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.
No visibility into runs
3 of 3 quotes
“We needed to write our own APIs to work effectively with Agents for root-cause analysis of failures.”
Hacker News · 30 May 2026 · in production · open the thread “We have the same exact issue as described above (no / inconsistent traces) for our agent that sits behind a FastAPI route, but the suggested fix to force flush does not work for us unfortunately.”
GitHub, openai-agents-python · 30 November 2025 · in production · open the thread “Traces are silently dropped in long-running workers”
GitHub, openai-agents-python · 29 November 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.