Velu shares an AI agent pipeline for writing help centers
Understand this story
Velu shared a seven-stage AI agent pipeline that, using only a product URL and login credentials and without access to the code repository, can automatically generate a help center with images, text, and short videos. According to Velu's description, the research stage uses Haiku to record the interface and button behavior screen by screen to form a map; writing and planning switch to Sonnet, and tasks are split so that each page has one parallel writing agent, making cost grow linearly with the number of pages; a separate editing agent reviews each page's content according to the rules in SKILL.md.
AI overview based on source reports · Updated 3 days ago
Coverage timeline
Follow the coverage to explore different perspectives.
- Hacker News AIHow Our AI Agents Write a Help Center
Velu describes building a help center generator that needs only a web address and a login, not source code access, by having agents use the product the way a new employee would. The system evolved from a single agent into a seven-phase pipeline—research, planning, writing, editing, mock data, screenshots and videos, and publishing—splitting work whenever an agent grew too large. Haiku handles high-volume simple browser work while Sonnet handles planning, writing and editing, with an editor's rules stored in a customizable SKILL.md.
Activity for this story
- Current comparable activity
- 3
- Peak comparable activity
- 10Nov 4 03:00
- Change in the past 24 hours
- -50%
Trends compare the same fully observed participants, which may cover fewer participants than current activity. Move the pointer or tap the chart to inspect hourly activity; use the left and right arrow keys with a keyboard.