AI-ready data.

Every reading comes with the structured data behind it, ready for a model or an integration to read as it stands.

1 · What it is

Behind every dashboard and report is a structured JSON payload: the same readings shown on screen, in the form a machine reads. Hand it to a large language model, an ERP or a BI tool and it reads directly, without the data-engineering cleanup that usually comes first. You can ask your own questions of the sensor data, rather than only the ones a dashboard was built to answer.

2 · What’s in it

Alongside the readings, the payload carries a short piece of embedded guidance, what the fields mean and how they relate, so a model does not have to guess at the shape of your data. Every figure traces back to the sensor it was measured on, so an answer built on the payload rests on measured data rather than an estimate.

3 · What you can do with it

The payload supports three levels of use, from something any user can do today to integrations you or Augos build on top.

Ask a question today

Download a sensor’s JSON, give it to a secure model, and ask something specific. A cold-chain manager hands over a month of a store’s temperature data and asks for every breach above 8°C that lasted more than fifteen minutes; a grower uploads a season of soil-moisture and rainfall and asks which blocks were driest through flowering.

Automate a report

A scheduled agent can take the JSON at set intervals and write a summary. One reads last week’s breach data every Monday and drafts a three-line note of the worst events before stand-up. These are integrations you build on the export, not features switched on out of the box.

Connect it to your systems

Further out, an agent can act on the data: raising a maintenance job in your CMMS when a fridge keeps drifting warm, or signalling a control switch as a reading approaches a limit. Advanced, build-on-top scenarios that show where AI-ready data leads.

4 · Other formats

If you would rather work with the data yourself, every reading also exports as a file. Pick by what you are doing with it:

• CSV or Excel, for your own analysis, raw or aggregated down to the minute.
• PDF, a fixed record of what a report showed, for sharing and sign-off.
• JSON, the same machine-readable payload above, for a model or an integration.
• The API, when you want a live feed straight into your systems rather than a file.

5 · Access and privacy

Getting the data out does not widen who can see it. The payload obeys the same point-level permissions as the platform: you can only pull the points you are cleared for. See Roles & access.

One caution when using external models. Do not upload raw Augos data to a public, consumer-tier AI: consumer models may keep what you upload to train future versions, and a minute-level profile can reveal more than you intend. Use an enterprise model with a zero-retention agreement, or one hosted on your own infrastructure, and strip out sensitive metadata first.

Common questions