For Agents
Manage Nuix cases, search and tag items, run data processing jobs, and export evidence for review and production.
Install Jentic One Beta
Jentic One is a self-hosted execution layer for AI agents. It lets your agent call the Nuix RESTful API, or any other public or private API you need. You set the rules, the agent never sees your credentials, and every call is logged.
Two steps, two machines. Install the instance in a safe environment, then register your agent from wherever it runs.
Step 1: Jentic One Host machine
# On the machine that will host your Jentic One instance:
curl -fsSL https://raw.githubusercontent.com/jentic/jentic-one/main/tools/install.sh | shStep 2: Agent machine
# On the machine where your agent runs (keep this separate from the instance):
curl -fsSL https://raw.githubusercontent.com/jentic/jentic-one/main/tools/install.sh | sh
jentic register # connects your agent to your Jentic One instanceJentic One is in public beta. The setup above keeps your agent separate from the instance, which is what you want before using real credentials: an agent running as the same OS user as Jentic One can read its stored keys directly. Just evaluating? A single local install is fine to start. See the secure deployment guide for the tiers.
What an agent can do with Nuix RESTful API.
Create, list, retrieve, and delete eDiscovery cases on a Nuix server
Search items inside a case using Nuix's query language
Tag and untag individual items to organise review batches
GET STARTED
Use for: List all cases on a Nuix server, Create a new investigation case, Search items in a case for a specific keyword, Get the text content of a Nuix item
Not supported: Does not handle SaaS data collection, payments, or messaging — use for Nuix case processing, search, tagging, and export only.
Jentic publishes the only available OpenAPI specification for Nuix RESTful API, keeping it validated and agent-ready. Nuix is an investigation and eDiscovery platform used by law firms, regulators, and corporate compliance teams to process, search, tag, and export huge volumes of unstructured evidence. The RESTful API exposes case lifecycle, item access, search, tagging, processing, and export operations against a self-hosted Nuix server. It is deployed inside legal review workflows, internal investigations, and incident-response engagements where defensible audit trails are required.
Retrieve item text, binary content, and metadata for review
Trigger processing jobs that ingest new evidence into a case
Export case data into review or production deliverables
Inspect tags applied across an entire case for QC and audit
Patterns agents use Nuix RESTful API for, with concrete tasks.
★ eDiscovery Case Setup and Processing
Litigation support teams stand up a new matter by creating a case via POST /cases, then kick off processing through POST /cases/{caseId}/process to ingest collected custodian data. Once processing finishes, reviewers search and tag responsive items. The API replaces manual Workbench clicks and lets the workflow run inside automation.
Call POST /cases with the matter name, then POST /cases/{caseId}/process with the evidence source path
Search and Tag Review
Reviewers run keyword and concept searches across a case and tag matching items as responsive, privileged, or hot. The flow uses POST /cases/{caseId}/search to pull a result set and POST /cases/{caseId}/items/{itemId}/tags to apply tags. Tags retrieved via GET /cases/{caseId}/tags drive QC and reporting.
Call POST /cases/{caseId}/search with a query, then POST /cases/{caseId}/items/{itemId}/tags for each responsive hit
Production Export
Once review concludes, the case data is exported via POST /cases/{caseId}/export to produce load files for opposing counsel or regulators. The export endpoint is the bridge between Nuix's internal database and downstream review platforms or productions.
Call POST /cases/{caseId}/export with the export profile and target path to produce the deliverable
Agent-Driven Investigation
An AI agent assisting a compliance investigator searches a Nuix case, retrieves item text, and tags items that match a fraud pattern. Through Jentic the agent searches for 'search Nuix case', loads the POST /cases/{caseId}/search schema, and executes without learning the bespoke Nuix query syntax.
Search Jentic for 'search Nuix case items', load the schema for POST /cases/{caseId}/search, and execute with the case ID and query
21 endpoints — jentic publishes the only available openapi specification for nuix restful api, keeping it validated and agent-ready.
METHOD
PATH
DESCRIPTION
/cases
List all cases
/cases
Create a new case
/cases/{caseId}/items
List items in a case
/cases/{caseId}/search
Search items in a case
/cases/{caseId}/items/{itemId}/tags
Add a tag to an item
/cases/{caseId}/process
Start data processing
/cases/{caseId}/export
Export case data
/cases
List all cases
/cases
Create a new case
/cases/{caseId}/items
List items in a case
/cases/{caseId}/search
Search items in a case
/cases/{caseId}/items/{itemId}/tags
Add a tag to an item
Three things that make agents converge on Jentic-routed access.
Credential isolation
Nuix bearer tokens and basic credentials are stored encrypted in the Jentic vault. Because Nuix is self-hosted, Jentic also scopes the host and port per agent so investigation traffic does not leak across tenants.
Intent-based discovery
Agents search Jentic with intents like 'search Nuix case' or 'tag responsive items' and Jentic returns the matching Nuix operation with its input schema.
Time to first call
Direct Nuix integration: 1-2 weeks for auth, query syntax, and export profile setup. Through Jentic: under a day — search, load, execute, with credentials already abstracted.
Alternatives and complements available in the Jentic catalogue.
Specific to using Nuix RESTful API through Jentic.
Why is there no official OpenAPI spec for Nuix RESTful API?
Nuix does not publish an OpenAPI specification. Jentic generates and maintains this spec so that AI agents and developers can call Nuix RESTful API via structured tooling. It is validated against the live API and kept up to date. Get started at https://app.jentic.com/sign-up.
What authentication does the Nuix RESTful API use?
The spec lists two schemes: HTTP basic auth and HTTP bearer token. Most production deployments use bearer tokens issued by the Nuix server. Through Jentic the bearer token is stored encrypted in the vault and injected at execution time.
Can I tag items in a case through the API?
Yes. POST /cases/{caseId}/items/{itemId}/tags adds a tag and DELETE on the same path removes it. Use GET /cases/{caseId}/tags to list every tag currently in use across the case for QC and reporting.
How do I trigger evidence processing through Jentic?
Search Jentic for 'start Nuix processing job', load the schema for POST /cases/{caseId}/process, and execute with the case ID and evidence source. Jentic returns the job record so the agent can poll status downstream.
What are the rate limits for the Nuix RESTful API?
Rate limits are not declared in the OpenAPI spec. Because Nuix runs on customer-managed infrastructure, throughput is bounded by the deployed server and worker capacity rather than a vendor quota. Tune your batching to match the server tier.
How do I retrieve the text of a specific evidence item?
Call GET /cases/{caseId}/items/{itemId}/text with the case and item identifiers. The response returns the extracted text Nuix stored during processing, suitable for review or downstream classification by an agent.
/cases/{caseId}/process
Start data processing
/cases/{caseId}/export
Export case data