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
- 0:00:52
Why a Premium Application Needs Thorough Debugging
Luqman explains that users of a higher-priced application are less tolerant of bugs, so he wants to verify the full user journey carefully and prepare the product to run with minimal intervention after launch. He also keeps the completion date uncertain as further work continues to surface during review.
- 0:02:49
A Gamified Community Workspace Around Telegram
Luqman explores a still-uncertain virtual workspace idea, partly credited to another person, where members could see what others are building, ask questions, present work for feedback, and follow progress toward shipping in a more engaging way.
- 0:04:17
Reviewing Coding-Agent Changes After a Merge
Luqman describes leaving a coding agent to make manifesto changes, then reviewing whether those changes work after merge and deployment. The server appears unavailable during the check, so he asks for it to be revived and for the manifesto state to be verified before testing; this page does not confirm a resolution.
- 0:05:49
Turning the Community-Space Idea into a User Flow and Execution Plan
Luqman asks for a concise user-flow description beginning with opening Telegram, then considers avatar customization for engagement and chooses a crew-oriented concept with room for personalization. He requests that the brainstorm be consolidated into a broad execution plan that can evolve during building and review.
- 0:11:01
A Separate Note-Taking Session for QA Walkthroughs
Luqman asks for a separate session that acts as a QA copilot without editing code. Its main role is to take notes during application walkthroughs and receive the bugs he spots so they remain organized.
- 0:13:41
Hands-On Checks of Manifesto Generation, Editing, and Export
Luqman begins testing the manifesto-draft logic while noting issues, expects the loading dialog to close within seconds, and watches the wait time. He then notes the newly added tap-to-edit feature, checks the PDF download, and observes that the generated result is longer than the earlier version.
- 0:17:31
Turning a User Manifesto into Editable Internal Instructions
Explains that the user's manifesto is read and transformed into an internal system prompt that the user does not see, while testing full-manifesto download and narrative editing for a cleaner result.
- 0:19:50
Capturing Bugs and Feedback During Testing
Hands-on testing surfaces several bugs and feedback items, with an intent to record and address them as they appear. The segment also tests another coding model, but its name and version are not clear enough to state confidently.
- 0:22:25
Preferring Explicit Control Over Agent Execution
The speaker dislikes Claude beginning work without an explicit instruction, reflecting a preference for clear control over when an agent starts executing.
- 0:26:46
Prioritizing Backend Wiring and UX Over UI Polish
While collecting bugs and feedback, the speaker says UI polish is not the current priority; the more important work is backend wiring and the user experience.
- 0:28:25
Regenerating the Manifesto and Finishing Through Debugging
He asks to delete the current manifesto so a new one can be generated, then says the application flow is essentially complete and the UI is close, while debugging remains the main task because a paid product needs to feel clean and reliable.
- 0:30:09
AI Codebase Review and Keeping Debugging in Scope
The speaker describes asking Claude for a candid, codebase-wide review against defined quality criteria, while acknowledging that later debugging will still be necessary. He also notes that generating new feature ideas during debugging creates distraction and delays, so he wants to finish the core work first.
- 0:32:55
Concept for a Virtual Project-Status Desk
The speaker outlines an early mock-up for a “desk” where members could present projects, explain current problems, and show what they are working on now or planning next. It might optionally connect to GitHub to display activity and updates and allow materials such as videos to be shared, but the concept remains exploratory and is being considered as a Telegram app prototype.
- 0:39:18
Music Copyright Risks in YouTube Streams
The speaker discusses the possibility that copyrighted background music in a YouTube stream could trigger copyright strikes and potentially affect the channel, and considers using calmer background audio. He remains uncertain about the copyright status of particular songs or artists.
- 0:42:32
Cheb Khaled and Algerian Music
A brief discussion describes Cheb Khaled as an internationally known Algerian artist, while the speaker qualifies that his familiarity with Algerian music is limited and that he rarely listens to songs.
- 0:43:28
Manifesto Progress-Bar Notes
Initial notes identify a bug in manifesto approval, call for adjusting and resetting the progress bar, and briefly mention click behavior; the exact interaction details are unclear in the captions.
- 0:45:40
Testing Manifesto Generation for a Shopify Development Store
A test evaluates whether a manifesto-generation system can understand the context of a Shopify development store that supposedly sells snowboards, respond flexibly and creatively to its fields, and handle market choices such as the United States and Canada before its output is reviewed.
- 0:52:34
An Impression of Algerian Music’s Distinctive Style
The speaker expressed strong personal appreciation for the melody and romantic lyrics, and felt that Algerian music has a notably distinctive style.
- 0:55:27
Improving the Manifesto Generation Experience on Web and Mobile
The speaker reported that manifesto generation takes about one minute and twenty seconds and proposed staged progress intervals instead of a long pause near completion. He also identified a major post-generation CTA issue: it appears compressed and redirects to the home page or dashboard. Additional feedback called for slightly slower walking motion and a closer default view of the avatar on mobile, while still allowing users to zoom out.
- 1:05:44
Learning Programming in the Age of AI-Assisted Development
Responding to a question about needing a computer-science background, the speaker said he began without a programming background and learned many concepts through AI-assisted development. In his view, logical thinking and database structures can be learned through practice, while mastering programming languages requires deeper study. He argued that effective AI use can narrow part of the gap between a novice and an experienced programmer, though developers who combine programming expertise with serious AI adoption retain a strong advantage. He advised choosing between broad fundamentals, a specialty such as cybersecurity, and deep language study according to the person’s actual goals and ambitions.
Got a question about something in this stream?
Ask in the group