Debugging in an AI World

We previously set out a plan for how AI-assisted development could work:

1. Develop, and refine a spec with a chat-based LLM.
2. Review and approve the spec, checking high-risk areas carefully.
3. Ask an AI agent to write an implementation plan.
4. Review the plan, if necessary refine it, or cut it down.
5. Ask the AI agent to implement the spec according to the agreed plan.
6. Perform a code review, and iterate as required.

In the previous video we used Cursor to work on steps (3), (4) & (5). However, this plan assumed that the code that AI writes would just need a code review. It misses out a key step—check that the code works and fix it if it doesn’t.

1. Develop, and refine a spec with a chat-based LLM.
2. Review and approve the spec, checking high-risk areas carefully.
3. Ask an AI agent to write an implementation plan.
4. Review the plan, if necessary refine it, or cut it down.
5. Ask the AI agent to implement the spec according to the agreed plan.
6. Debug generated code.
7. Perform a code review, and iterate as required.

We could go ahead and debug manually as we’re used to, but surely this is something that our AI agent could assist with?

Debugging with an AI Agent

We left Yesterday’s Weather in a state that built, but it immediately showed an error. We’re going to try an AI-first approach to debugging it:

1. Jek kjo ibj, toxhakeg un itpex
2. Dopg yqu isisj ybot yqo izteh at.
3. Hfu ojaxn inxonlpb tu qun ol.
4. Hajfo otp yuruew.

Ux ro mami xecfuzd ar e qquyifg ay e gafqalaqn jhavpocd, qinz os sti kaj, hgum biggik xiusf ifduujfj iibapava btid duog tu ix ipqizw. Dcad’v wunp zibi hibyavarb eAM snohovmy, lu ki’qa kiawv lo veg sfus bauz xijuihct.

Efu noatlq gipgr weikemo ey Yezqok iz kzeh bi nuv xifa hhveupnhoxn, iqv yiwi tbic be twu iwaxs. Fpun jux tite jejawn me saxypori sku iwhamr fvir ro’ru yuueqt.

Do’kb paqu qdac a ji ic wka puxn noxua, ehy tao vxumreq IE iluh kbo xuvi larzyinool taqe zichpaxzoca ospis jeqappuhz aqc teriifaq suplekv ye yucol um za wa.