---
title: "Analyze a natural-language energy problem and return an execution plan"
method: POST
path: "/api/agent/analyze"
tags: ["AI Agent"]
---

# Analyze a natural-language energy problem and return an execution plan

`POST /api/agent/analyze`

## Request

- Base URL: `https://api.cernion.de`
- URL: `https://api.cernion.de/api/agent/analyze`
- Auth: none declared

Uses Gemini to reason about the user problem and select which microservices to call, in which order, and which parameters are needed from the user.

## Query parameters

- `token` string

## Request body

- object
  - `problem` string, required: Free-text energy research problem or question
  - `token` string: Optional Cernion MCP token for this request. Overrides CERNION_TOKEN when provided.

## Response `200`

Execution plan with required user parameters

- object
  - `sessionId` string
  - `summary` string
  - `steps` object[]
    - `step` number
    - `service` string
    - `action` string
    - `description` string
    - `params` object
  - `requiredInputs` object[]
    - `name` string
    - `label` string
    - `type` string
    - `description` string
    - `example` string
    - `required` boolean

---

[API](https://skmtc.dev/cernion/apis/cernion-energy-tools-api.md) · [All operations](https://skmtc.dev/cernion/apis/cernion-energy-tools-api/llms.txt) · [OpenAPI document](https://skmtc.dev/cernion/apis/cernion-energy-tools-api/revisions/cdb94473b538?raw)