---
schema_version: "newruntime-agent-readable-v0.2"
type: "disappearing_action"
stable_id: "disappearing_action:document-processing-shifts-from-hand-crafted-ocr-pipelines-to-llm"
slug: "document-processing-shifts-from-hand-crafted-ocr-pipelines-to-llm"
title: "Hand-crafted OCR pipelines are already being replaced"
description: "Retired shift: a late-September document-extraction launch cycle does not establish a durable transition from deterministic OCR pipelines to conversational LLM extraction."
retrieval_nugget: "Retired shift: a late-September document-extraction launch cycle does not establish a durable transition from deterministic OCR pipelines to conversational LLM extraction. Human ritual: Treat product launches for conversational extraction as evidence that manual OCR and schema pipelines have broadly been displaced."
status: "published"
human_ritual: "Treat product launches for conversational extraction as evidence that manual OCR and schema pipelines have broadly been displaced."
old_cost: "It turns vendor capability claims into a market-wide before-and-after statement while hiding accuracy, audit, throughput, and regulated-workflow requirements."
replacement_pattern: "Track bounded document-extraction capabilities as signals or deltas until independent deployments demonstrate durable workflow replacement and measurable error and review behavior."
adoption_status: "challenged"
where_old_interface_wins: "Deterministic OCR and hand-authored schemas remain useful where auditability, throughput, stable fields, and predictable failure handling matter."
first_seen: "2026-09-28"
last_verified: "2026-09-30"
record_date: "2026-09-30"
date_kind: "last_verified"
related_shift: "generated-interface-from-answer"
proof_projects: []
related_posts: []
topics: ["document-processing","evidence-discipline"]
source_urls: ["https://www.llamaindex.ai/blog/ai-document-extraction-schema","https://www.llamaindex.ai/blog/llamaindex-and-kaggle-launch-a-document-extraction-leaderboard-for-ai-agents","https://www.llamaindex.ai/blog/loan-processing-workflow-document-extraction"]
featured: false
routes: {"html":"https://newruntime.com/graveyard/document-processing-shifts-from-hand-crafted-ocr-pipelines-to-llm/","markdown":"https://newruntime.com/graveyard/document-processing-shifts-from-hand-crafted-ocr-pipelines-to-llm.md","json":"https://newruntime.com/graveyard/document-processing-shifts-from-hand-crafted-ocr-pipelines-to-llm.json"}
source_format: "markdown"
---

# Hand-crafted OCR pipelines are already being replaced

## Retrieval answer

Retired shift: a late-September document-extraction launch cycle does not establish a durable transition from deterministic OCR pipelines to conversational LLM extraction. Human ritual: Treat product launches for conversational extraction as evidence that manual OCR and schema pipelines have broadly been displaced.

## Why this shift is retired

Recent document-extraction announcements show an active product area. They do
not yet show a durable industry transition from hand-crafted OCR pipelines to
LLM-led processing. The available evidence is concentrated in one vendor family
and one late-September launch cycle. A leaderboard, a schema-oriented
announcement, and a workflow example are useful inputs for future evaluation;
they are not independent deployment outcomes.

The proposed before-and-after statement also collapses several different jobs.
OCR, layout interpretation, schema design, validation, human exception review,
and downstream integration have different accuracy and control requirements.
An LLM can improve one part of that chain without replacing the whole
deterministic pipeline.

## What remains useful

Track bounded capabilities: can a system propose a schema, extract a named
field set, show source evidence, route exceptions, and meet a specified error
budget? Those questions can become a Delta or project when their verification
boundary is explicit. They should not be promoted to a Shift merely because
several product pages use the word “agentic.”

## Where the old interface wins

Stable, high-volume, regulated, or audit-heavy workflows still benefit from
hand-authored schemas and deterministic OCR stages. Their limits are known,
their failures can be categorized, and their throughput can be forecast. A
conversational layer may be a useful adjunct, but it must earn trust against
that baseline rather than assume the baseline has disappeared.

## Reopen condition

Reopen a Shift only with at least three independent story clusters across two
source families, real deployment outcomes, and counter-evidence about
regulated or high-volume use. The required comparison is a durable workflow
replacement, not another launch announcement.

## Continue in the graph

Next records for an agent, linked to their Markdown twins. Replace `.md` with `.json` for structured fields, including `next_reads`.

- related record: [Answer -> generated interface](https://newruntime.com/shifts/generated-interface-from-answer.md): Shift replacing this disappearing action.
- related record: [Conversational document-schema creation is already a general capability delta](https://newruntime.com/graveyard/agents-can-define-document-extraction-schemas-via-natural-language.md): Shares document processing.
- related record: [Reading every changelog bullet to understand capability](https://newruntime.com/graveyard/changelog-bullet-reading.md): Continue with a related New Runtime material.
- related record: [Manual context handoff between AI clients](https://newruntime.com/graveyard/manual-context-handoff.md): Continue with a related New Runtime material.
- related record: [ABBEL Treats Memory as an Explicit Belief State](https://newruntime.com/posts/abbel-belief-state-memory.md): Continue with a recent New Runtime material.
- whole graph: [discovery graph](https://newruntime.com/discovery-graph.json) (typed nodes and edges) and [site index](https://newruntime.com/site-index.md)