
Jev, OpenAI, and the Shift Towards Decision AI
I started by asking what Jev actually built. A four-subagent RAG example brought the opportunity into focus: useful decisions need useful context and software that knows what to do next.
Kingsley Ijomah
AI Adoption Lead · Gravity9The person behind Codehance
I lead AI adoption and engineering initiatives at Gravity9, backed by more than 15 years of building software across complex, real-world environments.
I built Codehance to share my journey through the three layers of AI: using AI, working with AI, and building AI. It’s an open notebook for anyone curious about how AI changes the way we think, work, and create.
Codehance is my personal project. The views and experiences shared here are my own and do not represent Gravity9 or its clients.
Fresh from the notebook
Ideas, patterns, and lessons drawn from real agentic systems and delivery work. Shared so you can apply them in your own context.

I started by asking what Jev actually built. A four-subagent RAG example brought the opportunity into focus: useful decisions need useful context and software that knows what to do next.
Kingsley Ijomah

The valuations attached to frontier-model companies will not rise forever. If they correct, the useful question for engineers is not whether AI disappears, but which parts of the stack remain worth understanding.
Kingsley Ijomah

I keep hearing the same reaction around AI-heavy meetings: people leave tired, confused and unsure what was decided. The problem is not simply new terminology. It is what happens when teams discuss an AI solution before agreeing on the business problem.
Kingsley Ijomah
Your place at the table
You don’t need “AI” in your job title—or any particular job title. Bring the work you do and the questions you have.
Build a clear mental model of AI and find useful ways to bring it into your everyday work.
Move from autocomplete to agentic delivery without giving up engineering judgment.
Shape work that humans and agents can execute together, then introduce AI responsibly across teams.
Explore without needing an AI job title, a technical background, or all the answers.
Keep growing
No guru theatre. No fear of being behind. Just practical notes, honest experiments, and better ways to work with AI.
Start reading