What is agentic engineering?

With the rapid growth of artificial intelligence (AI) and AI agents, using generative AI for building software has become a default part of the standard software development workflow. In Stack Overflow’s 2025 Developer Survey, it was found that 84% of respondents use or intend to use AI-assisted programming in their development process.¹

However, the survey also shows more developers distrust the accuracy of AI tools than trust them, with 46% expressing skepticism compared to 33% who feel confident in the results.

Only a small share (3%) says they “highly trust” AI‑generated output. Seasoned developers are especially wary, reporting the lowest rate of “highly trust” (2.6%) and the highest rate of “highly distrust” (20%).¹ This pattern highlights a broad expectation that human oversight remains essential, particularly for roles with significant responsibility.

In practice, developers use AI for tasks that are time-consuming but relatively low risk when guided by an experienced human reviewer. This action includes tasks such as code refactoring, generating boilerplate code and tests, performing lightweight code reviews, drafting documentation, scaffolding APIs and other low risk tasks.

To recap, vibe coding allows developers to automate and prototype quickly with a few natural language prompts using large language models (LLMs) or agentic systems.

The word “vibe” in the term “vibe coding” has a casual, improvisational connotation. While this framing was well‑suited to the early, exploratory phase of AI‑assisted programming, it clashes with the current reality of developers’ skepticism toward AI coding agents.

Without the proper expertise in using LLMs for software engineering purposes, vibe coding can produce what is called “AI slop”—code that is not useful or breaks existing code. Such broken code often increases the technical debt of engineering teams with much of their time spent understanding, debugging and refactoring the code.

Alternatively, the term “agentic engineering” is detailed by Karpathy on X in a different way:

• “Agentic”: An orchestration of agents writes the code, and the human developer oversees and validates the output. As the agent or multi-agent system iterates through the subtasks, we maintain a human-in-the-loop.
• “Engineering”: There is a level of expertise required to use agentic workflows for meaningful code production that does not jeopardize the code quality. This skill is one that can be developed and improved.

Agentic engineering allows us to shift away from deterministic logic toward the nuanced territory of probabilistic judgment. Hence, it requires a fundamental shift in how organizations think and how engineering teams operate.

This process begins with establishing clear governance frameworks that define when and how agentic workflows should be used, ensuring human oversight remains central to quality control. Engineering teams should be trained not just in prompting, but in system design. Learning how to orchestrate autonomous agents, validate their output and integrate iterative review loops into existing CI/CD pipelines is critical.

Well-designed agentic systems break tasks into smaller modules, enabling agents to generate self‑contained components in real-time that integrate cleanly into the existing codebase without increasing technical debt. Many organizations are also adopting RAG‑based architectures, so agents can ground their output in real documentation, specifications and code repositories, reducing hallucinations and improving accuracy.

Organizations can also develop internal playbooks that standardize patterns for safe agent usage, including code‑review requirements, testing expectations and guardrail configurations. Providing engineers with examples of successfully deployed agentic AI systems for various use cases can provide a helpful starting point.

Finally, leadership must foster a culture that encourages experimentation while maintaining accountability: agentic systems should accelerate development, not replace software engineering expertise. In doing so, organizations can integrate agentic engineering in a way that strengthens productivity and uplifts developers without compromising trust or code quality.

As the landscape of AI‑assisted software development continues to evolve, its terminology will likely continue to shift as well. While “agentic engineering” provides a more mature and accurate framing for how developers collaborate with autonomous systems today, the practices behind it will continue to advance as AI agents become more capable. In the coming years, we can expect agentic systems to handle increasingly complex tasks.

At the same time, the role of developers will evolve from simply writing code to designing, supervising and shaping the behavior of these AI systems. Whether you are an AI engineer, full‑stack developer, data scientist or someone beginning your coding journey, the core principles or human oversight, system design literacy and high‑judgment decision making, will remain foundational.

If you’re feeling unsure about where to begin, start small. Explore one agentic workflow, whether open source or enterprise-grade, test it with your team and see what’s possible.