The AI model for agentic workflows

Your AI needs an if-statement.

Sage answers closed-ended questions about any content in ~200ms, with a calibrated confidence score your code can route on.

Model routing
content inPOST /decide
"kind": "choice"
Route this prompt to the cheapest model that can still answer it well.
options: gpt-5.6-luna (cheapest) · gpt-5.6-terra (mid) · gpt-5.6-sol (flagship)
decision out
waiting for content…
if confidence >= 0.85
≥ 0.85Sent to the cheapest model
< 0.85Falls back to the flagship

Real responses recorded from the Sage API. Every scenario is a preset you can run live in the console.

The problem

LLMs are verbose and overconfident. Your code needs an answer, a confidence, and a next step.

01

Machines need decisions, not paragraphs

Chat models return prose to parse and second-guess. Automation needs a typed answer it can branch on.

02

Overconfidence is the failure mode

LLMs sound just as sure when they're wrong. Without a calibrated signal, you trust everything or nothing.

03

The hot path has a latency budget

A judgment call inside an agent loop or a checkout can't wait two seconds for a frontier model to stream an essay.

The missing primitive

LLM intelligence at classifier speed, with a confidence score.

Sage lets machines choose, act, or escalate to a human in 60–200ms, always with calibrated confidence. The missing primitive for agentic workflows: fast enough for the hot path, smart enough to read a system prompt, honest enough to say “I don’t know.”

How it works

Content → Decision + Confidence

Sage is a decision model we built and train ourselves: it answers closed-ended questions instead of generating text. Send content and a question, get a typed answer with calibrated confidence in one round-trip.

  1. 1

    Send content + a question

    Any text or list, plus a closed-ended question. Your policy goes in the instructions; Sage reads all of it.

  2. 2

    Get a typed decision

    Not prose: an answer field your code can switch on, plus a calibrated 0–1 confidence score.

  3. 3

    Route on confidence

    High confidence: act. Low confidence: escalate to a human. That one branch makes automation safe to ship.

# pip install levanto
from levanto import LevantoClient, YesNo

client = LevantoClient(api_key="lv_live_...")

env = client.decide(document, YesNo("Needs compliance review?"))

if env["result"]["confidence"] < 0.8:
    escalate_to_human(document)          # not sure? a human decides
elif env["result"]["answer"] == "yes":
    send_to_compliance(document)

Agent-native install

Don’t integrate it. Let your agent do it.

Paste one prompt into Cursor or Claude Code. Your agent installs Sage, then reads your repo and proposes where a decision model would replace brittle rules or a slow LLM call.

  1. 1

    Paste the prompt

  2. 2

    The agent installs the skill

  3. 3

    It finds where Sage fits

Download the skill

levanto-sage-decide.SKILL.md. Drop it in .cursor/skills/ or .claude/skills/

Copy this into your coding agent
You now have access to Levanto Sage, a decision-model HTTP API that turns content + a question into a structured, machine-actionable decision with a calibrated confidence score (Yes/No, Choice, Scale, Sort, Tags).

1. Install the skill so you know the full API contract:

   mkdir -p .cursor/skills && curl -fsSL "https://platform.levanto.ai/api/intelligence/skill" -o .cursor/skills/levanto-sage-decide.SKILL.md

   (If you use Claude, put it in .claude/skills/ instead.)

2. Set my Levanto API key as the SAGE_API_KEY environment variable. If I don't have one yet, pause and tell me to mint one at https://platform.levanto.ai (signup includes $1 of free credit, ~1000 decisions).

3. The endpoint is https://sage.levanto.ai. POST /decide with the header `Authorization: Bearer $SAGE_API_KEY`.

4. As a first call, make this decision:

   {
     "content": "Marketing email draft promotes \"guaranteed 40% returns\" and describes the product as \"risk-free\" for accredited investors.",
     "question": { "id": "needs_review", "kind": "yesno", "instructions": "Does this copy require compliance review before send?" }
   }

Read the skill for the response shape. Then explore this repository: find places where we already make judgment calls with brittle rules, heuristics, or a slow LLM call (moderation, triage, routing, risk, tool gating, ranking, etc.). Propose 2–3 concrete insertion points, pick the strongest one with me, wire it through /decide, and branch on result.confidence: act when it clears a threshold, escalate to a human when it doesn't.

Every closed-ended question your product asks

One API, five answer shapes. Each returns calibrated confidence.

Q: Is this transaction likely fraudulent?
{ "answer": "yes", "probability": 0.94, "confidence": 0.88 }

The hot path

We asked three models the same question.

May support auto-fulfill an export request today by email, without Owner approval or a DSAR?”, replayed at the speed it actually happened. Logs

Sagelevanto-sage-v0.5, our decision model
0ms
deciding…
Claude Opus 4.8flagship reasoning, JSON-only prompt
0ms
streaming…
Claude Haiku 4.5fast tier, JSON-only prompt
0ms
streaming…

Recorded run, 2026-07-23.

Run it yourself · $1 free credit
~200ms
typical decision latency
vs 1.5–2.0s for a chat LLM round-trip
$3/M
input tokens, output free
vs $3/M in + $15/M out for frontier models
0–1
calibrated confidence
a score that means what it says

Use cases

Where teams point Sage

Judgment calls that usually run on brittle rules, slow LLM round-trips, or human review.

Agent workflows

Gate tool calls, route between models, and escalate when confidence is low: one fast call inside the agent loop.

Ops & support triage

Route tickets, score urgency, and auto-approve the clear cases; everything else escalates to a human.

Moderation & content screening

Tag spam, scams, and policy violations at feed speed, with your community's actual rules as the policy.

Risk & fraud

Judge transactions and account activity inline, so clear cases flow and only the suspicious ones stop.

Data pipelines

Tag, score, sort, and screen records in batch: LLM judgment with a confidence column, no classifier training.

Levanto Labs

We make AI safe for humans.

“Levanto” is Spanish for “I rise”: the warm light of a new dawn where humans, agents and nature prosper together.

We are hiring.