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.
Hallucinated or ignored tool results
4 of 4 quotes
“Delegate is still hallucinating functions causing it to timeout”
GitHub, ag2 · 22 June 2026 · open the thread “the LLM correctly invokes a tool (tool call is successful), but it appears unable to interpret or process the tool's result.”
LangChain forum · 31 December 2025 · open the thread “when the model hallucinates a tool that is not hooked into the tool list, and platforms SDK fails and raises an exception, causing teardown of the session.”
GitHub, openai-agents-python · 18 December 2025 · open the thread “I've been running AI agents in production and noticed they kept hallucinating the current date (thinking it was 2023) due to training data cutoffs.”
Hacker News · 14 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.