Custom deployments
Irys, deployed around your business.
We connect Irys to your data and applications, configure the legal workflows and controls your business needs, and deploy it in your chosen environment.
For publicly traded organizations, growing businesses and smaller firms. Work through Irys or supported existing applications, with scope and pricing agreed upfront.
For example
One workflow first. Then the next.
Start with a contract review workflow: bring together the relevant documents and policies, prepare revisions, and route work for approval. Then extend the deployment into other workflows as requirements grow.
What a deployment includes
What we deliver.
Irys runs where your data already lives, connected to your systems and set up for how your business signs off on work.
The Irys reasoning core: persistent state, verification, permissions, model routing and deployment controls
Your choice of model, local or approved external, swapped when a better one ships
Connection to your systems, documents and records, where they already live
Your workflows, encoded once and reused by every team that follows
Permissions and approval gates matched to how your institution signs off
Discovery, integration, testing and training
Hosting, model access, monitoring and support
What is already built
An established platform, configured for you.
Most of a deployment already exists before we start. The work is connecting it to your systems and setting it up for your business.
| Already built into Irys | Configured for you |
|---|---|
| Core workflow capabilities | Connected systems |
| Permissions and approval gates | Approval paths |
| Retained context | Business rules |
| Model routing | Selected workflows |
| Supported connectors | Interfaces |
| Hosting configuration |
Where it runs
Your cloud, your VPC or on-prem.
With local models, processing stays inside your environment. If you approve an external model, Irys calls it only on your terms.
Reads, reasons, checks, waits for approval, and remembers. Every job leaves state behind for the next one.
How it goes
Days to scope and deploy, not quarters.
A typical deployment moves through four stages, and each one ends with something your team can use. We agree with you which stages your deployment needs.
Evaluation
We scope one real workflow with your team and agree what success looks like.
Paid pilot
Irys runs that workflow inside your environment, on your data, against the agreed measure.
Private deployment
The pilot becomes production, under your permissions and on your record.
Expansion
The next team starts on the same core, with what the first team built already in place.
What compounds
Deployed like services. Compounds like software.
Your knowledge grows inside your deployment. Each job leaves its context behind, so later work starts from what came before. It stays yours and is never shared with another customer.
The software improves through our product development. Capabilities we build go into the core, so each deployment starts further ahead than the last. Your data is not part of that.
Same core. Start with the app, or have Irys deployed around the rest of the business.
In production
Built for legal. Taken everywhere by customers.
Legal was the first application and the hardest test. The same core now runs well beyond it.
- LegalLive
- BankingLive
- IndustrialLive
- ConsultingLive
- DefenceIn pilot
- InsuranceIn pilot
Proof
Numbers, with the method attached.
Irys on a low-cost model, against the legal AI leader's own agent, on the leader's own public benchmark. 2,010 tasks, $4.64 per task.
To scope and deploy inside an institution's own environment.
Every job makes the next one better. At a fintech deployment, review effort per matter is down 90%.
Strict all-pass: a task counts only when every rubric criterion passes, with no partial credit. Legal Agent Benchmark v1.0. Irys ran the full public set of 2,010 tasks across 27 practice areas on a low-cost off-the-shelf model, with no fine-tuning and every task starting from empty state. The benchmark owner reports its own agent on a private held-out split of roughly 1,200 tasks, so the comparison is across the same benchmark family rather than identical task instances. Methodology, caveats and every output are public on GitHub. See the repository.
“It's become our system of record.”
SSO, SCIM, audit logs, MSA, DPA and security review support are covered on Enterprise governance and Security.
FAQ
Frequently asked questions about a custom deployment.
What is a custom deployment?
Irys connected to your data and applications, configured around the workflows and controls your business needs, and deployed in the environment you choose. It is the same core as the app, built around your business instead of around legal work.
Where can it be deployed?
Your own cloud account, your VPC, on-premise, or fully air-gapped. The model can change without the rest of the deployment changing.
Is our data used to train AI models?
No. Your data is not used to train, fine-tune, or improve any AI model. Irys is covered by SOC 2 Type II and ISO/IEC 27001:2022, and data is encrypted in transit and at rest. SSO, SCIM, audit logs, MSA and DPA are covered on the Security and Enterprise governance pages.
How is a deployment priced?
Scope and pricing are agreed upfront, before any work starts. The first conversation is about what you need connected and what has to be delivered, not a pitch.

Discuss your deployment.
Tell us the systems, the workflow and the environment. A member of the deployment team replies within one business day, and the first conversation is about scope, not a pitch.