Bixso AI domain proof · Services marketplace
A product that teaches
services marketplace.
A services marketplace where AI removes the admin pain — bookkeeping, contracts and support — so households and providers can just get the job done.
Why → Business model → Business analysis → Domain brain → Architecture → The agents
Why we built it
The reason this project exists.
Local services run on paperwork — invoices, contracts, chasing. We started here to prove agentic AI can take the admin off both sides of a job, so people can just get the work done.
Every BIXSO project starts the same way — with a real business problem worth solving, not a technology looking for a use. Then comes the model, the analysis, and the agents.
01 · Business model
It starts with the business.
A marketplace creates value by matching a need to a trustworthy provider — and by taking the paperwork off both their plates.
- Households hold a job and a budget; providers hold skills and availability.
- Value is captured by trusted, well-scoped matches.
- Trust signals — verified badges, ratings, clear pricing — reduce the anxiety that kills adoption.
02 · Business analysis — the DNA
Then the rigour.
We modelled scoping, trust and the paperwork around a job before automating any of it.
- Job intake & scope
- Match & book
- Invoice & reconcile
- Contract & e-sign
- Job specs
- Provider track record
- Invoices (vendor, amount, GST)
- AU service agreements
- Provider verification
- Fair, explicit scope
- BAS/GST categories
- Signed before work
- Who to match
- Fair price band
- How to categorise spend
- When to flag
fig. — business analysis: decoding service-place into processes, data, rules & decisions
The rules that let an agent act without going wrong
- Trust signals are verified, not assumed.
- Scope is explicit and signed before money moves.
02¼ · Domain brain
The product becomes training ground for Bixso AI.
service-place is not only a product page in the portfolio. It is a field-specific operating surface: every workflow, record, decision, exception and correction can become evidence for a specialist domain brain.
BIXSO’s moat is the loop: build real products, learn from real activity, distil the field into an SLM, then place that specialist model inside governed agents. The claim matures only as the product evidence matures.
02½ · The architecture
The shape of the agentic AI.
A marketplace runs on many small, distinct jobs — scope a request, negotiate a price, reconcile an invoice, draft a contract — so the AI is built around tasks and processes, not one monolithic bot. The user sees a single assistant; behind it, a coordinator routes each request to the specialist persona built for that action. A bigger job is decomposed the same way: a multi-service project is planned into phases and tasks, then each task is matched to a verified provider. Every AI action is one governed, metered step; deterministic search and matching stay free.
Each task is a discrete, metered action · a multi-service job is decomposed into phases → tasks → a matched provider · deterministic search stays free
fig. — task & process orchestration, the pattern behind service-place
One face, many specialists
The user talks to a single assistant; the personas — intake, negotiator, care, bookkeeper, contract drafter, flow designer — are hats it wears per task.
Every action is a discrete task
Each capability maps to one governed, metered action with a typed input and output — clean to test, price and audit.
Process decomposition
A multi-service project is planned into phases and tasks, and each task is routed to the right verified provider.
Boundaries ship in the prompt
The bookkeeper is not a tax agent and a contract is a draft — every persona carries its disclaimer and its limits.
03 · The agents at work
It ships as agentic AI — verified.
AI works where the admin pain is — and grows as the platform ships.
Reads an invoice and extracts vendor, date, amount, GST and BAS category for reconciliation.
Auto-fills Australian service-agreement templates and tracks e-signature status.
Handles routine customer-care questions, with a human fallback.
What the product does
- Scope a job clearly
- Match verified providers
- Parse invoices into clean books
- Draft and track signed agreements
Guardrail. Verified trust and explicit, signed scope — no black-box matching, a human always in the loop.
Live at serviceplace.com.au — built on Firebase and Google Cloud Run, with two-sided sign-up, verified providers, an AI bookkeeper and contract drafter, and a full backend test suite.
Visit service-place →Frequently asked
Questions about service-place.
What is service-place?
A services marketplace where AI removes the admin pain — bookkeeping, contracts and support — so households and providers can just get the job done.
Is service-place available now?
Live in production. Live at serviceplace.com.au — built on Firebase and Google Cloud Run, with two-sided sign-up, verified providers, an AI bookkeeper and contract drafter, and a full backend test suite.
How does service-place use agentic AI?
AI works where the admin pain is — and grows as the platform ships.
How does service-place contribute to Bixso AI?
service-place is a field-specific product. Its workflows, records, decisions, exceptions and feedback form domain evidence that can help BIXSO distil a specialist SLM and a governed Bixso AI brain for Services marketplace.
What keeps service-place safe and accurate?
Verified trust and explicit, signed scope — no black-box matching, a human always in the loop.
What it means for you
Want this — grounded in your business?
service-place is the BIXSO method, shipped: a business model, analysed with rigour, running as governed agentic AI. We start with the questions, not the tech.
Book a free consult