Code Driven Manifesto
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
The stream centers on an unfinished hands-on review of Burnish and its Code Driven Manifesto workflow: generating, editing, and exporting a manifesto; turning it into internal instructions for the storefront, articles, visibility, reputation, and discovery; and considering how its status and Autopilot integration should appear. Testing surfaced issues with generation, progress, navigation, state updates, scoring, auto-publishing, and background jobs. Some next-batch logic appeared to work in one attempt, but critical bugs and questions about cancellation, timeouts, concurrency, and persistence remained under investigation. Luqman emphasized backend wiring, user experience, and debugging before interface polish, arguing that premium-positioned software needs commensurate reliability while acknowledging that no launch can eliminate every bug. Other discussions covered an exploratory Telegram community workspace, audience questions about learning programming with AI and the advantage of experience, uncertain opinions about coding-tool quality, pricing, and context capacity, and acquisition and retention measurement without invented figures, plus shorter conversations about YouTube music copyright, Algerian music, personal goals, and screen-use glasses.
85 moments from the stream
- 5:11:51
Structuring a System Prompt into Domain Sections
The discussion proposes organizing one system prompt into targeted sections for areas such as the storefront, visibility, reputation, and discovery, so a task can use the relevant section instead of reading the entire prompt. It is raised as a design question that still needs confirmation in the plan.
- 5:14:10
An Inconclusive Comparison of AI Model Tiers
The speaker informally compares pricing across professional and standard tiers and competing AI models, repeatedly stressing uncertainty about the actual prices and size of the differences. Some tier names and figures in the captions are unclear, so they are not treated as verified facts.
- 5:20:49
Structuring CLAUDE.md and brand-specific instructions
The discussion proposes keeping always-needed core context in CLAUDE.md while organizing detailed instructions for areas such as the storefront, visibility, and articles. It also raises the risk of conflict between an existing system prompt and instructions extracted from a brand manifesto, calling for a clear conflict-resolution approach.
- 5:29:22
Combining unit-economics research with backend development
A workflow combines estimates around costs, pricing, and conversion with market research through Perplexity and ongoing backend implementation. The discussion notes that the work becomes difficult to follow when the application's purpose and backend behavior have not been explained clearly.
- 5:32:32
Explaining a complex application without getting lost in backend details
A reflection on explaining an application with many nested parts: a comprehensive mind map became overwhelming because of its size, while the initial focus on frontend work, wiring, and auditing did not fully account for the backend workload. Debugging then made both progress and explanation more difficult.
Got a question about something in this stream?
Ask in the group