Enterprise AI agent platform

Your busywork, handled by AI agents.

Tell Xagent what you need. It plans the work, runs it, and hands back the result, on your models and in your environment.

✓Describe the task in plain words. Nothing to build or draw first.

✓Run it in your own cloud or data centre, so nothing has to leave your environment.

✓Save what worked as an agent your team reuses and schedules.

Book a demo

Bring one workflow your team repeats every week. We will hand it to agents while you watch. We reply within one business day.

Trusted by teams building at scale

Berry Genomics XW Bank

Everbright

The product

Describe the outcome. Watch the work happen.

Every step, tool call and token stays visible while the task runs, so you can hand over work without losing sight of it.

au.cloud.xagent.co/task

Agent development

Task

Agents

Templates

Resources

Knowledge base

Models

Memory

au · Sydney

All tasks

5

Draft Monday’s QBR deck

RUNNING

Qualify 6 inbound leads

RUNNING

Triage support inbox

DONE

Month-end invoices

DONE

Weekly usage report

FRIDAYS 9AM

Draft Monday’s QBR deck

“Pull this quarter’s pipeline, summarise it by stage, and draft the QBR deck.”

LIVE

Tokens

42,180

Tool calls

6

Model

deepseek-v4-flash

Execution plan

Step

Agent

Tool

Status

Pull pipeline data

Knowledge

crm.query

Done

Summarise by stage

Knowledge

python.exec

Done

Build the deck

Studio

slides.gen

Running

Send for review

Planner

mail.draft

Queued

Describe your next task… deepseek-v4-flash Send

Recreated from the Xagent app.

Why Xagent

Four reasons teams pick Xagent.

Ask in plain words

Say what you want back. Xagent works out the steps, the tools and the order.

It finishes the job

A drafted reply, a filed invoice, a built deck. Not a plan for you to run yourself.

Your models, your data

Open or hosted models, chosen per step. Nothing has to leave your environment.

One stack, GPU to agent

The only agent platform with its own inference layer, so inference costs up to 70% less.*

The workforce

Five specialists. One planner.

You hand the work to the planner. It delegates to the specialists and hands you back one finished result.

au.cloud.xagent.co/workforces

LIVE

P

Planner

TEAM LEAD

Plans the steps, delegates to the specialists, and re-plans when the work changes.

S

Support

Triages the queue, answers repeat questions from your documents, escalates anything unclear to a person.

G

Growth

Qualifies inbound leads overnight, updates the CRM, drafts the outreach for you to approve.

K

Knowledge

Reads the documents, writes the report with sources, remembers what your team decided.

St

Studio

Turns the numbers into Monday’s deck, a landing page or a chart, on brand.

Teams usually start with one thing: inbound leads, the support queue, month-end invoices, interview scheduling, or the Monday report.

The difference

Not another workflow builder.

Rigid workflows break the moment requirements change. Xagent plans each run, watches the result, and adjusts as the work unfolds.

Drag-and-drop workflow builders

×Every path drawn by hand, before the work is understood

×Break the moment requirements change

×Maintained forever by whoever drew them

×Or closed platforms in someone else’s cloud, taking your data with them

Xagent plans at runtime

✓Describe the outcome. A plain-language goal is the whole spec

✓Xagent plans the steps, and re-plans when reality disagrees

✓Tools do the work, every call and result visible while it runs

✓Keep what worked. Save it as an agent your team reuses

DESCRIBE→ PLAN→ EXECUTE→ RESULT re-plans when the work changes

The economics

Powered by Xinference.

Run agents on hosted providers, any OpenAI-compatible endpoint, or models on your own hardware through Xinference. Same team, same engine, end to end.

Inference cost per 1M tokens, indexed

Same workload, three ways to run it

Closed-source API100

Hosted open models55

Self-hosted via Xinference30

At $10,000 a month in model API spend, self-hosting via Xinference costs about $3,000, keeping $7,000 a month for the roadmap.

*Indexed to closed-source API = 100. Customer-reported infrastructure comparisons, illustrative at the top of the reported range.

Up to

70%

lower inference cost than closed-source APIs, on customer-reported comparisons

300+

open and custom models served through one API, via Xinference

200+

built-in tools your agents can call, plus your own through MCP

Integrations

Connect the tools you already run.

Native connectors for Google, Microsoft, Meta and LinkedIn. Everything else, including your internal systems, plugs in through MCP.

Gmail

Google Calendar

Google Drive

Google Sheets

Microsoft 365 Outlook

Outlook

Teams

Slack

Your models. Your data. Your infrastructure.

Run the platform wherever your compliance team needs it, then ship agents into your own products.

01

Hosted

Run in our Australian cloud. Nothing to install, workspaces and agents ready the same day.

✓Hosted in Australian data centres

✓Fastest path to a first agent

02

Private cloud

A dedicated deployment in your own cloud account, with your models served through Xinference.

✓Your VPC, your keys, your network

✓Use the GPUs you already reserve

03

On-premises

Install into your own data centre for workloads that cannot leave the building.

✓No data crosses your perimeter

✓Built for regulated workloads

Data residency: Australia SSO (OIDC) Admin controls Run logs Traces and usage Human approval steps

Stop repeating the same work.

Book a demo on your own workflow. We will hand the busywork to agents while you watch.

Meet the workforce