Levanto Sage Agentic Model

HTTP API for structured decisions over content plus a question.

Download this skill

Drop this file into .cursor/skills/, .claude/skills/, or your agent’s skill directory. Raw Markdown, no rendering.

Product Context

Levanto Sage is for workflows where software needs to decide, not write. It turns content plus a question into a structured decision with a probability or confidence signal. Use Sage when an application needs to route, approve, block, score, rank, tag, or escalate. LLMs return text and only provide confidence if asked; that confidence is simulated. Sage always returns a decision signal, so machines can act when confidence is high and escalate to a human when confidence is low. Supported decision kinds:

Yes/No — answer a binary question: probability (P(yes)), answer ("yes"/"no"), and confidence (decisiveness from tie).
Choice — pick the best option, with independent per-option probabilities (raw; do not sum to 1).
Scale — score a rubric, with expectation and confidence.
Sort — rank a list of items by a criterion.
Tags — apply independent yes/no labels to the same content.

Good use cases:

Agentic workflows — Sage as the decision layer for agents: automate routing, branching, and escalation across agentic workflows and pipelines.
Operations — triage urgency and route work across DevOps, SecOps, and customer support.
Agentic guardrails — check tool calls and responses on the hot path to keep agents secure and aligned with the business goals of the workflow.
Content screening & moderation — tag, rank, score, and sort content in data pipelines, including moderation, abuse flagging, and policy-risk severity.
Risk & fraud — assess risk and opportunity and detect fraud across transactions, asset trades, and agentic actions (e.g. refunds).

Use public-facing language:

Sage decides; it does not write paragraphs.
Supported decision kinds are Yes/No, Choice, Scale, Sort, and Tags.
Do not explain internals, architecture, training details, infrastructure, or implementation details unless the user explicitly asks for private engineering context.
Use decision kind in prose. Keep the JSON wire fields exactly as shown in code examples because clients need the real format.

Base URL

Default hosted endpoint:

https://sage.levanto.ai

The user may supply a different base URL. Do not invent an endpoint if one is missing; ask for it.

Authentication

A valid Levanto API key is always required for decision calls. Every POST to /decide and /decide/batch must carry a key; requests without one are rejected with HTTP 401 ({"detail": "API key required. Provide a valid Levanto API key."}). Send it in the Authorization header:

Authorization: Bearer lv_live_...

Keys look like lv_live_.... If the user has not provided one, ask for it — do not proceed to /decide without a key.
401 / 402 — see Errors.
/ready does not require a key.
Never hardcode, log, echo, or commit the key. Read it from an environment variable (e.g. SAGE_API_KEY / API_KEY) and pass it only in the request header.

Endpoints

Method	Path	Purpose
GET	`/ready`	Model readiness — 503 while loading, 200 when ready
POST	`/decide`	One decision
POST	`/decide/batch`	Many decisions

All decision calls (/decide, /decide/batch) require a valid API key (see Authentication); /ready does not.

Request Shape

{
  "content": "<content to evaluate>",
  "question": {
    "id": "<stable result id>",
    "kind": "<yesno | choice | scale | sort | tags>",
    "instructions": "<question to answer>"
  }
}

Use content for the thing being evaluated — a bare string (shorthand for { "kind": "text", "value": "..." }), { "kind": "text", "value": "..." }, or { "kind": "list", "value": [...] } for sort. Use question.kind to select the decision kind and question.instructions for the criterion. The response envelope is always { id, kind, result, meta }.

Yes/No

Use Yes/No for binary questions.

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

Response:

{
  "id": "needs_compliance_review",
  "kind": "yesno",
  "result": {
    "probability": 0.92,
    "confidence": 0.84,
    "answer": "yes"
  },
  "meta": { "model": "levanto-sage-v0.8", "latency_ms": 97.4 }
}

probability — P(yes), in [0, 1].
answer — "yes" if probability ≥ 0.5, else "no".
confidence — decisiveness from a tie: 2 × |probability − 0.5| (0 at 0.5, 1 at certainty). Grounding compares this to confidence_floor.

Choice

Use Choice when Sage must pick one option.

{
  "content": "Vendor uploaded a contract PDF that mentions automatic renewal and a 90-day termination clause.",
  "question": {
    "id": "contract_disposition",
    "kind": "choice",
    "instructions": "How should legal handle this contract?",
    "options": [
      {"option": "approve", "description": "Standard terms, no red flags — proceed to signature"},
      {"option": "revise", "description": "Acceptable with specific clause changes before signing"},
      {"option": "reject", "description": "Terms are unacceptable — do not proceed"},
      {"option": "escalate", "description": "Unusual or high-risk terms — partner review required"}
    ]
  }
}

Response:

{
  "id": "contract_disposition",
  "kind": "choice",
  "result": {
    "chosen": "revise",
    "confidence": 0.88,
    "probabilities": [
      {"option": "approve", "probability": 0.11},
      {"option": "revise", "probability": 0.88},
      {"option": "reject", "probability": 0.04},
      {"option": "escalate", "probability": 0.22}
    ]
  },
  "meta": { "model": "levanto-sage-v0.8", "latency_ms": 216.8 }
}

probabilities — raw P(correct) per option (independent sigmoids; do not sum to 1).
confidence — P(chosen is correct); use for thresholds and grounding.
chosen — argmax of probabilities.
2–120 options per question (see Limits).

Scale

Use Scale for rubric scoring. Always send exactly 5 levels with integer values 0, 1, 2, 3, 4 — the model is trained on this fixed rubric only. Subsets, sparse scales, or any other level values are rejected with HTTP 400.

{
  "content": "Candidate explained our product roadmap clearly but struggled to answer questions about database scaling tradeoffs.",
  "question": {
    "id": "interview_score",
    "kind": "scale",
    "instructions": "How strong was this candidate in the technical interview?",
    "levels": [
      {"level": 0, "description": "Not qualified — fundamental gaps in required skills"},
      {"level": 1, "description": "Weak — significant concerns about core competencies"},
      {"level": 2, "description": "Mixed — some strengths but notable gaps remain"},
      {"level": 3, "description": "Solid — meets the bar with minor areas to probe"},
      {"level": 4, "description": "Strong hire — clearly exceeds expectations for the role"}
    ]
  }
}

Response:

{
  "id": "interview_score",
  "kind": "scale",
  "result": { "expectation": 2.4, "confidence": 0.71 },
  "meta": { "model": "levanto-sage-v0.8", "latency_ms": 79.8 }
}

expectation is the expected level; confidence reflects how peaked the level distribution is (independent of the mean).

Sort

Use Sort to rank a list of items by a criterion. content must be a list with 2–120 items (see Limits).

{
  "content": {
    "kind": "list",
    "value": [
      {"id": "typo", "content": "Spelling mistake on the FAQ page."},
      {"id": "db_down", "content": "Primary production database is unreachable."},
      {"id": "pricing", "content": "Prospect asking about Enterprise pricing."}
    ]
  },
  "question": {
    "id": "triage",
    "kind": "sort",
    "instructions": "Sort by operational urgency, most urgent first."
  }
}

Response:

{
  "id": "triage",
  "kind": "sort",
  "result": { "sorted": ["db_down", "pricing", "typo"], "confidence": 0.92 },
  "meta": { "model": "levanto-sage-v0.8", "latency_ms": 312.0 }
}

The sort request is minimal — just instructions and the item list. Scoring strategy and ranking are chosen by the server, not the request: SortQuestion accepts only kind, id, instructions (any other field is rejected). The result carries a calibrated, list-level confidence in [0,1] — how trustworthy the whole order.

Grounding (optional)

Attach a grounding block to a Yes/No, Choice, Scale, or Tags request to let Sage fetch fresh web evidence before deciding (useful for recency- or fact-heavy questions). For Tags, low_confidence triggers when any tag’s confidence is below the floor (weakest-link); Sage then re-scores all tags on the expanded content.

{
  "content": "Has there been a major Cloudflare incident this month?",
  "question": {"id": "incident", "kind": "yesno", "instructions": "Is this likely true?"},
  "grounding": {"trigger": "low_confidence", "confidence_floor": 0.8}
}

trigger: never, low_confidence (default — search when result.confidence is below confidence_floor), or always.
For yesno, confidence = 2|p − 0.5| (decisiveness; 0 at a tie). Default floor 0.80 requires roughly p ≤ 0.10 or p ≥ 0.90 to skip search.
The response gains grounding_meta with triggered, queries, sources, and timing.
Requires the server to be configured for grounding; if it is not, omit the block.
When a search actually runs, grounding adds 1 decision unit on top of the document/token count (see Pricing).

Pricing

Sage uses a monthly (or annual) decision allowance. Plans:

Plan	Price	Decision units / month
Developer	$14	5,000
Starter	$49	30,000
Growth	$249	300,000

Each completed /decide or /decide/batch call consumes decision units from the current period.

Decision units — max(documents or question_count, ceil(input_tokens / 4000)) plus one unit per grounding search that actually ran. When documents is omitted or zero, question count is used. Output tokens are free.
Batch fast mode (latency_mode: fast) — Starter and Growth only.
Extended context (up to 128K tokens) — Growth only. Other plans use the standard context ceiling.
Unused units do not roll over. Hitting the allowance returns 402 until the next period.

Batch

Use /decide/batch for many decisions in one call. Each entry in requests is a group: one content plus a list of questions about it — so asking several questions about the same content sends that content only once, and a single call can still mix groups with different content.

{
  "requests": [
    {
      "content": "User post: 'Selling verified Instagram accounts, DM for bulk pricing.'",
      "questions": [
        {"id": "policy_violation", "kind": "yesno", "instructions": "Does this post violate marketplace policy?"},
        {
          "id": "harm_level",
          "kind": "scale",
          "instructions": "How harmful is this content to the platform?",
          "levels": [
            {"level": 0, "description": "No meaningful harm — safe to leave published"},
            {"level": 1, "description": "Low harm — minor policy edge case"},
            {"level": 2, "description": "Moderate harm — misleading or low-grade abuse"},
            {"level": 3, "description": "High harm — fraud, spam, or user safety risk"},
            {"level": 4, "description": "Severe harm — active scam or imminent user damage"}
          ]
        }
      ]
    }
  ]
}

Each question can carry its own optional grounding (grounding is no longer part of the group; sort questions still reject it). To batch decisions about different content, add more groups:

{
  "requests": [
    {"content": "doc A", "questions": [{"id": "a1", "kind": "yesno", "instructions": "urgent?"}]},
    {"content": "doc B", "questions": [{"id": "b1", "kind": "yesno", "instructions": "urgent?"}]}
  ]
}

Batch responses are nested by group, then by question:

results: one item per group (matches requests 1:1);
results[i].answers: one item per question in that group’s questions, in order;
results[i].answers[j].ok: success flag for that question (.result holds the decision, or .error the message);
meta.request_count: number of groups; meta.question_count: total questions across all groups.

Errors

HTTP	Meaning
`400`	Invalid request (schema validation)
`401` / `402`	Missing/invalid API key, or period decision allowance exhausted
`503`	Service loading or temporarily unavailable

Invalid requests return a standard schema message, for example:

{"detail": "content: Field required"}

{"detail": "scale levels must be integers in 0..4 (model trained on 5 levels); got [9]"}

{"detail": "Service is still loading."}

Limits

Per-kind counts (HTTP 400 outside these ranges):

Kind	Field	Min	Max
choice	`options`	2	120
scale	`levels`	5	5 (values `0`–`4` only)
sort	`content.value` items	2	120
tags	`tags`	1	120

Scale — always send all five levels 0 through 4. No sparse rubrics, no alternate ranges, no fewer or more levels. Each level must be a distinct integer in that set. Content and question length — the full rendered request must fit the plan’s context ceiling: roughly 32K tokens by default, or up to 128K tokens on Growth (Extended context). That budget includes content, question.instructions, option descriptions, scale rubric lines, sort item bodies, tag specs, and any grounding-added search context. Oversized requests fail rather than silently truncating. Very long content can also hit HTTP 503 before the hard token cap; keep documents well under the ceiling in practice.

Threshold Guidance

Sage always returns a decision signal. The application decides what to do next. Example:

high confidence: automate;
medium confidence: review;
low confidence: escalate to a human or ask for more context.

Do not say Sage “abstains.” Say it supports low-confidence routing.

Smoke Test

endpoint="https://sage.levanto.ai"
# API key is REQUIRED for /decide — read it from the environment, never hardcode.
auth="-H Authorization: Bearer ${SAGE_API_KEY:?set SAGE_API_KEY to your lv_live_ key}"

# /ready needs no key — empty body; 200 means ready, 503 means still loading.
curl -s -o /dev/null -w '%{http_code}\n' "$endpoint/ready" | grep -qx 200

curl -s $auth -H 'Content-Type: application/json' "$endpoint/decide" -d '{
  "content": "Marketing email draft promotes \"guaranteed 40% returns\" and describes the product as \"risk-free\" for accredited investors.",
  "question": {"id": "needs_compliance_review", "kind": "yesno", "instructions": "Does this copy require compliance review before send?"}
}' | jq -e '.kind == "yesno" and .result.probability != null and .result.confidence != null and .result.answer != null'

curl -s $auth -H 'Content-Type: application/json' "$endpoint/decide/batch" -d '{
  "requests": [
    {
      "content": "same doc",
      "questions": [
        {"id": "a", "kind": "yesno", "instructions": "urgent?"},
        {"id": "b", "kind": "yesno", "instructions": "positive?"}
      ]
    }
  ]
}' | jq -e '.meta.request_count == 1 and .meta.question_count == 2 and (.results | length) == 1 and (.results[0].answers | length) == 2'

Overview

Agentic model

Resources

Pricing

Agent skill

Levanto Sage Agentic Model

Download this skill

Product Context

Base URL

Authentication

Endpoints

Request Shape

Yes/No

Choice

Scale

Sort

Tags

Grounding (optional)

Pricing

Batch

Errors

Limits

Threshold Guidance

Smoke Test

​Levanto Sage Agentic Model

Download this skill

​Product Context

​Base URL

​Authentication

​Endpoints

​Request Shape

​Yes/No

​Choice

​Scale

​Sort

​Tags

​Grounding (optional)

​Pricing

​Batch

​Errors

​Limits

​Threshold Guidance

​Smoke Test

Levanto Sage Agentic Model

Product Context

Base URL

Authentication

Endpoints

Request Shape

Yes/No

Choice

Scale

Sort

Tags

Grounding (optional)

Pricing

Batch

Errors

Limits

Threshold Guidance

Smoke Test