Building AI with AI

2025-11-15 · Source: Explosion · Developer tools and consulting for AI, Machine Learning and NLP - Explosion.ai · Field: Technology & Digital — Artificial Intelligence & Machine Learning, Software Development & Engineering · Depth: Intermediate, quick

Summary

AI-powered coding assistants have fundamentally reshaped software development practices and the evolution of artificial intelligence itself. A recent talk by Ines highlights a critical shift in perspective regarding Large Language Models (LLMs). The presentation advocates for utilizing LLMs primarily as powerful tools to construct more complex and robust software systems, rather than deploying them as standalone, end-user systems. This approach underscores the enduring and even increasing significance of traditional code, asserting that its role is amplified, not diminished, by the advent of advanced AI. The discussion emphasizes that while AI assists in creation and accelerates development, the underlying programmatic logic remains central to building sophisticated, reliable, and maintainable AI-driven applications.

Key takeaway

For AI Engineers building new applications, recognize that LLMs are powerful development accelerators, not complete solutions. You should focus on integrating LLMs as components within larger, well-coded systems, rather than relying on them as standalone products. This approach ensures maintainability and robustness, making your foundational code more critical than ever for defining system logic and behavior. Prioritize strong software engineering practices alongside AI integration.

Key insights

LLMs should be used to build systems, not as systems, reinforcing code's critical role.

Principles

• LLMs are system-building tools.
• Code's importance is amplified by AI.
• AI assists, but code defines logic.

In practice

• Integrate LLMs into development workflows.
• Focus on robust code for AI systems.
• Design AI as a component, not a monolith.

Topics

• AI Coding Assistants
• Large Language Models
• Software Development
• System Architecture
• Code Quality

Best for: Machine Learning Engineer, AI Engineer, Software Engineer, AI Architect

Related on AIssential

• Step-by-Step Guide to Building AI Agents Using LLMs — LLM-powered AI agents enable advanced automation by understanding language, reasoning, and interacting with systems autonomously.
• Top AI coding tools make mistakes one in four times, study shows — New research from the University of Waterloo indicates that artificial intelligence (AI) continues to struggle with fundamental software development tasks, prompting concerns about the reliability of…
• Components of a Coding Agent: How LLMs Become Software Engineers — Coding agents transform LLMs into dynamic, multi-step problem solvers through structured system design.
• Our New Agentic AI Engineering Course! — Building production-ready AI agents requires extensive engineering beyond basic LLM calls.
• The Must-Know Topics for an LLM Engineer — LLM engineering requires understanding an interdependent stack, from data representation and model architecture to training, optimization, and evaluation.
• Most Influential ArXiv (Software Engineering) Papers (2026-04 Version) — LLMs and AI agents are rapidly transforming software engineering, driving innovation in code generation, testing, and repair.

Open in AIssential →

Editorial summary, takeaway, and curation by AIssential. Original article published by Explosion · Developer tools and consulting for AI, Machine Learning and NLP - Explosion.ai.