implementation

Build the Topology Graph with LangGraph

Inspect the original prompt language first, then copy or adapt it once you know how it fits your workflow.

Linked challenge: Agentic IoT Forecasting with LangChain and Modal Runtimes

Format

Text-first

Lines

Sections

Linked challenge

Agentic IoT Forecasting with LangChain and Modal Runtimes

Prompt source

Original prompt text with formatting preserved for inspection.

1 lines

1 sections

No variables

0 checklist items

Define a LangGraph workflow with two nodes: 'Sampler' and 'Forecaster'. The 'Sampler' agent should inspect a list of IoT sensor metadata and output a subset of relevant features. The 'Forecaster' should receive these features and prepare a tool call.

Adaptation plan

Keep the source stable, then change the prompt in a predictable order so the next run is easier to evaluate.

Keep stable

Hold the task contract and output shape stable so generated implementations remain comparable.

Tune next

Update libraries, interfaces, and environment assumptions to match the stack you actually run.

Verify after

Test failure handling, edge cases, and any code paths that depend on hidden context or secrets.

Prompt diagnostics

Variables

Lists

Code blocks

Purpose

implementation

This prompt is mostly narrative and instruction-driven, so adapt examples and output constraints before you rewrite the structure.

Linked challenge

Agentic IoT Forecasting with LangChain and Modal Runtimes

Drawing from the 'TopoBrick' research, this challenge involves creating a zero-shot forecasting system for building IoT data. You will use LangChain (and LangGraph for state management) to build an agent that samples the 'topology' of exogenous variables—such as external weather, occupancy sensors, and grid pricing—to predict a building's energy load. Because time-series forecasting and topology sampling can be computationally expensive, you will implement the model runtime using Modal. This allows your LangChain agent to offload heavy 'Prophet' or 'N-BEATS' forecasting tasks to a serverless GPU/CPU environment. The agent must dynamically decide which IoT variables are 'relevant' to the current forecasting window and adjust its graph structure accordingly, effectively performing zero-shot adaptation to new building layouts.

Open challenge

Related prompts

Browse library

Problem Definition and Requirements Gathering

To establish a clear understanding of the problem space and define comprehensive requirements for the AI solution.

AI Solution Architecture and Strategy

To create a comprehensive technical architecture and AI strategy that guides the implementation of the solution.

Implementation Plan and MVP Development

To provide a clear, actionable roadmap for implementing the AI solution from concept to deployment.