implementation

Cerebras Integration Config

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

Linked challenge: Real-time AI Newsroom Pod with Mastra AI and Cerebras Inference

Format

Text-first

Lines

Sections

Linked challenge

Real-time AI Newsroom Pod with Mastra AI and Cerebras Inference

Prompt source

Original prompt text with formatting preserved for inspection.

1 lines

1 sections

No variables

0 checklist items

Write the TypeScript configuration for the Mastra agent to use Cerebras Inference. Set the model to 'llama-3.1-70b' (or the fastest available) and define a system prompt focused on concise, fact-based summarization.

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

Real-time AI Newsroom Pod with Mastra AI and Cerebras Inference

In light of the BBC leadership change and newsroom security concerns, this challenge focuses on building a high-speed, secure newsroom pod. You will use Mastra AI to orchestrate a workflow that ingests live news feeds and securely summarizes them. To achieve near-instant latency, you will leverage Cerebras Inference for the summarization tasks. A GPT-5.4 Pro agent will act as the Senior Editor, performing deep reasoning on source reliability and cross-referencing, while a Claude Sonnet 4.6.6 agent will handle the creative drafting and formatting of news briefs. The entire infrastructure will be deployed using Baseten for efficient model serving and custom logic runtime.

Open challenge

Related prompts

Browse library

Initial Assessment Prompt

planning

Content Classification Prompt

implementation

Problem Definition and Requirements Gathering

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