ServiceAI agents · production
EngagementPilot → production
Primary fitOperators, service teams
Melbourne
Service · phase 02 · ai agents

AI agents that actually do work — not AI demos that almost do.

Practical AI agents wired into the tools your team already uses — inbox triage, lead qualification, internal Q&A, customer support drafts, recurring reporting. Implementation, not demos.

Melbourne basedImplementation-firstEvals + monitoringModel-portable
01 / What you get backSpecific outcomes · not a deliverables list
01
An inbox agent that triages, routes and drafts replies
Sorts incoming mail, identifies intent, drafts first-pass responses and flags what still needs a human.
02
A support agent grounded in your actual content
Answers from your documented help, SOPs and knowledge — not the open internet. With citations.
03
A qualification agent before a human talks to the lead
Asks the right questions, scores fit, and books the ones worth a conversation — skipping the ones that are not.
04
An internal Q&A agent for process, SOPs and admin
Your team stops asking the same twelve questions. Grounded in your documents, always current.
Good fit

Teams with repetitive decisioning hidden inside an inbox.

  • Repetitive decisioningYour team makes the same judgement calls dozens of times a day — routing, qualifying, drafting, summarising.
  • Inbox-heavy operatorsLead and client conversations live in email. Follow-up quality depends on one person being online.
  • The same twelve questionsFounders and ops leads answering the same prospect or team questions on a loop. An agent holds that context.
Skip if

A few cases where an agent will not earn its keep yet.

  • Pre-revenueWithout real traffic or workflow volume there is nothing meaningful for an agent to improve.
  • You only want a chatbot widgetWidgets are easy. Production agents that actually do work require scope, evals and iteration.
  • General-purpose creativity toolsWe build narrow, accountable agents. If you want a blank-canvas creative assistant, a commercial product already does that.
Step 01

Discovery

We map where the team currently spends judgement time — and whether an agent is the right fix. Not every task is.

Step 02

Scope one agent

We pick the agent with the clearest payback and define the inputs, tools, guardrails and success criteria.

Step 03

Build + evals

We ship the agent with a dataset of real prior cases as the evaluation bar. No green dashboards without it.

Step 04

Handover + monitor

Your team runs it. We watch for drift, failure modes and new use cases. Scope the next agent only when this one is healthy.

Investment guidance

All figures ex-GST in AUD. Final scope confirmed after discovery.
Pilot agent
from A$4k
One narrow agent, one tool, a clear eval bar. Designed to prove value before broader rollout.
Production agent
from A$10k
Production-grade build on one critical workflow, with monitoring, retraining hooks and handover docs.
Agent system
from A$20k+
Multiple agents wired into a shared ops backbone — inbox, CRM, knowledge, reporting working as one.
01 / LIVE

Circle Wellbeing

Website, booking and local-service architecture for a three-clinic wellness brand.

See work
02 / LIVE

Revitalise WCS

A publishing system the organisers can actually run — without waiting on a dev cycle.

See work
03 / INTERNAL

CrownX operating model

Forms, payments, CRM steps and automations wired into one working flow.

See work

Questions we get before people book.

Common answersFive minutes of reading
Q / 01

How reliable are these in practice?

As reliable as their evals. We set the bar with real prior cases, measure against it, and only ship when the agent clears it. Reliability without evals is marketing copy.

Q / 02

What about hallucinations?

Grounding, retrieval, structured tool use, and refusal behaviours. Most production hallucinations come from asking the model to make up what it should be retrieving. We engineer around that.

Q / 03

We are a clinic — what about patient data?

We do not touch clinical data. Agents are scoped to operations: bookings, reminders, admin queues, intake triage, follow-up. De-identified examples only, and your vendor agreements apply.

Q / 04

What tools do you build on?

Model-portable where it matters — OpenAI, Anthropic, Google, open source. Orchestration via TypeScript, n8n, Make or native platform tooling depending on the workload. We pick for fit, not fashion.

Q / 05

What if a better model drops mid-project?

Good. Our builds are model-portable by default. The prompts, evals, tools and guardrails outlast any one model — you swap the engine and re-run the evals.

Q / 06

Who owns the work?

You do. Prompts, configurations, evals and integration code are handed over at the end of the engagement with documentation your team can run without us.

Start with scope, not a demo

Build one agent that actually does the job.