# Agentic Engineering vs Software Engineering: Beyond Vibe Coding

## Executive summary

Software engineering is undergoing a fundamental shift from writing explicit, deterministic instructions to defining high-level goals and orchestrating autonomous AI agents. Agentic Engineering treats AI systems as collaborators capable of multi-step workflows, requiring the human developer's role to evolve into that of an architect who supervises, constrains, and validates probabilistic outputs rather than manually executing every task.

## Key takeaways

- The Shift in Effort: Traditional software engineering requires writing explicit instructions (deterministic logic). Agentic Engineering allows developers to define goals, while AI agents handle the execution, changing where the core engineering effort is applied.
- Defining Agentic Engineering: Agentic refers to an organization of agents that write code, while the human developer maintains a 'human in the loop' to oversee and validate the output as the multi-agent system iterates through subtasks.
- The Coding Spectrum: Coding methods exist on a spectrum based on human agency: Traditional SE (full control) $ ightarrow$ AI-assisted coding (snippets/refactoring) $ ightarrow$ Vibe coding (natural language intent) $ ightarrow$ Agentic coding (autonomous planning/execution) $ ightarrow$ Agentic engineering (designing environments for autonomous systems).
- Increased Value of Oversight: As agentic systems become more autonomous, the value of human oversight increases significantly. Engineers are now responsible not only for writing code but also for ensuring reliability across probabilistic workflows.

## Technical details

- Determinism vs. Probability: Traditional software engineering is fundamentally deterministic (same input yields same output). LLMs introduce goal interpretation, memory, tool use, and planning loops, shifting the focus from rigid logic to probabilistic judgment.
- Agentic Workflow Challenges: Because agentic systems operate probabilistically, they can make flawed decisions or hallucinate even if appearing correct. The central engineering challenge is therefore focused on orchestration and verification.
- Technical Debt Risk: While Vibe coding is excellent for rapid prototyping, without strong engineering discipline, it can quickly accumulate technical debt due to code lacking structure, testing, or architectural consistency.

## Practical implications

- The engineering bottleneck is shifting away from manually writing every line of code toward supervising, constraining, and evaluating increasingly autonomous systems.
- Engineers must develop expertise in managing reliability across probabilistic workflows rather than just mastering deterministic coding patterns.
- Teams should view AI agents as collaborators for multi-step workflows, not merely as coding assistants. This requires adopting a mindset of system orchestration.
- The process of development is evolving from direct programming to designing environments where autonomous systems can reason and adapt dynamically under constraints.

## Topics

Agentic Engineering, Software Engineering, AI Agents, LLMs, Probabilistic Programming, Technical Debt, Agentic Engineering Info, IBM AI Newsletter Signup

Source: https://www.youtube.com/watch?v=FgaBdwSvOGM