Insights & Updates
Explore insights from our engineering team on software development, AI, cloud architecture, and industry best practices.
Master Claude API integration for enterprise applications. Learn authentication, streaming responses, tool use, vision capabilities, and best practices for building reliable AI-powered features with Anthropic's most advanced models.
Jishu Labs
CTO
January 20, 2026
13 min read
Featured Article
122 articles · page 2 of 11
Cyclomatic complexity counts the independent paths through a function. It is the most widely used code metric and the most widely misused - useful as a smoke alarm, useless as a target.
With a large share of new code now AI-generated, review is the bottleneck rather than authoring. What machines review well, what they review badly, and how to split the job without losing the part that mattered.
A service level objective is a target for reliability, deliberately below 100%. The number is not the point - the error budget it creates is, because that is what turns reliability into a decision instead of an argument.
Financial services has governed models for decades. Generative AI does not escape that framework - it stresses it. What model risk management asks of an LLM feature, and what to instrument.
An entity-relationship diagram shows what things exist in a system and how they relate. Its real value is not documentation - it is that cardinality forces questions nobody asks until the data is wrong.
Adding an LLM to a product that touches protected health information changes who your subprocessors are, what your logs contain, and what you must be able to prove. An engineering view of the constraints.
AI readiness is whether an organisation can actually put AI into production and keep it there. It is mostly a data, governance and operations question, and almost never a model question.
The Act's most consequential obligations landed on 2 August 2026, and some were then moved. What is in force now, what shifted, and what an engineering team building AI features should actually do about it.
A story point is a relative measure of effort, not a unit of time. Almost every problem teams have with them comes from quietly converting them back into hours.
Most AI build-versus-buy decisions are made on cost and regretted on control, or made on control and regretted on maintenance. A framework based on what is actually differentiating for your business.
A migration is a versioned, repeatable change to a database structure. The interesting part is not writing them - it is running them against a live system without downtime or data loss.
AI features have a cost structure traditional software does not: it scales with usage, varies per request, and is set by design decisions made months earlier. A method for estimating before you build.
Get the latest insights on software development, AI, and technology trends delivered to your inbox.
Get consistent results. Collaborate in real-time.
Build Intelligent Apps. Work with Jishu Labs.