From autocomplete to agents

The first wave of AI coding tools completed lines and functions. The current wave plans and executes multi-step tasks — reading a codebase, writing code across several files, running tests, and iterating on failures with limited supervision. That’s a change in kind, not just speed: the unit of work an AI touches has grown from a line to a feature, and the human’s job has shifted from typing to reviewing and directing.

Standardized plumbing is enabling standardized agents

Protocols like MCP are doing for AI tool access what REST and later GraphQL did for web APIs: turning bespoke integration work into a shared, reusable layer. That standardization is what makes it economical to build agents that reach into real systems, rather than agents that only talk. See our companion piece on what MCP actually is.

The bottleneck has moved, not disappeared

Code generation was rarely the actual constraint on software delivery — requirements clarity, architectural judgment, and review capacity were. AI tooling makes the easy 80% of implementation faster, which means the remaining 20% — the ambiguous requirements, the cross-system trade-offs, the “is this actually the right thing to build” conversations — is now a larger share of where a team’s time goes.

What we’d actually bet on

• Brownfield-aware AI coding practices becoming table stakes, not a specialty (see our piece on brownfield vs. greenfield).
• Agentic workflows handling more internal, reversible work before they’re trusted with customer-facing actions.
• Governance — audit trails, approval gates, rollback paths — becoming a normal line item in AI project scope.
• Model and provider choice being treated as a swappable architectural decision rather than a permanent commitment.

Summary: None of this requires believing AI will write all the code or none of it. It requires paying attention to where the actual mechanism has changed, and building the engineering discipline around it before the incidents force the issue.

#AI #SoftwareDevelopment #AgenticAI #FutureOfWork #SazkoSolutions

Published by Sazko Solutions – Driving Innovation in AI-Powered Software Delivery

The post The Future of AI in Software Development: What’s Actually Changing appeared first on Sazko Solutions.

What formal verification actually gives you

Ordinary testing checks the cases you thought of. Formal verification proves a property holds for all possible inputs — no counterexample exists. The catch has always been cost: writing those proofs by hand is slow, specialised work, so it’s reserved for avionics, cryptography, and a handful of other domains where failure is catastrophic.

Why AI assistance changes the economics

If a model can draft a proof that a human then checks and refines, the cost of verifying a critical component drops. That potentially widens the set of software worth verifying — payment logic, access control, safety interlocks — beyond the domains that can currently afford it.

The realistic near-term picture

• Verification stays expensive and specialised, just less so.
• The model drafts; humans still own correctness and the specification itself.
• The hardest part remains writing a specification that actually captures what “correct” means — AI doesn’t remove that.

Summary: AI-assisted formal verification won’t make every system provably correct. It might make it affordable to prove the handful of components where a bug is unacceptable.

#AI #FormalVerification #SoftwareEngineering #CriticalSystems #SazkoSolutions

Published by Sazko Solutions – Driving Innovation in High-Assurance Software

The post Formal Verification Meets AI: Why Machine-Checked Proofs Matter for Critical Systems appeared first on Sazko Solutions.