Sage by Levanto Labs · A decision model API
Intelligence. At runtime.
What if software could think while it runs?
The program asks. Sage responds. The program continues.
A new way to write software
Document: Maya Chen lives at 14 Cedar Lane.. The shown regexes find neither a name nor an address.
Match known patterns
ssn = r"\b\d{3}-\d{2}-\d{4}\b"
card = r"\b(?:\d[ -]?){16}\b"
if (re.search(ssn, doc)
or re.search(card, doc)
or "passport" in doc.lower()):
block(doc)
else:
publish(doc)
The running program asks Sage
private = decide(
doc, yesno("Contains personal information?")
)
match private["answer"]:
case "yes": block(doc)
case "no": publish(doc)
case None: review(doc)
Sage returns yes, so the application blocks the document. No publishes it; null sends it for review.
Inside the machine
A new way to write software.
Same input
Maya Chen lives at 14 Cedar Lane.
Before
Match known patterns.
These checks miss the name and address.
With Sage
Ask about meaning.
The same document. A semantic decision.
The application asks
Does this document contain personal information?
The question and the document go to Sage while the program runs.
→Sage responds
{
"answer": "yes",
"probability": 0.99
}
The application blocks publication. An uncertain answer goes to a person.