs, feed errors to Claude Code, let it fix, build, and restart — unattended. Here's what it actually fixed.
AI & Engineering · 6 min
Hallucination is not a model problem — it's a system design problem
Ground the model in retrieved evidence, constrain its output, verify its claims, and measure everything. A layered defense against LLM hallucination.
AI & Engineering · 7 min
How We Actually Measure RAG Quality
RAG quality by vibes doesn't survive a second engineer. Decompose by stage, build the eval set from real failures, calibrate the LLM judge, and gate CI.
AI & Engineering · 7 min
7 prompting techniques that actually work (tested & ranked)
A research-backed breakdown of the prompting methods — from zero-shot to ReAct — that reliably produce better, smarter, more useful AI output.
AI & Engineering · 7 min
How to structure your agentic workflows (Claude Code, Cursor, or any AI tool)
Five layers — context file, plan gate, atomic tasks, git checkpoints, verification loop — that make AI agents fast and trustworthy instead of chaotic.
AI & Engineering · 1 min
Episodic memory for agents with Graphiti
Episodic, bi-temporal memory with Graphiti lets an AI agent answer not just what's true now, but what was true when, without re-indexing the whole world.
AI & Engineering · 7 min
Multilingual RAG, Where the Languages Are Code
Code is many languages plus an identifier dialect tokenizers shred. Use code-specialized embeddings, identifier-aware retrieval, and structure-aware chunking.
AI & Engineering · 7 min
Agentic Workflows That Don't Spiral Out of Control
Reliable agents come from control, not capability. Cap turns and time, push predictable steps into a state machine, and keep a human on the irreversible ones.
AI & Engineering · 2 min
Why knowledge graphs beat vector-only RAG
Vector-only RAG returns flat, context-poor chunks ranked by similarity. Knowledge graphs model entities and relationships to traverse why things connect.
AI & Engineering · 6 min
Choosing a Vector Database: Benchmarks from My Own Workloads
Every vector DB benchmark was run on someone else's data. Benchmark your own vector count, dimensions, and — above all — your real filtering pattern.
AI & Engineering · 8 min
POC to Production: What Breaks When RAG Meets Real Users
A RAG demo proves the happy path exists. Production is everything else — tracing, drift, evals, and learning to say 'I don't have that part.'
AI & Engineering · 7 min
The Hallucination Problem: What Reduced Ours, What Didn't
Most LLM hallucination is a retrieval failure in disguise. Fix the context first, force citations, and give the model a sanctioned way to say 'I don't know.'
AI & Engineering · 7 min
Cutting LLM Inference Cost ~40% Without Losing Quality
Inference cost optimization is a measurement problem in disguise. Fix the quality metric first, then trim context, route models, and cache the stable prefix.
AI & Engineering · 6 min
RAG vs Fine-Tuning vs Long Context: My Decision Framework
'Should we fine-tune?' is usually the wrong first question. Ask instead: is the gap knowledge or behavior, and how often does the answer change?