Best of Prompt Engineering — September 2025

  1. 1
    Article
    Avatar of bytebytegoByteByteGo·34w

    How Anthropic Built a Multi-Agent Research System

    Anthropic built a multi-agent research system using an orchestrator-worker pattern with a Lead Researcher agent coordinating specialized subagents and a Citation Agent for accuracy. The system outperformed single-agent setups by 90% through parallel processing and dynamic adaptation, though it consumes 15x more tokens. Key engineering principles include proper prompt design, delegation strategies, effort scaling, and parallelization. Production challenges involve managing stateful agents, debugging non-deterministic behavior, and handling deployments without breaking running tasks.

  2. 2
    Article
    Avatar of ergq3auoeReinier·36w

    Context Engineering, Clearly Explained

    Context engineering is a framework that encompasses prompts, memory, files, tools, and retrieval-augmented generation (RAG) to optimize how large language models generate responses. Unlike prompt engineering which focuses solely on input text, context engineering considers the entire information ecosystem that influences AI outputs, providing a more comprehensive approach to building reliable agentic systems and improving AI conversation consistency.

  3. 3
    Article
    Avatar of hnHacker News·35w

    Awesome-Nano-Banana-images/README_en.md at main · PicoTrex/Awesome-Nano-Banana-images

    A comprehensive collection of 68 creative use cases showcasing Nano Banana's AI image generation and editing capabilities. The repository demonstrates diverse applications including character design, photo manipulation, style transfer, 3D rendering, product visualization, and multi-image fusion. Each case includes detailed prompts and examples for tasks like converting illustrations to figures, generating ground views from maps, creating AR annotations, designing custom stickers, and transforming photos into various artistic styles.

  4. 4
    Article
    Avatar of tdsTowards Data Science·35w

    Building Research Agents for Tech Insights

    A comprehensive guide to building specialized AI research agents that can aggregate and analyze tech content from multiple sources. The approach uses structured workflows, data caching, and prompt chaining to create personalized tech reports. Key components include preprocessing data pipelines, strategic use of small vs large language models for cost optimization, and structured JSON outputs for reliability. The system fetches trending keywords, processes facts from tech forums, and generates themed reports based on user profiles.

  5. 5
    Video
    Avatar of vscodeVisual Studio Code·34w

    Refactor an Existing Codebase using Prompt Driven Development

    A practical demonstration of using GitHub Copilot and prompt-driven development to refactor an existing Python inventory API. The tutorial shows how to separate business logic from database operations by moving code from CRUD layers to service layers, using structured prompts and copilot instructions to guide the AI through the refactoring process. The example includes setting up copilot instructions, creating prompt files, and validating the refactored code through manual testing.

  6. 6
    Video
    Avatar of youtubeYouTube·36w

    How to Get Ahead of 99% of People (with AI)

    A comprehensive guide to advanced ChatGPT techniques including creating master prompts (personal context documents), system prompts (behavior definitions), project folders for organized context, canvas feature for iterative editing, custom instructions for consistent formatting, and custom GPTs for reusable workflows. The approach focuses on providing AI with detailed context about your role, preferences, and goals to generate more accurate and personalized outputs.

See all Prompt Engineering archives