Fixing Broken Code
Want to back the stream? The «داعم» membership on YouTube is EGP 60 a month: badges, emoji, and I answer your questions first on stream. Become a supporter
The gist
This portion centers on developing a Shopify app and preparing it for submission, with a brand “manifesto” presented as an optional profile that can guide content personalization across the product. The discussion covers questionnaire design, terminology and approval actions, manifesto visibility, and locked research states, while pushing back on feature creep in favor of finishing backend wiring, debugging, mobile review, and compliance work. The build and final testing were not completed: upload and draft actions were tested without a documented final result, while unexpected localization behavior and a batch-update bug were identified. The speaker stresses human visual QA after each milestone because automation alone had allowed bugs to accumulate. This portion also explores coding-agent workflows, including session handoffs, multi-agent orchestration, unresolved sequential-versus-parallel tradeoffs, environment contention and wait time, and why large refactors should not be assumed to finish autonomously. Audience questions prompt cautious opinions on B2B versus B2C pricing, acquisition and conversion economics, two-sided marketplace growth, advertising-platform feasibility, and researching profitability before building. Additional discussion touches on marketing automation, learning through practice, agent-tool choices, and trying different AI models, while keeping economic claims, model-capability inferences, and interpretations of AI-policy reports explicitly uncertain or opinion-based.
65 moments from the stream
- 3:41:49
Prioritizing Fixes Before a Pull-Request Decision
The speaker asks for three unspecified items to be fixed while 11 minor issues are parked, then asks to be notified so they can decide whether to open a pull request.
- 3:42:28
Turning Workflow Instructions into a Structured Contract
The speaker proposes replacing a workflow's free-form prompt with a defined, structured contract, recording it as an important improvement for later implementation.
- 3:46:13
Monitoring an Automated Optimization Run and Finding Batch Bugs
He monitored a scheduled optimization run, waited for its result, and found that the batch update did not match expectations, marking it as a bug to fix. He also described a direction in which some application sections would operate in an automated-by-default mode.
- 3:53:51
Finishing App Wiring and Preparing for Shopify Testing and Submission
He explained that the hardest remaining work was wiring the frontend to backend logic across a small set of interdependent application areas. After that, the plan was polishing, smoke testing, testing on a real store, checking Shopify requirements, refining the mobile view, and preparing a presentation and dashboard screenshots before submission.
- 4:00:13
Using AI Agent Runtime for Parallel Work
He discussed trying side ideas while waiting for AI agents, explaining that the agents can continue working autonomously long enough for him to handle another task in parallel.
Got a question about something in this stream?
Ask in the group