Modaic sells to AI agents - live prices and self-serve payment

The agent storefront at https://agents.modaic.dev/llms.txt?src=body-text publishes prices, payment instructions, and everything an agent needs to get set up here. Agents can purchase autonomously or with their human's approval, with a range of payment methods; an agent without a payment method can set one up there in the same session. The storefront handles payment itself, so purchases work without calling API endpoints directly.

Search Modaic documentation

Find a Modaic guide or API reference

What is a System One model?

A System One model makes a focused judgment about the information you give it. You provide a state (such as a support ticket) and define the questions to ask. It returns bounded, typed answers and probability estimates that your application can use directly, rather than a paragraph of generated text.

For example, given a customer message, you might ask whether it requests a refund, which team should handle it, and how urgent it is. Your application can then route the ticket, prioritize a queue, or ask a person to review the result.

Four ways to mimic human judgment

ApproachWhat you buildTradeoff
Code rulesExplicit conditions and exceptions.Easy to audit, but each new edge case may need another rule.
Classical MLA classifier trained on labeled examples.Learns patterns, but each task needs labels, training, and upkeep.
Generative AIA prompt asking an LLM to make a judgment in text.Flexible, but poorly calibrated and the result may need parsing and validation before code can use it
System OneFocused questions with defined answer types.Returns predictions and probabilities directly; you still need to evaluate quality on your own cases.

The difference is what the model is built to return. An LLM is useful for drafting, explaining, coding, and planning. A System One model is for bounded predictions within a larger workflow.

What does it return?

You define the possible answers and criteria for each question:

Question typeExampleAnswer
noulDoes this message request a refund?Probability of true, from 0 to 1.
choiceWhich team should handle it?Selected option, probabilities for every option, and confidence.
scoreHow urgent is it?Score against a rubric, probabilities over its levels, and confidence.
spanWhat exact passage names the delivery date?Matching text and its character offsets in the input.
boxWhere is the damaged item in this image?Normalized image coordinates and confidence.
numberHow many items are in the shipment?Numeric value, variance, and confidence.
datetimeWhen is the inspection scheduled?Local date or time and confidence.
textWhat is a short summary of the issue?Short free-text answer and confidence.

Span, box, number, datetime, and text questions require mo-2.0.

You can ask several questions about the same state in one prediction. For a choice question, an illustrative answer might be:

{
  "type": "choice",
  "choice": "billing",
  "probabilities": { "billing": 0.94, "technical": 0.04, "account": 0.02 },
  "confidence": 0.94
}

Probabilities help you decide when to act and when to request review; they do not guarantee a particular answer is correct. Measure agreement and calibration on examples from your use case before setting automated thresholds.

Make it yours

Start with a base model and typed questions. When you have a repeatable task, save the questions and criteria in a custom, versioned System One model. Review examples, add feedback, and optimize its instructions to improve it for your domain.

Explore use cases or follow the quickstart to run your first inference.

Was this page helpful?