Illustration for the Sazko Solutions article on the future of AI in software development

The Future of AI in Software Development: What’s Actually Changing

By September 2026 the industry’s own framing had shifted: the value is in workflows, data rights and human review, not flashy demos. That’s a good moment to take stock of what has actually changed in how software gets built. It’s easy to be either dismissive or breathless about AI’s effect on software development, and both postures avoid the more useful question: what, specifically, is actually different about how software gets built today versus three years ago? A few concrete shifts are worth naming, separate from the marketing around them.

Sazko Solutions article on AI-assisted formal verification for critical software, July 2026

Formal Verification Meets AI: Why Machine-Checked Proofs Matter for Critical Systems

In July 2026, Mistral released a model aimed at formal software verification — generating machine-checked mathematical proofs, in Lean 4, that a piece of software behaves as specified. It’s a narrow capability with outsized implications for anyone building systems where “we tested it and it seemed fine” isn’t good enough.

Sazko Solutions article on long-running AI agents that improve between sessions, mid-2026

Agents That Learn Between Sessions: The Move to Long-Running AI Workflows

In May 2026, Anthropic described a technique it called “dreaming” — letting an autonomous agent review its own past behaviour between sessions, spot patterns, and adjust how it works next time. It’s part of a broader industry push toward agents that handle long-running workflows in areas like coding, finance and legal work, rather than one-shot tasks. That shift changes what you have to build around an agent.

Sazko Solutions article on AI-assisted defensive cybersecurity and vulnerability discovery in 2026

AI for Defensive Security: What the Industry’s Vulnerability-Hunting Push Signals

In April 2026, Anthropic announced a collaboration with several major technology and security firms to test an unreleased model on defensive cybersecurity work, and reported it had already surfaced thousands of vulnerabilities across operating systems, browsers and widely used software. Whatever becomes of that specific project, the direction is clear: AI-assisted vulnerability discovery is moving from research demo to standard practice.

Illustration for the Sazko Solutions article explaining the Model Context Protocol (MCP) and agentic AI

What MCP Actually Is, and Why It’s Becoming AI’s Common Plumbing

By March 2026, the Model Context Protocol had reportedly crossed tens of millions of installs, and NVIDIA’s GTC keynote was full of enterprise agents running in production. Every AI agent eventually needs the same thing: a reliable way to reach outside its own context window — into a database, a ticketing system, a filesystem, an internal API — and act on what it finds. Before the Model Context Protocol (MCP), teams solved this the same way they solved every integration problem: a bespoke adapter per tool, per model, per vendor. MCP’s contribution is boring in the best possible way — it standardizes that connector so it only has to be built once.