Bring Your Own Agent
Every inventory vendor is now selling you their AI. You rent it, it does what their roadmap says it does, and it stops at the edge of their product. We think that is the wrong way round. Your agent should be yours: the one your team already trusts, running where you want it, able to reach the systems you choose. Qoblex is built to be driven by it. The API reference is a downloadable spec an agent can read on its own.
What makes a system agent-ready
Not a chat box bolted onto a sidebar. An agent needs to find out what it can do, be trusted with a limited amount of it, know when something happens, and not break when we ship on Thursday.
It can read the manual itself
The whole API is one downloadable OpenAPI 3.0.1 document. An agent ingests it and knows every endpoint, every parameter and every response shape, without anyone hand-writing a tool definition or keeping one in step. This is the difference between agent-ready and agent-possible.
Give it a key that cannot do everything
Permissions and scopes are set per key. An agent that drafts purchase orders gets a key that drafts purchase orders, and cannot touch your pricing or delete a customer. You generate it, you revoke it, and you do not have to trust a model with the keys to the building.
It reacts instead of asking
Webhooks push an event to your agent when stock moves, an order arrives or a shipment goes out. An agent that polls is either late or expensive, and usually both. One that is told can sit idle until there is something to do.
Everything, not a read-only export
Coverage is close to total: the same sale orders, stock, purchase orders, shipments, invoices, customers and suppliers a person works with. An agent that can only read writes you a report. One that can act finishes the job.
Nothing bespoke to teach it
REST, resource-oriented URLs, JSON in and JSON out, standard status codes, the same filtering and pagination on every list. Models are good at this because everything else is like it. A proprietary protocol is a thing you would have to explain in every prompt.
We will not break it on a Thursday
The API evolves additively under `/v1`: new endpoints and fields appear, nothing is quietly removed or renamed. Build the agent to ignore what it does not recognise and it keeps working. A breaking change gets a new version in the path, so you move when you are ready.
We do not sell you the agent
There is no Qoblex copilot, no seat to buy, no model to choose from a dropdown. That is a deliberate refusal rather than a gap in the roadmap. An agent you rent from your inventory vendor can only ever be as good as that vendor, and it can only reach that vendor’s data. The interesting work is almost always across systems: the stock is here, the freight quote is there, the customer email is somewhere else.
So bring the one you already use. Claude Code, OpenAI Codex, OpenClaw, something your team wrote, something you host yourself on your own hardware because the data cannot leave the building. They all speak HTTP and they can all read an OpenAPI document, which is the whole requirement. What runs the agent, where it runs, and what else it is allowed to see are your decisions, not ours.
The practical version of that promise is that we spend our effort on the surface rather than on the assistant: the spec, the scopes, the webhooks, the coverage. Those are what make any agent useful here, including ones that do not exist yet.
Frequently asked questions
Agents, access, safety, and what we do and do not provide.
Can an AI agent manage inventory in Qoblex?
Yes. Qoblex exposes its whole operation over a REST API with a downloadable OpenAPI 3.0.1 specification, so an agent can read what it is allowed to do and then do it: check stock, draft and raise purchase orders, allocate and ship sale orders, raise invoices, update products. You bring the agent and Qoblex provides the surface it drives.
Which agents work with it?
Any agent that can make an HTTP request and read an OpenAPI document, which in practice is all of them. Claude Code, OpenAI Codex, OpenClaw, a framework your team built, or something self-hosted on your own hardware. We do not certify a list, because a list would go stale faster than this page.
Do you sell an AI agent or a copilot?
No, and not by accident. An agent rented from your inventory vendor is limited to that vendor’s data and that vendor’s pace. We would rather make Qoblex something any agent can drive properly, and leave the choice of agent to you.
How do I stop an agent doing something it should not?
Give it its own API key and scope that key to what it needs. Permissions are set per key, so an agent that reorders stock cannot edit pricing, and one that reads reports cannot write anything at all. Revoke the key and it stops, immediately, without touching anyone’s login.
Does an agent have to poll for changes?
No. Webhooks push events to your endpoint as records change, so the agent is woken by the thing it cares about. Polling still works if it suits your architecture better.
Can I run the agent on our own infrastructure?
Yes. Nothing about this requires a hosted anything: the agent runs wherever you put it and talks to the API over HTTPS. For teams whose data cannot leave their own network, the agent stays inside it and only the API calls go out.
Will an update break our agent?
It should not. The API evolves additively under `/v1`, so new endpoints and fields can appear but nothing is quietly renamed. Build the agent to ignore fields it does not recognise. Anything genuinely breaking gets a new version in the path.
What does it cost?
There is nothing to buy for the agent, because we are not selling one. What it needs is API access, which is a paid add-on on Starter and Business and included on Scale. See pricing.
The rest of the developer story
How it works
Be up and running in a fraction of the time you’re expecting it to take.
- 1
Talk to an expert
Our experts have helped hundreds of product sellers just like you.
Book a demo - 2
Bring in a specialist
Engage an onboarding specialist to make it much easier for you.
Book a demo - 3
Go live fast
Unlike other systems, we can get you up and running within 1 week.