Find any clause across 500 documents in seconds
Peony's AI reads, classifies, and indexes every document the moment it's uploaded. Full-text search across PDFs, Word, Excel, and scanned files — no manual tagging, no waiting for batch processing. The search engine behind every AI feature in your data room.
How Auto-Indexing works
Full-text search on upload
Every word in every document is indexed the moment it arrives. Search across your entire data room by keyword, clause, entity name, or date — no waiting, no batch processing.
AI classification
Peony reads and categorizes every file automatically — financials, legal agreements, IP filings, corporate records. Each document is classified by what it contains, not just its filename.
Smart tagging by content
Documents are tagged by type, topic, entity, and date. AI extracts key terms, counterparty names, effective dates, and jurisdictions — making every file findable by what matters.
Cross-format search with OCR
Search across PDFs, Word documents, Excel spreadsheets, PowerPoint decks, and scanned files. Built-in OCR means even image-based documents are fully searchable.
Search everything. Find anything.
Due diligence review
Search across an entire data room. Find every reference to 'change of control' across 500 documents in seconds — not the 2-3 hours of manual searching through folders that legacy VDRs require.
Compliance audits
Auditors can search for specific clauses, dates, or entities across thousands of pages without opening a single file. Every certification, policy, and regulatory filing is instantly findable.
Large data rooms
Deals with 1,000+ files are instantly navigable. Every document is classified and searchable from the moment it's uploaded — no weeks of manual tagging before the room is usable.
Skip the manual tagging
Legacy VDRs like Ideals, Firmex, and Digify have no AI-powered search. Teams spend days manually tagging files and searching folder by folder — hoping they labeled everything correctly.
Peony indexes every document on upload. Classification, entity extraction, and full-text search are automatic — AI-powered and available on the Business plan, ready in under 5 minutes.
The engine behind every AI answer
Auto-Indexing is the foundation that powers every AI feature in Peony. Better indexing means better search, better Q&A, and faster document discovery.
"Every now and then, you come across a product that has a massive positive impact on your business. Peony is one such product."
Panos Moutafis
Founder & CEO, Zenus
Frequently asked questions
How does auto-indexing help an M&A team organize a diligence data room?
In a typical sell-side M&A process, the data room holds hundreds of contracts, financial statements, employment agreements, IP filings, and regulatory permits that bidders need to review under tight timelines. Peony's Auto-Indexing reads every document on upload and classifies it by content — tagging a supply agreement as 'Material Contract' and a lease as 'Real Property' regardless of filename. Bidder counsel can then search across the entire diligence room for a specific clause like 'change of control' or 'non-compete' and get results in seconds, instead of opening folders one by one. Legacy VDRs like Ideals, Firmex, and Digify require deal teams to manually tag and organize each file before it becomes searchable, adding days to data room setup.
Can a PE sponsor use auto-indexing to set up an exit data room faster?
Yes. When a PE sponsor prepares a portfolio company for exit, the data room typically includes years of audited financials, board minutes, cap table history, material contracts, and compliance records — often pulled from multiple systems with inconsistent naming. Peony's Auto-Indexing reads the content of every uploaded file and categorizes it by type (financials, legal agreements, corporate records, HR documents) based on what the document actually contains, not its filename. It also extracts key entities like counterparty names, effective dates, and jurisdictions, so a misspelled or generically named file still gets classified correctly. A sponsor can go from raw file dump to a fully searchable exit room in under an hour instead of the days of manual sorting that legacy VDRs require.
How does Auto-Indexing differ from AI Rooms?
Peony's Auto-Indexing is the search and retrieval engine — it indexes every word in every document for full-text search, runs OCR on scanned files, and applies smart tags based on content. AI Rooms is a separate feature for data room setup and readiness — it builds folder structures, sorts documents into folders, detects missing files, and scores completeness. Auto-Indexing makes files findable; AI Rooms makes the room organized. Both are available on the Business plan ($40/admin/month).
Can outside counsel search scanned closing binders in a Peony data room?
Yes. Law firms regularly inherit closing binders from prior transactions that exist only as scanned PDFs or even photographed pages. Peony includes built-in OCR (Optical Character Recognition) as part of Auto-Indexing, so every scanned contract, image-based PDF, and photographed document is converted to searchable text on upload. Outside counsel reviewing a post-closing matter can search across an entire binder set for a specific indemnity clause, escrow provision, or representations section — finding results in seconds rather than manually flipping through hundreds of pages. Before sharing indexed closing binders with counterparties, your team can apply controlled redaction to permanently black out privileged or sensitive information. Legacy VDRs like Ideals and Firmex either lack OCR entirely or charge extra for it.
How fast can a diligence team search across thousands of documents?
Peony indexes documents the moment they are uploaded — there is no batch processing or overnight indexing queue. In a live M&A diligence process, buy-side counsel often needs to trace a single defined term, obligation, or counterparty name across hundreds of contracts, board minutes, and financial exhibits under a tight exclusivity window. Peony returns search results in seconds across the entire data room, even with thousands of files, so a diligence team can locate every reference to a specific clause, entity, or date across 500 documents almost instantly — compared to the 2-3 hours of manual folder-by-folder searching that legacy VDRs require. All data is protected by AES-256 encryption at rest and TLS 1.3 in transit, backed by SOC 2-ready, GDPR, CCPA, and HIPAA compliance.
Does auto-indexing power other AI features?
Yes. Peony's Auto-Indexing is the foundation that powers every AI feature in the platform. AI Extraction uses the index to deliver cited answers across documents. Smart Q&A uses it to draft responses to counterparty questions. AI Rooms uses it to classify files during setup. Better indexing means better search, better Q&A, and faster document discovery across every workflow.
How much does auto-indexing cost in a data room?
Peony includes Auto-Indexing on the Business plan ($40/admin/month, 1 TB storage, 1,000 AI credits/month). Full-text search, AI classification, OCR, and smart tagging are all included — no per-document fees or per-query charges, and no per-viewer, per-page, or per-link limits. The Free ($0, 2 GB) and Pro ($20/admin/month, 200 GB) plans include 10 and 200 AI credits per month respectively. Competitors like Datasite charge enterprise pricing, while Ideals, Firmex, and Digify require manual tagging with no AI search capabilities.
What file formats can a legal team search with auto-indexing?
Peony's Auto-Indexing supports every format a legal team encounters: PDF contracts, Word (.doc/.docx) redlines and engagement letters, Excel (.xls/.xlsx) capitalization tables and financial models, PowerPoint (.ppt/.pptx) management presentations, and scanned image files via OCR — including legacy closing binders and executed signature pages. All formats are indexed identically, so a single keyword search for a defined term like 'Material Adverse Change' returns results from contracts, spreadsheets, and slide decks in the same query. This cross-format search eliminates the need to open and search files individually, which is still required on legacy VDRs like Ideals and Firmex.
Related features
Smart Q&A
Let counterparties submit questions and get AI-drafted answers your team reviews before sending.
AI Rooms
Set up data rooms faster with AI-powered folder templates, missing document detection, and completeness scoring.
Page Analytics
Track exactly who viewed your documents, which pages they read, and how long they spent.