Artificial Intelligence|Published: Oct 30, 2026
6 ways AI can quietly sabotage your SDLC
AI makes coding cheap, but it doesn’t replace engineering judgment. Here are six ways AI agents can quietly undermine your SDLC, and what you can do about them.
Artificial Intelligence|Published: Oct 27, 2026
Beyond One AI Reviewer: Build Your Own Code Review Council
We ran a council of AI reviewers on a real Strapi PR that shipped two bugs. It caught both, every time. Here’s how to build your own, and when it’s worth the extra tokens.
Artificial Intelligence|Published: Sep 30, 2026
Who needs documentation anyway in the era of AI?
When software engineering emerged in the mid-20th century, shaped by pioneers such as Alan Turing, John von Neumann, Grace Hopper, Edsger Dijkstra, and later Fred Brooks, software was largely about logic, mathematics, and precise instructions for a machine. Programs were smaller, the gap between the implementation and the knowledge required to understand was relatively short, and much of the truth about a system could be found directly in its source code. The code was the documentation.
Artificial Intelligence|Published: Sep 30, 2026
OWASP AISVS 1.0 - Practical Look at the New AI Security Standard
Not so long ago, I wrote an article about OWASP ASVS 5.0 (a comprehensive security checklist aiming for web applications). I mentioned there that AI security was intentionally left outside of its scope. There is now a brand new OWASP document specifically for filling this gap: AISVS. I've looked at this standard. Is it actually helpful when building an AI-enabled system?
Artificial Intelligence|Published: Sep 28, 2026
AI-driven CVE overload: where the secure SDLC breaks, and how to fix it
Around 66,000 CVEs are expected in 2026. Most won't affect your code, but which ones will? A practical look at layered, AI-supported vulnerability triage.
Artificial Intelligence|Published: Sep 22, 2026
How Banks Govern Autonomous AI in Software Development
For a bank, introducing autonomous coding agents is an architecture, security and governance problem. Here is how Visdom addresses data residency, machine-enforced boundaries, credential security, AI tracing, audit integrity, human oversight, code quality, test verification, organizational context and cost governance.
Artificial Intelligence|Published: Sep 7, 2026
Shadow AI Is Already in Your Codebase - Why Banking Needs a Risk-Based Governance Model for AI-Native SDLC
Most of the AI-generated code already in your codebase arrived through unsanctioned tools on personal accounts. This is Shadow AI — and like shadow banking before 2008, the risk is invisible until it isn't. Here's how to govern it with risk-based triage, traceability, and Continuous Modernization.
Artificial Intelligence|Published: Sep 2, 2026
Why AI-Native Software Delivery Needs More Than a Better Model
AI tools work. Adoption is above 80%. And yet measurable business value remains stubbornly low. The bottleneck is not the model — it's the software delivery system around it.
Artificial Intelligence|Published: Sep 2, 2026
When AI Writes the Code, What Runs the SDLC?
A coding agent is not an AI-native SDLC. Visdom provides the control plane — context, orchestration, sandboxing, and auditability — required to turn AI-generated code into software enterprises can trust in production.
Artificial Intelligence|Published: Jul 14, 2026
Natural language search to domain query search with AI & AWS Bedrock
Learn how to build a natural language search feature using AI and Amazon Bedrock. Translate user intent into secure, structured SQL or GraphQL queries without training custom LLMs.
Artificial Intelligence|Published: Jul 13, 2026
How to evaluate your agents?
Evaluating agentic systems is a multi-dimensional challenge that requires a multi-layered framework. A robust evaluation system must verify both functional and non-functional requirements. The system should verify whether an agent is fulfilling its core objectives, while performing efficiently, safely and with low latency. Furthermore, the system must account for scalability while ensuring the agent's underlying reasoning remains transparent and traceable. Those different evaluation layers allow, to evaluate the model both from the technical and strategic business perspectives.
Artificial Intelligence|Published: Jul 1, 2026
AI Must-Read for June 2026: Top Trends that Keep Great Engineers Ahead
A monthly reading roundup - no chasing every model, no top-50 lists, no marketing. One thread running through it all: the best model on the planet can be switched off on a Friday afternoon, so the real asset is what you build around it. You lease the model, but the process is yours.
