I assumed chunking was a solved problem. Pick a text splitter, set 512 tokens, add some overlap, move on. After running structured experiments across three different data types, that assumption collapsed. The best chunker for markdown documentation actively hurt performance on code. The winner changed completely depending on what I was chunking. Data type Winner Headline metric Markdown doc
The Autonomous Paradox In 2026, we’ve moved past simple chatbots. We are building Production-Grade RAG pipelines and autonomous agents that can plan, execute, and iterate. But as an architect, I’ve noticed a glaring hole in our "Agentic" future: Identity Sprawl. We are giving agents non-human identities (NHI) with "Full Admin" permissions just to ensure the RAG works smoothly. We are effectively
Introduction It's Black Friday. In the space of a single second, your e-commerce platform processes 4,000 orders, updates inventory counts, triggers fulfillment workflows, and debits customer accounts. Every one of those operations lands in your OLTP database, fast, atomic, precise. None of it, in that same second, tells you that customers are abandoning their carts at three times the normal rat
An opinionated list of Python frameworks, libraries, tools, and resources
What if your Kubernetes cluster simply refused to run unsigned images? I spent some time experimenting with enforcing image provenance in a small Kubernetes setup using MicroK8s. The idea was simple: Only container images with valid cryptographic signatures are allowed to run in the cluster. For this I used: GitLab CI/CD (build + signing pipeline) Cosign / Sigstore (image signing) Kyverno (admissi
Most teams I have worked with have one auth test in their suite. It looks like this: test('valid token verifies', () => { const token = signSync({ sub: 'user-1', aud: 'api://backend' }, secret); const result = verify(token, options); expect(result.valid).toBe(true); }); That test is fine. It is also a smoke test, not a regression suite. It catches the case where verification is completely b
The on-call alert at 02:14 said auth_5xx_rate spiked from 0.01 to 31.4. Not a deploy window. Not a traffic spike. Just thirty-one percent of authenticated requests failing for ~four minutes, then back to baseline. The cause was a JWKS rotation on the issuer side. New keys came in. Old keys went out. Caches in our service didn't refresh fast enough. Tokens signed with the new key were rejected beca
The DataFrame class (from Pandas) is a work of art. Even if you never "do data", priceless lessons can be gleaned by studying this class. It starts simple enough. Usually you will create a DataFrame by ingesting from a CSV file or database table or something. But you can whip up a small one like this: import pandas as pd df = pd.DataFrame({ 'A': [-137, 22, -3, 4, 5], 'B': [10, 11,