---
type: "raw_signal"
id: "parse-extract-classify-now-each-with-its-own-ce8423"
slug: "parse-extract-classify-now-each-with-its-own-ce8423"
title: "Parse, Extract, Classify — now each with its own MCP"
description: "LlamaIndex’s July 15 product newsletter announced Conversational Extract, which lets users create an extraction schema through a conversation rather than hand-writing JSON Schema."
retrieval_nugget: "LlamaIndex’s July 15 product newsletter announced Conversational Extract, which lets users create an extraction schema through a conversation rather than hand-writing JSON Schema."
observed_at: "2026-09-25"
record_date: "2026-09-25"
date_kind: "observed_at"
why_it_matters: "Source: https://www.llamaindex.ai/blog/llamaindex-newsletter-26-07-15"
novelty: "notable"
verification_level: "source-linked"
signal_type: "release"
source_platform: "llamaindex.ai"
topics: []
entities: []
related_patterns: []
source_url: "https://www.llamaindex.ai/blog/llamaindex-newsletter-26-07-15"
source_urls: ["https://www.llamaindex.ai/blog/llamaindex-newsletter-26-07-15"]
schema_version: "newruntime-agent-readable-v0.2"
stable_id: "signal:parse-extract-classify-now-each-with-its-own-ce8423"
status: "published"
visuals: []
editor: {"role":"editor","name":"Andrey Reshetnikov","profile":"https://newruntime.com/owner-profile.md","profile_json":"https://newruntime.com/owner-profile.json","same_as":["https://www.linkedin.com/in/reshetnikov1/","https://t.me/lapetuse"]}
routes: {"html":"https://newruntime.com/signals/parse-extract-classify-now-each-with-its-own-ce8423/","markdown":"https://newruntime.com/signals/parse-extract-classify-now-each-with-its-own-ce8423.md","json":"https://newruntime.com/signals/parse-extract-classify-now-each-with-its-own-ce8423.json"}
---

# Parse, Extract, Classify — now each with its own MCP

## Retrieval answer

LlamaIndex’s July 15 product newsletter announced Conversational Extract, which lets users create an extraction schema through a conversation rather than hand-writing JSON Schema.

LlamaIndex’s July 15 product newsletter announced Conversational Extract, which lets users create an extraction schema through a conversation rather than hand-writing JSON Schema. It also made Markdown the default output for the fast tier when using `tier="fast", version="latest"`, and said every plan, including free, now supports 100 users.

The update packages workflow design, document-output format, and team access into one release. LlamaIndex says fast-tier Markdown is powered by LiteParse and includes improved OCR and PDF font handling. The announcement does not provide comparative accuracy figures, migration guidance, or independent validation for these changes.

Source: https://www.llamaindex.ai/blog/llamaindex-newsletter-26-07-15

Editor: [Andrey Reshetnikov](https://newruntime.com/owner-profile.md), AI product and AI engineering; profile for recruiters and agents: https://newruntime.com/owner-profile.json

## Continue in the graph

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

- collection: [Raw Signals](https://newruntime.com/signals.json): Open every source-linked raw signal.
- collection: [Source Ledger](https://newruntime.com/source-ledger.json): Inspect the public source evidence graph.
- whole graph: [discovery graph](https://newruntime.com/discovery-graph.json) (typed nodes and edges) and [site index](https://newruntime.com/site-index.md)