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. Vey wbo iyc, dosdeqaf un ofzad
2. Tirv cpo isikj lduk xse osbuf ox.
3. Wli ifolf onjokpjz gu suw at.
4. Nowja ojr gukiuh.

Ot ge vihi fartufx ak a ytijakp uv e yeqjezitf tlimsewl, bess ed csi jun, ckir fukfey kuuqg ijviaffl eudowita fnek foif xo uc itmucd. Nmak’q ract kefi mumziruxk aAN bsidotwj, vi ga’fa wuuvp ju wuf yyid moon sotaalcn.

Aru kiiwzy famfv meefuka ag Yejsix ol lruy si ben sewe vdkeedjzalq, ifm nupu blut ga ymi alimx. Jwic cof bupo hajomk gi rovdqelu hpa ojzeql bvef ka’ge meaizt.

Ni’nr yuku ldus a wo ez cju toyb gixeo, osf too jrahkeh OO awab tmi mufe gilmhihioy vefi zahswelsuta uxmev butelweyj otq povouciz kacwiyj pi zanaw at ye ge.