# Code Capsule A blog by Emmanuel Goossaert This is one page of public article previews, not the complete archive. Follow Next page to continue. Summaries are not the original full articles. ## What I worry about with AI DevFeed: [What I worry about with AI]() Original publisher: [Read original article]() Author: Emmanuel Goossaert Published: 2026-09-03T19:56:54Z Content type: opinion Language: en Sources: [Code Capsule]() Topics: [Artificial Intelligence](), [Software Engineering](), [trust]() Tags: [ai](), [ai-ai-isolation-llm-loneliness](), [covid-19](), [critical-thinking](), [dopamine-loops](), [isolation](), [llm](), [loneliness](), [mental-health](), [relationships](), [self-awareness](), [society](), [technology]() ### AI overview A personal reflection on how AI and addictive technology may weaken human empathy, relationships, and appreciation of in-person connection. The author argues that AI may eventually automate software engineering once code correctness can be ensured reliably at scale, but is more concerned about loneliness, isolation, and self-absorbed social behavior. ### Source excerpt My reflection on societal isolation amplified by technology and COVID-19, and what to do to foster genuine relationships, critical thinking, and self-awareness to combat loneliness. The post What I worry about with AI first appeared on Code Capsule. ## Requirements-as-Code for AI-Augmented Software Engineers DevFeed: [Requirements-as-Code for AI-Augmented Software Engineers]() Original publisher: [Read original article]() Author: Emmanuel Goossaert Published: 2025-04-22T14:11:56Z Content type: opinion Language: en Sources: [Code Capsule]() Topics: [User Stories](), [AI Models](), [Large Language Model](), [Vibe coding](), [Software Engineering]() Tags: [acceptance-tests](), [agentic-ai](), [ai-models](), [requirements](), [software-engineering](), [uncategorized]() ### AI overview This opinion article projects that AI-augmented software engineering may shift emphasis from writing code in programming languages to specifying requirements in PRDs and acceptance tests, a practice the author calls "requirements-as-code." It compares this workflow with product managers relying on engineers and describes possible use of LLMs and agentic AI systems to generate, revise, and test software against stated requirements. ### Source excerpt Most content about AI model predictions is not going to age well given how quickly the frontier is moving on what is possible these days. Yet, I find it useful to write such articles as they form the basis of the ongoing conversations about how those models are going to impact... The post Requirements-as-Code for AI-Augmented Software Engineers first appeared on Code Capsule. ## Solving the Prompt Management Problem DevFeed: [Solving the Prompt Management Problem]() Original publisher: [Read original article]() Author: Emmanuel Goossaert Published: 2025-04-09T11:52:00Z Content type: article Language: en Sources: [Code Capsule]() Topics: [prompt](), [Web](), [JSON](), [ChatGPT](), [Prompt Engineering]() Tags: [agentic-ai](), [ai](), [ai-ai-ai-models-artificial-intelligence-large-language-models-llms-productivity-prompt-engine](), [ai-models](), [artificial-intelligence](), [chatgpt](), [code](), [json](), [large-language-models](), [llms](), [productivity](), [prompt](), [prompt-engineering](), [prompt-library](), [prompting](), [templates](), [web]() ### AI overview The author introduces Prompt Library, a web-based tool for creating, editing, searching, tagging, and composing prompts. It stores data locally, supports JSON export, and may later add prompt history, version comparison, and prompt paths. ### Source excerpt I developed Prompt Library, a web tool for organizing prompts with features like editing, tagging, and exporting. The post Solving the Prompt Management Problem first appeared on Code Capsule. ## My Takeaways on Vibe Coding DevFeed: [My Takeaways on Vibe Coding]() Original publisher: [Read original article]() Author: Emmanuel Goossaert Published: 2025-03-24T21:44:25Z Content type: opinion Language: en Sources: [Code Capsule]() Topics: [Vibe coding](), [ChatGPT](), [Large Language Model](), [OpenAI](), [web applications](), [API](), [Development](), [Node.js](), [PostgreSQL](), [Programming](), [TypeScript](), [Database]() Tags: [ai](), [algorithms-and-programming](), [algorithms-and-programming-ai-artificial-intelligence-chatgpt-llms-openai-programming-vibe-co](), [api](), [applications](), [artificial-intelligence](), [chatgpt](), [development](), [generate](), [html](), [javascript](), [llms](), [node-js](), [openai](), [postgresql](), [programming](), [vibe-coding]() ### AI overview The author describes using OpenAI's o3-mini-high model to build a small TypeScript, Node.js, and PostgreSQL web application that sends ChatGPT conversations and research sessions to an e-reader. Through iterative prompting and error correction, the generated code became functional and well structured, including a bookmarklet. The experience led the author to reflect on vibe coding, trust in LLMs, and the future relationship between human engineers and language models. ### Source excerpt I have used OpenAI's o3-mini-high model to create a web application for transferring ChatGPT conversations to an e-reader, addressing challenges like login barriers. The iterative development experience was smooth, but trust in LLMs is essential, especially for more complex or sensitive applications. Future programming will combine LLMs with human engineers, potentially displacing less skilled positions. The post My Takeaways on Vibe Coding first appeared on Code Capsule. ## Performative Leadership: From Cargo Cults to OKRs DevFeed: [Performative Leadership: From Cargo Cults to OKRs]() Original publisher: [Read original article]() Author: Emmanuel Goossaert Published: 2023-09-25T20:47:50Z Content type: opinion Language: en Sources: [Code Capsule]() Topics: [Agile](), [context](), [Google](), [intel]() Tags: [agile](), [andy-grove](), [business-processes](), [cargo-cults](), [conformity](), [consulting](), [corporate](), [corporate-culture](), [corporate-identity](), [corporate-rituals](), [critical-thinking](), [culture](), [executive-leadership](), [human-psychology](), [industry-standards](), [leadership](), [leadership-and-management](), [leadership-and-management-business-processes-cargo-cults-conformity-corporate-culture-corporate](), [management-practices](), [okrs](), [organization](), [organizational-behavior](), [performative](), [processes](), [rituals](), [workplace-dynamics]() ### AI overview The article argues that leadership tools and organizational practices are often transferred from the local contexts where they worked into other companies through consulting and training, where their original purpose can be lost. It uses OKRs as a central example and states that the author found no empirical evidence that OKRs improve cost efficiency, profits, or stock price, while citing reported difficulties and potential harms from implementation. ### Source excerpt Unveiling the corporate cargo cult and how industry standards shape a homogenized leadership culture. The post Performative Leadership: From Cargo Cults to OKRs first appeared on Code Capsule. ## Part 4: Beyond The Code and What I've Learned - Ethereum Payment DevFeed: [Part 4: Beyond The Code and What I've Learned - Ethereum Payment]() Original publisher: [Read original article]() Author: Emmanuel Goossaert Published: 2022-11-29T19:18:30Z Content type: tutorial Language: en Sources: [Code Capsule]() Topics: [Ethereum](), [Blockchain](), [Code](), [Back end](), [Front end]() Tags: [algorithms-and-programming](), [algorithms-and-programming-blockchain-crypto-ethereum-mongodb-nodejs-payment-programming-typ](), [blockchain](), [code](), [crypto](), [developer](), [developing](), [ethereum](), [functions](), [how-to](), [implementation](), [mongodb](), [networks](), [nodejs](), [payment](), [product-design](), [programming](), [typescript](), [web3]() ### AI overview The fourth and final article in a series reviews lessons from developing a hobby payment system for the Ethereum blockchain. It discusses extending the code, using redundant data providers, implementing couponing, handling Ethereum testing and production networks, and improving automation and safeguards before production use. ### Source excerpt I'm sharing what I've learned while developing this project in terms of tech specificities product design when creating for the blockchain. The post Part 4: Beyond The Code and What I've Learned - Ethereum Payment first appeared on Code Capsule. ## Part 3: Processing Payments - Ethereum Payment DevFeed: [Part 3: Processing Payments - Ethereum Payment]() Original publisher: [Read original article]() Author: Emmanuel Goossaert Published: 2022-11-29T19:18:12Z Content type: tutorial Language: en Sources: [Code Capsule]() Topics: [Ethereum](), [Blockchain](), [web applications](), [API]() Tags: [algorithms-and-programming](), [algorithms-and-programming-blockchain-crypto-ethereum-mongodb-nodejs-payment-system-typescri](), [api](), [blockchain](), [crypto](), [ethereum](), [mongodb](), [nodejs](), [payment](), [processing](), [system](), [typescript](), [web](), [web3]() ### AI overview A tutorial walkthrough of processing and validating payments from a web application on the Ethereum blockchain. It covers server-side prevalidation, submitting purchase transactions, tracking transaction status through polling, and handling successful or failed payments. ### Source excerpt A walkthrough of the steps needed to process and validate payments from a web application on the Ethereum blockchain. The post Part 3: Processing Payments - Ethereum Payment first appeared on Code Capsule.