Rachis

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.

  • “The issue is that checkpoint_blobs keeps growing much faster over time.”
    LangChain forum · 27 August 2026 · open the thread
  • “With `AsyncPostgresSaver` and the default `durability='async'`, pod memory grew linearly over the lifetime of a long agent run”
    GitHub, langgraph · 8 June 2026 · in production · open the thread
  • “my only problem with it was some limits on request payload or event sizes, created some inconveniences to us when building solutions.”
    Hacker News · 28 May 2026 · open the thread
  • “LLM Context window overflow that it forgets initial steps and redoes the first step after a few steps”
    LangChain forum · 26 February 2026 · open the thread
  • “The checkpoints collection is growing far beyond expected size and consuming excessive storage.”
    LangChain forum · 6 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.