Question 1

Why should I use Irys instead of Claude, GPT, Perplexity, and Lexis separately?

Accepted Answer

Each of those tools is strong at one thing. but every one of them is amnesiac and isolated. Claude forgets everything when you close the tab. Perplexity has no matter context. GPT has no legal structure. NotebookLM has no output workflow. And none of them know your firm, your client, or your history. More critically: using consumer AI tools for client work without proper DPAs may violate your professional conduct obligations under ABA Model Rule 1.6. Irys is built with data isolation, zero retention, and architecture designed for attorney-client privilege. One platform, one subscription, full compliance.

Question 2

How does Irys compare to Harvey or Legora?

Accepted Answer

Harvey and Legora are general-purpose legal AI tools built for large law firms. Irys is purpose-built for the full legal workflow. research, drafting, redlining, matter management. with a three-tier reasoning architecture and citation verification against 50M+ cases. Irys is also significantly more accessible on pricing, with no enterprise-only gating.

Question 3

What is Irys?

Accepted Answer

Irys One is a unified AI platform for legal work. research, draft, redline, manage matters, and collaborate in one system built specifically for legal professionals. It replaces five tools with one.

Question 4

How is this different from general AI?

Accepted Answer

General AI tools like ChatGPT and Claude have no legal-specific guardrails, no citation verification, no matter management, and no audit trail. Irys starts with your matter. documents, facts, and legal context. and produces real legal analysis with sourced citations against 50M+ cases.

Question 5

Will Irys replace my legal team?

Accepted Answer

No. Irys augments your team, not replaces it. It handles the time-consuming research, first-draft generation, and document comparison so your lawyers can focus on strategy, judgment, and client relationships. Think of it as giving every attorney a tireless associate.

Question 6

Do you have your own LLM, or do you use existing models?

Accepted Answer

We do not build our own LLM from scratch. We use the best available foundation models and are model-agnostic. we route to the right model for the right task. What we own is the infrastructure around it: the retrieval pipeline, the citation verification engine, the knowledge graph, the matter context layer, and the reasoning orchestration. The LLM is the engine. We built the car.

Question 7

What does unlimited context actually mean?

Accepted Answer

It is not a metaphor. Our three-layer architecture (Worker / Coordinator / Synthesizer) processes documents across tiers so that matter context is preserved regardless of how many documents you upload. No token limits, no chat resets. Firms upload hundreds of documents into a single matter and the AI works from the full matter every time.

Question 8

Is Irys a wrapper around ChatGPT?

Accepted Answer

No. Wrappers take a general-purpose LLM, add a prompt template, and charge a markup. Irys is purpose-built infrastructure: a three-tier reasoning architecture, proprietary retrieval pipeline, citation verification against 50M+ cases, a knowledge graph engine, and a matter-native context layer. We rent the intelligence from the best AI models available. We own the legal system around it.

Question 9

Do I need technical expertise or IT support to use Irys?

Accepted Answer

No. Irys is designed for lawyers, not engineers. The interface is intuitive and requires zero technical setup. Most users are productive within minutes. For enterprise deployments, we handle onboarding and configuration.

Question 10

Who is Irys Lite for?

Accepted Answer

Irys Lite is an entry-level way to start using the application, including anyone exploring AI for legal work without a firm-tier commitment, solo practitioners just starting with AI and in-house counsel testing the platform before recommending a firm-wide rollout.

Question 11

What's included in Irys Lite?

Accepted Answer

Everything in Irys: every feature, including the Drafting Assistant, Workbench, the Microsoft Word Add-In, Matters, and Playbooks. You experience the entire application until you reach the usage caps.

Question 12

What are Irys Lite's usage caps?

Accepted Answer

Irys Lite includes:

• 12 messages per day (AI questions, including Standard and Thorough)
• 175MB of storage (approximately 35 documents)

Matters and Playbooks are unlimited, subject to the 175MB storage limit.

Question 13

How does the Irys Lite daily message limit work?

Accepted Answer

Your 12 daily messages reset at midnight in your local timezone. Messages that fail or don't complete do not count toward your daily limit.

Question 14

What's not included in Irys Lite?

Accepted Answer

Irys Lite is designed for individual, single-matter use. It does not include:

• Team sharing or collaborative Workspaces
• Advanced firm admin controls
• Priority support
• Expanded storage
• Integrations beyond the basic Word Add-In

If you find yourself needing any of these, that's a good sign you're ready for Irys One.

Question 15

Can I share my Irys Lite account with colleagues?

Accepted Answer

No. Irys Lite is a single-user plan. Team features, shared Workspaces, and multi-user functionality are not available and are hidden from the interface. For team access, Irys Teams is the right fit.

Question 16

Do I need a student email or verification to sign up for Irys Lite?

Accepted Answer

No. Irys Lite is open to everyone; no verification or .edu email is required. At signup, you'll be asked your role. Selecting Lawyer or Other gives you access to Irys Lite. Selecting Student routes you to our Student plan instead.

Question 17

What does Irys Lite look like on my billing statement?

Accepted Answer

Your receipts, invoices, and Stripe checkout will show Irys Lite.

Question 18

What happens when I hit an Irys Lite cap?

Accepted Answer

Caps surface only when you hit them. There are no usage meters or counters before that point, and your existing work always stays intact. Here's what happens at each cap:

Daily messages: 12/day - See the daily message limit FAQ above for reset timing and how different query types are counted. Conversations and outputs from prior days remain fully accessible; only your ability to send new messages pauses until the counter resets.

Storage: 175MB (~35 documents) - Your 175MB covers every document in your account, across every Matter and your Personal Library. When an upload would push you over the limit, the upload is blocked and you'll be prompted to free space (by deleting documents from any Matter or library) or to upgrade to Irys One for expanded storage. Documents already uploaded stay available; nothing gets locked or removed.

You can upgrade to Irys One ($299/month) at any time, either directly from a cap-hit prompt or from your account settings. Everything carries over: your Matters, documents, conversations, drafts, analysis, and insights.

Question 19

How do I upgrade from Irys Lite to Irys One?

Accepted Answer

You can upgrade to Irys One ($299/month) at any time from the billing section in your account settings, or directly from any cap-hit prompt. Your existing Matter, documents, and work product carry over; nothing starts from scratch. You'll immediately unlock unlimited messages, storage, Matters, and Playbooks.

Question 20

How do I cancel Irys Lite?

Accepted Answer

Irys Lite is a month-to-month plan with no long-term commitment. To cancel, visit your account settings; you'll see options to cancel your subscription.

Question 21

Does Irys Lite have an annual billing option?

Accepted Answer

No.

Question 22

How is Irys Lite different from the free trial?

Accepted Answer

The 7-day free trial gives you full, unrestricted access to Irys with no usage caps. Irys Lite is a paid plan at $19.99/month that gets you the full product with usage caps of 12 messages per day and 175MB of storage. Your trial does not auto-convert to a paid plan. At the end of your trial, you'll choose between Irys One (the full version of the platform) and Irys Lite.

Question 23

What happens when my free trial ends?

Accepted Answer

Your trial does not auto-convert to a paid plan. Two days before your trial expires, you'll get a reminder email. On the day your trial ends, your next login will show a paywall: Irys One ($299/month, the full platform) is the primary option, with Irys Lite ($19.99/month with usage caps) as the secondary option. You have a 7-day grace window after expiration during which you can still choose a plan and resume your work; your data is preserved through the grace window.

Question 24

Is the Word Add-In included on Irys Lite?

Accepted Answer

Yes. Every paid Irys plan, including Lite, includes the Microsoft Word Add-In at no additional cost.

Question 25

What is Irys Workbench?

Accepted Answer

Workbench is the agentic legal AI workspace. You ask in plain English, and it plans the task, reaches into the tools you already use, does the work, and brings it back to the matter, so you review finished work instead of assembling it yourself.

Question 26

What can Workbench do?

Accepted Answer

Research and analyze, draft, compare, revise, and produce real work product across your matters, grounded in your documents and real case law, using the tools you already use, all in one place.

Question 27

What does Workbench produce?

Accepted Answer

Real, reviewable deliverables: a Google Doc, a downloadable Word document, an Excel workbook, or an email draft ready in Gmail or Outlook, along with case-law research linked to the actual reporters.

Question 28

What happens after I ask Workbench for something?

Accepted Answer

It plans the task, works across your matter documents and the accounts you have allowed, checks case-law citations as it goes, and returns finished work to the matter: documents, drafts, and research you review rather than assemble. You can watch it work, steer it, or stop it at any point.

Question 29

Where does the finished work go?

Accepted Answer

Back into the matter. Deliverables and research fold into the matter so the next question builds on them, and anything created in a connected account, like a Google Doc or an email draft, stays there for you to review.

Question 30

How is Workbench different from a general AI agent?

Accepted Answer

A general agent does not know your matter, starts cold each session, and makes you wire it to your systems and re-explain context. Workbench is built for legal work: it lives inside the matter, organizes legal context by design, cites real case law and checks it, and holds a trust posture built for privileged client data.

Question 31

Can I stop or redirect Workbench while it is working?

Accepted Answer

Yes. You watch it reason in real time, you can stop it mid task, and you can steer it by adding an instruction to a running turn. It adjusts course instead of finishing wrong and making you start over.

Question 32

Which tools and connectors can Workbench work with?

Accepted Answer

At launch, Workbench connects to Gmail, Google Drive, Google Calendar, Google Sheets, Outlook, OneDrive, Dropbox, and Slack, plus legal case-law research. It can search and read across these systems, draft emails, create documents, and pull emails and files into a matter.

Question 33

Do I need to connect accounts to use Workbench?

Accepted Answer

No. Workbench works out of the box with your matter documents and legal case-law research. Connecting accounts extends its reach: it can then search your email and files, create documents in Drive, and prepare drafts in Gmail or Outlook.

Question 34

How do I connect an account?

Accepted Answer

Open the connections area in your account settings, choose a service, and authorize it. Workbench requests read and limited write access only. You then decide, per chat, which connected accounts Workbench may use.

Question 35

Can I bring emails and files into a matter?

Accepted Answer

Yes. Browse a connected account, select the emails, attachments, or files you need, and bring them in as first-class matter documents. Ingestion supports Word, PDF, Excel, CSV, PowerPoint, text, and markdown.

Question 36

Does Workbench send emails or take actions automatically?

Accepted Answer

No. Connections run on a read and limited write posture, and Workbench never sends on its own. Email tools create drafts only, actions are confirmation gated, and you control per chat which accounts Workbench may touch.

Question 37

Can I control which accounts Workbench can access?

Accepted Answer

Yes, per chat. A matter can be locked to documents only, or scoped to specific accounts, for example Drive and Gmail but nothing else.

Question 38

What kinds of legal matters can it handle?

Accepted Answer

Any legal matter. It works across practice areas on one surface, from litigation and transactional work to regulatory, compliance, and in-house matters, for everyone from solo attorneys to large firms and legal departments.

Question 39

What is Agentic Retrieval?

Accepted Answer

Agentic Retrieval is the research engine inside Workbench that powers Thorough mode. Instead of answering in a single pass, it runs a structured investigation: it plans the research, pursues multiple lines of inquiry in parallel, checks case law against primary sources, and synthesizes a legal memorandum with inline citations linked back to their source. The result is more reliable citations and answers grounded in verifiable sources rather than model inference alone.

Question 40

Is Agentic Retrieval included in my Irys plan?

Accepted Answer

Yes. It is part of Workbench, and Thorough mode is available on all Irys plans at no additional cost.

Question 41

Do I need to do anything to start using it?

Accepted Answer

No setup needed. Quick is the default mode for fast answers; to run a full, cited investigation, open the mode selector below the input bar and choose Thorough. Every mode is included: there are no settings to turn on.

Question 42

What are the three modes and when should I use each one?

Accepted Answer

There are three, and you pick how deeply Irys investigates; you never pick a model. Quick (the default): fast, direct answers for drafting, summarizing, rewording, or a straightforward question. Standard: one comprehensive pass that returns a memo-quality report with aggregated citations, best for statutes, regulations, and secondary-source questions. Thorough: a full investigation that reads your matter, checks case law, and returns a memo with inline citations you can click, best for matter-bound or case-law work you will stand behind. Switching is one click.

Question 43

What’s the difference between Quick and Thorough?

Accepted Answer

Quick gives a fast, single answer with no inline citations, ideal for quick drafting and questions. Thorough runs a full investigation: it plans, pursues multiple leads in parallel, checks case law against CourtListener, and returns a structured memorandum with inline citations. Use Quick for speed; use Thorough for anything you would cite or show to someone else.

Question 44

What’s the difference between Thorough and Standard?

Accepted Answer

Standard makes one comprehensive pass and returns a memo-quality report with aggregated citations, strong for statutes, regulations, and secondary-source synthesis. Thorough runs an iterative, step-by-step investigation, checks case law against source, and cites each claim inline, the better choice when the question turns on case law. Both are current modes: pick Standard for a single synthesis pass, Thorough for a checked, cited investigation.

Question 45

How do I switch between modes?

Accepted Answer

Open the mode selector below the input bar and choose Quick, Standard, or Thorough. The mode applies to your next message, so glance at the selector before you send, especially when you reopen an earlier conversation.

Question 46

Does an existing chat remember which mode I last used?

Accepted Answer

Yes. Each chat now reopens with the chat mode that was used for its last message (Quick, Standard, or Thorough). Pick up exactly where you left off.

Question 47

Which mode does a new chat start in?

Accepted Answer

Whichever chat mode you last selected (Quick, Standard, or Thorough). The default follows your latest choice so you don't have to reset it each time.

Question 48

What is Thinking and how do I use it?

Accepted Answer

Thinking is the live investigation panel that opens when you submit a query in Thorough mode. You can follow along in real time as Workbench identifies key issues, pursues each lead, and pulls in relevant sources. Once the query is complete, Thinking displays a compressed summary of every lead and cross-reference used to generate the answer, so you can see not just what it concluded, but how it got there.

Question 49

What happens after I submit a question in Thorough mode?

Accepted Answer

Thorough runs a four-step process. First, the Thinking panel opens showing the planned investigation and key issues to pursue. Second, leads run in parallel, each one a line of inquiry such as a case to check, a document section to read, or a statute to retrieve. Third, a structured legal memorandum is written with inline superscript citations. Fourth, the Sources & Citations panel populates with everything retrieved, grouped by Case Law and Web, with a search function and Copy All option.

Question 50

Does Thorough mode work with my matter documents?

Accepted Answer

Yes. Thorough is matter-aware by default, when you’re working inside a Matter, Workbench prioritizes your attached documents alongside external legal sources. Document citations link directly to the source PDF at the cited page.

Question 51

What’s the difference between Case Law and Web Search in the Sources panel?

Accepted Answer

Case Law refers to opinions retrieved and checked through CourtListener, a free, authoritative repository of U.S. legal opinions, oral arguments, and federal filings. Web Search refers to additional relevant sources located through online search. Both are grouped separately in the Sources & Citations panel so you can see exactly where each piece of information came from.

Question 52

How do inline citations work?

Accepted Answer

Hover over any footnote number in Thorough’s output to see the citation and a hyperlink to the source. Click the footnote number to open the full Sources & Citations panel, where all references are listed and grouped by type. From either view, you can navigate directly to the full opinion on CourtListener or to the source document page.

Question 53

How does Irys verify case law citations?

Accepted Answer

All case law references are checked against CourtListener, which covers 50M+ U.S. legal citations going back over 200 years. Clicking any case citation takes you directly to the full opinion on CourtListener. You should always review citations independently, it is still AI, but the checking chain is visible at every step.

Question 54

Do I need a CourtListener account or subscription to use Thorough mode?

Accepted Answer

No. CourtListener is a free resource and no account or subscription is required.

Question 55

Does Thorough mode affect how quickly Irys responds?

Accepted Answer

Thorough is the most thorough mode, so it takes longer than Quick’s near-instant answer. Because the Thinking panel shows the investigation as it runs, you follow progress throughout rather than waiting for a final answer to appear all at once.

Question 56

Will my existing saved prompts and chat history still work?

Accepted Answer

Yes. Your saved prompts and chat history are unaffected by the modes. Quick is the default; Thorough and Standard are there whenever you need them.

Question 57

What is Quick mode?

Accepted Answer

Quick is the default mode: fast, direct answers for drafting, summarizing, rewording, and straightforward legal questions. It works from your matter’s full document context and returns copy-ready text without inline citations. Use it when you want an answer in seconds, not a research report.

Question 58

What is Focus Mode?

Accepted Answer

Focus Mode gives you a distraction-free, full-screen view of a conversation for reading the AI’s replies: it hides the surrounding panels so the chat fills the screen. Toggle it off to return to the standard layout.

Question 59

Why did my mode change, or does the platform switch modes on its own?

Accepted Answer

The mode you pick applies to your next message; it doesn’t change answers already on screen. Before you send, especially when you reopen an older conversation, glance at the mode selector to confirm you’re in the mode you expect, so the answer comes back the way you want.

Question 60

How do I verify Standard citations?

Accepted Answer

Standard gathers its citations at the end rather than checking each against a case-law database as it writes, so run Cite Check on the report to confirm every cited case exists, is correctly formatted, and is still good law. For case-law-heavy questions, Thorough checks citations against source as it works.

Question 61

Can I download or save an answer?

Accepted Answer

Yes. Download any reply as PDF or Word (DOCX), use “Save this output to Notes in My Desk” to keep it with the matter, or copy it straight out.

Question 62

What is the Dashboard?

Accepted Answer

The Dashboard is your landing page after you sign in: a command center that pulls your active work into one place. It has three views, Focus, Command, and Full, that reveal more as you ask for it, so it leads with what is urgent and stays out of the way until you want more.

Question 63

What do the Focus, Command, and Full views each show?

Accepted Answer

Each view answers a different question and is complete on its own, so you only go deeper when you need to. Here is what each one leads with:

Question 64

How do I switch views, and does Irys remember the one I use?

Accepted Answer

Use the "Dashboard View" control near the top of the Dashboard to move between Focus, Command, and Full. Irys remembers the view you chose and opens there next time.

Frequently Asked Questions

Still have questions?