AI AI assistants AI Coding

Claude, Code, and the Real Question: What Can’t Be Automated?

Svetozar Eliseev

24 Dec 2024 — 1 min read

In a glowing feature by OpenTools.ai, Anthropic’s Claude is cast as the next big leap in AI-assisted coding—an “AI code whisperer” reshaping how teams develop software. At Gehtsoft, we see the potential. But we also ask: where does real engineering begin when autocomplete ends?

CEO Ivan Gekht’s view is precise:

“Code generation is not delivery. And fluency is not foresight.”

Claude may help you write a regex. But it won’t tell you:

If your architecture supports scale under compliance
If your trade-offs are sound under real-world constraints
If your sprint velocity is optimizing the wrong thing

We use AI—but as augmentation, not delegation. In our world, mission-critical software isn’t built by suggestion. It’s built by understanding, validation, and accountability.

Claude is a tool. Strategy is still human.

Read the article: Claude: The AI Code Whisperer – OpenTools.ai

Risk Management under Real Velocity: Push Detection Downstream, Limit Blast Radius

I was recently quoted in a TechBullion article on balancing speed and security in business risk management. The core idea was simple: increasing business velocity does not remove the need for risk management. It changes its economics. This is not a technical nuance. It is a decision problem. At higher

AI and the missing first step in learning

What could be the long-term impact of AI on career progression in knowledge work? I saw a post recently asking whether AI will replace junior Scrum Masters. That question itself is not new. But it triggered a realization I had not connected this way before. And it is not very

Code Is No Longer the Bottleneck. Now What?

An advantage that everyone has is not an advantage. Agentic tools handle boilerplate, tests, and even non-trivial features. If your bottleneck was implementation speed, it's gone. Yet Amdahl's Law still applies: the speedup you get from accelerating one part is limited by the parts that don&

AI does not fail because of models. It fails because of governance.

A 2025 BCG analysis cited by Business Insider suggests that only around 5% of companies extract meaningful value from AI investments. The rest experiment, present, and absorb cost. The instinctive explanation is technical immaturity. Models are new. Tooling evolves quickly. Talent is scarce. That explanation is convenient. The DORA 2025

Read more

Risk Management under Real Velocity: Push Detection Downstream, Limit Blast Radius

AI and the missing first step in learning

Code Is No Longer the Bottleneck. Now What?

AI does not fail because of models. It fails because of governance.

Cookie Settings