AI ENGINEER

The Converge AI Engineer

The AI Engineer is the part of Converge that reads your lab report, builds the fluid with the same equation-of-state engine you use by hand, runs the calculations you ask for and explains the results. Every number it gives you can be traced to a calculation, and you decide what gets published.

FOUR STEPS

How does the AI Engineer build a fluid model?

It works in four steps: it reads the lab report, builds the fluid with the Converge equation-of-state engine, runs the calculations you ask for and hands you a draft to review. The steps run in order, and you can stop after any one of them and carry on by hand.

  1. 01 · PDF · XLSX · DOCX

    Read the report

    Upload the lab report, or paste a table. The AI Engineer pulls out the composition, plus-fraction properties, reservoir temperature and each experiment's measurements.

  2. 02 · EOS

    Build the fluid

    It sets up the equation of state, splits and lumps the plus fraction, and calculates saturation pressure and the lab experiments with the Converge engine.

  3. 03 · CALCULATIONS

    Run what you ask

    Ask for a phase envelope, a flash, a CCE or a separator test. It runs the calculation with the Converge engine in your project and explains the result next to the lab values.

  4. 04 · DRAFT

    You review

    The result is a draft model with every input it read from the report listed. Ask the AI Engineer to tune it to your lab data, or tune it yourself in the live tuning screen. You can check it, change it or discard it at any point.

SIGN-OFF

Rules it follows

An engineer has to sign off a PVT model. The AI Engineer is built to make that sign-off quick, not to skip it.

  • It shows every value it read from the report, so you can check it against the source page.
  • Every number it quotes is traced to a model calculation it ran in your project, and you see each calculation as it runs.
  • Lab measurements stay labelled as lab rows. A table that shows a lab value as model output, or a value with no source, raises a warning to you.
  • Gauge pressures are converted to absolute before any comparison, and the conversion is listed.
  • It keeps reported isomers as separate components and asks when the report lumps them.
  • It says when the report is missing something the model needs, instead of filling the gap silently.
  • Its work is a draft. Your published model changes only when you accept it.

WHOLE PROJECT

It reads every module

The AI Engineer starts from the project's one shared fluid and can read the saved results of every other module, from well performance and material balance to simulation and economics. It can run any calculation in the engine catalogue, the same functions the scripting editor and the API use.

  • Ask about a tank, a decline forecast or a cash flow, not only the fluid.
  • Other modules' data reach it read-only.
  • If a request fails, your message and any pasted report stay in the box, so you can send again.
  • A long answer can be stopped at any time, and a progress line shows the steps and seconds so far.

PROVIDERS

Model providers

Use the provider your company already approves. If a model is unavailable, the AI Engineer falls back automatically to the next model your company has configured, before it has answered, and never to a provider you have not set up. On an on-premises install, the AI Engineer can use a model you host yourselves.

  • Major cloud AI providers
  • Your company's approved provider

Start with a fluid you know.