Pain map
What breaks in document AI
290 production incidents from public threads. Every quote links to its source. Pick a category and check it yourself.
Months spent on the foundation
3 of 3 quotes
“Over the last few weeks I've been redesigning the retrieval pipeline for an AI knowledge system.”
Hacker News · 16 July 2026 · open the thread “I've spent the last few months building a document analysis tool and the amount of friction involved in trying to make cloud-based RAG pipelines 'durable' vs just keeping the state in local SQLite is night and day.”
Hacker News · 30 May 2026 · open the thread “I found that making this legally defensible and operationally stable required about 40+ additional components.”
Hacker News · 17 December 2025 · in production · open the thread Hit this one too? We are building for it. Join the waitlist.
Method
We collected 448 public posts published after 1 November 2025 in which a builder describes document AI failing. Each link was re-opened on 8 November 2026. We kept the 290 where the quote is on the page, the author describes an incident and not an opinion, and has no tie to a vendor. Quotes are verbatim and trimmed after 420 characters. The grouping is ours. A complaint is not a measurement.