Meet the Swarm
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
A wide-ranging, practical stream about building AI products in public. Its strongest thread is the shift from short tasks to long-running “missions” pursued by agent swarms, supported by a control center and living roadmap that expose progress, quality, and blockers. Luqman discusses requirements documents and system design as foundations for greater agent autonomy, splitting work between Codex, Claude, or specialized models, and measuring real cost per completed task rather than advertised token prices. These are presented as concepts, early experiments, and personal judgments—not settled results. Practical activity includes reviewing an interface and identifying a scrolling bug, requesting an interactive mock to clarify the design direction, and beginning an application walkthrough by granting access to a sample project and requesting a quick capability test. The stream also discusses web testing and continuous monitoring, with the explicit caution that agent-driven UI checks do not prove scalability. Audience questions broaden the stream to RAG and learning resources, context compaction, usage limits and tool handoffs, handwriting OCR, reviewed data-entry automation, and disclosed AI assistants for social engagement. It also covers app frameworks and community platforms, product validation, free-plan pricing, distribution and sales, SEO, ads, direct outreach, freelancing, and uncertain effects of AI on jobs and SaaS. Open questions remain around Mission Control’s interface architecture, subagent concurrency, the value and cost of bridging models, and whether several proposed integrations and workflows will work in practice. The supported conclusion is that documentation quality, low-friction onboarding, human oversight, realistic usage measurement, and distribution matter at least as much as model capability; many demonstrated products and workflows remained exploratory or unfinished.
124 moments from the stream
- 6:16:36
Managing Claude Code Context with /compact
After a suggestion to start fresh chats when context grows unwieldy, the speaker demonstrates that Claude Code’s /compact command can summarize the session and retain brief instructions for continuing with a lighter context, optionally guided by custom compaction instructions.
- 6:18:42
Compacting Coding-Session Context and Codex’s Limits
The speaker explains that compacting context and reusing a brief or instructions in a new session may improve precision and reduce session sprawl. After a quick check, he tentatively concludes that Codex offers automatic compaction only, while custom compaction instructions remain uncertain.
- 6:22:00
A Channel Format for Building AI Applications in Public
The speaker describes the channel as live streams that openly document the end-to-end journey of building AI applications and attempting to bring them to market.
- 6:23:02
A Living Roadmap for Tracking Autonomous Work
The speaker argues for a visual roadmap showing the current position, milestones, and completed and active tasks. As autonomous agents may work for days, the roadmap should be connected to execution steps and updated continuously—for example by counting completed tasks and displaying progress—instead of remaining a static snapshot.
Got a question about something in this stream?
Ask in the group