14 Days of Intensive “Agentic Coding”: What I Learned from Working with IBM Bob, an Agentic IDE

This post shares lessons from a 14-day engineering project using IBM Bob’s Agentic IDE. It is not a product review or benchmark, but a personal experience report about how intensive Agentic Coding changed the author’s engineering behavior. A central observation is the “Navigation System Syndrome”: as trust in the Agentic IDE increased, the author worked at a higher abstraction level and inspected fewer implementation details. The post explores why continuous specification management, verification, documentation, observability, Engineering Provenance, and human responsibility remain essential when AI becomes a more capable part of software engineering.

0

From Idea to Responsibility: Why AI Coding Needs Engineering Provenance

AI coding agents increasingly participate in planning, implementation, review, testing, and documentation. This raises a new engineering question: who actually created the software artifact? This post explores why Git history alone is no longer sufficient, how engineering provenance could capture the role of humans, agents, models, tools, and context, and why this matters for intellectual property, accountability, and risk. The broader shift may no longer be from coding to review, but from idea to responsibility.

0

AI generated Podcast Episode: AI Coding Assistants, Agentic IDEs, and Privacy: From Chatbots to Operational Systems

The AI generated explores the complexities of privacy in the context of AI coding assistants and agentic IDEs. It emphasizes that privacy is now a structural choice within development environments rather than a simple policy acceptance. The effectiveness of six platforms is assessed based on their privacy features, highlighting trade-offs between integration, cost, and data handling.

0

Prompting Cheat Sheet for Local LLMs and Autonomous Agents

This post shows the importance of clear prompt structure when developing local AI agents with frameworks like LangGraph and Ollama. Smaller models are less tolerant of ambiguities, making it crucial to separate instructions, context, and output formats. This enhances reliability, debugging, and reduces risks from untrusted inputs.

0

AI generated Podcast Episode: AI Decision-Making: Who’s Responsible When Things Go Wrong?

The blog post by Thomas Suedbroecker addresses the evolving governance challenges as AI becomes an active participant in engineering decision-making. It highlights the shift from human-centric to AI-assisted development and the resulting review gap. The author proposes specialized governance structures and emphasizes the importance of traceability for accountability in automated environments.

1

Blog at WordPress.com.

Up ↑