home.social

#softwarearchitecture — Public Fediverse posts

Live and recent posts from across the Fediverse tagged #softwarearchitecture, aggregated by home.social.

  1. #AICodingAgents can move fast. But… your architecture might not survive the ride!

    Speed without architectural guardrails can create new problems. Give agents the context they need to meet quality goals - and use them to explore, validate & evolve software architecture.

    In this #InfoQ article, Pierre Pureur, Kurt Bittner & Todd Miller share practical guidance for making AI Coding Agents work with architecture, not around it.

    🔗 Read now: infoq.com/articles/ai-agents-i

    #AI #SoftwareArchitecture

  2. #AICodingAgents can move fast. But… your architecture might not survive the ride!

    Speed without architectural guardrails can create new problems. Give agents the context they need to meet quality goals - and use them to explore, validate & evolve software architecture.

    In this #InfoQ article, Pierre Pureur, Kurt Bittner & Todd Miller share practical guidance for making AI Coding Agents work with architecture, not around it.

    🔗 Read now: infoq.com/articles/ai-agents-i

    #AI #SoftwareArchitecture

  3. #AICodingAgents can move fast. But… your architecture might not survive the ride!

    Speed without architectural guardrails can create new problems. Give agents the context they need to meet quality goals - and use them to explore, validate & evolve software architecture.

    In this #InfoQ article, Pierre Pureur, Kurt Bittner & Todd Miller share practical guidance for making AI Coding Agents work with architecture, not around it.

    🔗 Read now: infoq.com/articles/ai-agents-i

    #AI #SoftwareArchitecture

  4. #AICodingAgents can move fast. But… your architecture might not survive the ride!

    Speed without architectural guardrails can create new problems. Give agents the context they need to meet quality goals - and use them to explore, validate & evolve software architecture.

    In this #InfoQ article, Pierre Pureur, Kurt Bittner & Todd Miller share practical guidance for making AI Coding Agents work with architecture, not around it.

    🔗 Read now: infoq.com/articles/ai-agents-i

    #AI #SoftwareArchitecture

  5. can move fast. But… your architecture might not survive the ride!

    Speed without architectural guardrails can create new problems. Give agents the context they need to meet quality goals - and use them to explore, validate & evolve software architecture.

    In this article, Pierre Pureur, Kurt Bittner & Todd Miller share practical guidance for making AI Coding Agents work with architecture, not around it.

    🔗 Read now: infoq.com/articles/ai-agents-i

  6. Your documentation explains how the system works but does it explain why it was built that way?
    From the DjangoCon US archives, Juan Saavedra introduces Architectural Decision Records and a sustainable way to preserve technical context.
    Watch: youtu.be/_-0zHdJGTlw
    #Django #SoftwareArchitecture

  7. Your documentation explains how the system works but does it explain why it was built that way?
    From the DjangoCon US archives, Juan Saavedra introduces Architectural Decision Records and a sustainable way to preserve technical context.
    Watch: youtu.be/_-0zHdJGTlw

  8. Your documentation explains how the system works but does it explain why it was built that way?
    From the DjangoCon US archives, Juan Saavedra introduces Architectural Decision Records and a sustainable way to preserve technical context.
    Watch: youtu.be/_-0zHdJGTlw
    #Django #SoftwareArchitecture

  9. Your documentation explains how the system works but does it explain why it was built that way?
    From the DjangoCon US archives, Juan Saavedra introduces Architectural Decision Records and a sustainable way to preserve technical context.
    Watch: youtu.be/_-0zHdJGTlw
    #Django #SoftwareArchitecture

  10. Your documentation explains how the system works but does it explain why it was built that way?
    From the DjangoCon US archives, Juan Saavedra introduces Architectural Decision Records and a sustainable way to preserve technical context.
    Watch: youtu.be/_-0zHdJGTlw
    #Django #SoftwareArchitecture

  11. the-well-architected-cloud.com

    TypeSafe released Jev, a "decision model" that's "just like an LLM, but not an LLM". They didn't share how it works.

    So I guessed. My hypothesis: it's a regular LLM that stops before generating text and reports how likely each option is to continue the prompt.

    To test it, I built Jeb: an unmodified LLM, llama.cpp and the raw next-token probabilities. It works. It picks better than random, and yes, it plays Doom.

    Later I found that privatemode.ai had arrived at a similar approach independently. Science and progress have always relied on access to information.

    Also in this issue: a small fable about the first rule of cloud-native. One slow S3 write froze my entire blog, and it was a reminder that a system is only as strong as its weakest link. It's worse when the whole thing is just one link.

    The code is on github under dooreelko/jeb

    #AI #LLM #MachineLearning #OpenSource #llamacpp #CloudNative #AWS #Serverless #SoftwareArchitecture #Reliability

  12. the-well-architected-cloud.com

    TypeSafe released Jev, a "decision model" that's "just like an LLM, but not an LLM". They didn't share how it works.

    So I guessed. My hypothesis: it's a regular LLM that stops before generating text and reports how likely each option is to continue the prompt.

    To test it, I built Jeb: an unmodified LLM, llama.cpp and the raw next-token probabilities. It works. It picks better than random, and yes, it plays Doom.

    Later I found that privatemode.ai had arrived at a similar approach independently. Science and progress have always relied on access to information.

    Also in this issue: a small fable about the first rule of cloud-native. One slow S3 write froze my entire blog, and it was a reminder that a system is only as strong as its weakest link. It's worse when the whole thing is just one link.

    The code is on github under dooreelko/jeb

    #AI #LLM #MachineLearning #OpenSource #llamacpp #CloudNative #AWS #Serverless #SoftwareArchitecture #Reliability

  13. the-well-architected-cloud.com

    TypeSafe released Jev, a "decision model" that's "just like an LLM, but not an LLM". They didn't share how it works.

    So I guessed. My hypothesis: it's a regular LLM that stops before generating text and reports how likely each option is to continue the prompt.

    To test it, I built Jeb: an unmodified LLM, llama.cpp and the raw next-token probabilities. It works. It picks better than random, and yes, it plays Doom.

    Later I found that privatemode.ai had arrived at a similar approach independently. Science and progress have always relied on access to information.

    Also in this issue: a small fable about the first rule of cloud-native. One slow S3 write froze my entire blog, and it was a reminder that a system is only as strong as its weakest link. It's worse when the whole thing is just one link.

    The code is on github under dooreelko/jeb

  14. the-well-architected-cloud.com

    TypeSafe released Jev, a "decision model" that's "just like an LLM, but not an LLM". They didn't share how it works.

    So I guessed. My hypothesis: it's a regular LLM that stops before generating text and reports how likely each option is to continue the prompt.

    To test it, I built Jeb: an unmodified LLM, llama.cpp and the raw next-token probabilities. It works. It picks better than random, and yes, it plays Doom.

    Later I found that privatemode.ai had arrived at a similar approach independently. Science and progress have always relied on access to information.

    Also in this issue: a small fable about the first rule of cloud-native. One slow S3 write froze my entire blog, and it was a reminder that a system is only as strong as its weakest link. It's worse when the whole thing is just one link.

    The code is on github under dooreelko/jeb

    #AI #LLM #MachineLearning #OpenSource #llamacpp #CloudNative #AWS #Serverless #SoftwareArchitecture #Reliability

  15. the-well-architected-cloud.com

    TypeSafe released Jev, a "decision model" that's "just like an LLM, but not an LLM". They didn't share how it works.

    So I guessed. My hypothesis: it's a regular LLM that stops before generating text and reports how likely each option is to continue the prompt.

    To test it, I built Jeb: an unmodified LLM, llama.cpp and the raw next-token probabilities. It works. It picks better than random, and yes, it plays Doom.

    Later I found that privatemode.ai had arrived at a similar approach independently. Science and progress have always relied on access to information.

    Also in this issue: a small fable about the first rule of cloud-native. One slow S3 write froze my entire blog, and it was a reminder that a system is only as strong as its weakest link. It's worse when the whole thing is just one link.

    The code is on github under dooreelko/jeb

    #AI #LLM #MachineLearning #OpenSource #llamacpp #CloudNative #AWS #Serverless #SoftwareArchitecture #Reliability

  16. Beslissingen over software-architectuur horen bij de duurste keuzes van een bedrijf, maar worden vaak genomen op basis van onderbuikgevoel. 💡

    Door statische analyse en historisch onderzoek op je repository uit te voeren, zet je meningen om in harde feiten over technische schuld en risico's.

    🔗 dawn.tech/publicatie/hoe-je-jo

    #softwarearchitecture #codebaseanalyse #techschuld #devops #datadriven #dawntechnology

  17. What bridges the gap between an AI demo and a production agent? The Agent Harness.

    In this #InfoQ article, Trista Pan compares two ways to build a finance assistant - using a fully managed AWS AgentCore Harness VS. a self-managed LangChain + Envoy AI Gateway setup.

    Key trade-offs analyzed: operational ownership, portability, and engineering effort.

    🔗 Read now: infoq.com/articles/agent-harne

    #AI #AIAgents #AgenticAI #SoftwareArchitecture

  18. What bridges the gap between an AI demo and a production agent? The Agent Harness.

    In this #InfoQ article, Trista Pan compares two ways to build a finance assistant - using a fully managed AWS AgentCore Harness VS. a self-managed LangChain + Envoy AI Gateway setup.

    Key trade-offs analyzed: operational ownership, portability, and engineering effort.

    🔗 Read now: infoq.com/articles/agent-harne

    #AI #AIAgents #AgenticAI #SoftwareArchitecture

  19. What bridges the gap between an AI demo and a production agent? The Agent Harness.

    In this #InfoQ article, Trista Pan compares two ways to build a finance assistant - using a fully managed AWS AgentCore Harness VS. a self-managed LangChain + Envoy AI Gateway setup.

    Key trade-offs analyzed: operational ownership, portability, and engineering effort.

    🔗 Read now: infoq.com/articles/agent-harne

    #AI #AIAgents #AgenticAI #SoftwareArchitecture

  20. What bridges the gap between an AI demo and a production agent? The Agent Harness.

    In this #InfoQ article, Trista Pan compares two ways to build a finance assistant - using a fully managed AWS AgentCore Harness VS. a self-managed LangChain + Envoy AI Gateway setup.

    Key trade-offs analyzed: operational ownership, portability, and engineering effort.

    🔗 Read now: infoq.com/articles/agent-harne

    #AI #AIAgents #AgenticAI #SoftwareArchitecture

  21. What bridges the gap between an AI demo and a production agent? The Agent Harness.

    In this article, Trista Pan compares two ways to build a finance assistant - using a fully managed AWS AgentCore Harness VS. a self-managed LangChain + Envoy AI Gateway setup.

    Key trade-offs analyzed: operational ownership, portability, and engineering effort.

    🔗 Read now: infoq.com/articles/agent-harne

  22. #Cloudflare moved its main blog from WordPress to EmDash - its #opensource TypeScript CMS.

    A proxy Worker shifted traffic from 1% to 100% in a single day, with automatic fallback to WordPress.

    Running on Cloudflare Workers, the setup uses dual caching layers and was load-tested to 7,000 RPS.

    🔗 Read more: infoq.com/news/2026/09/cloudfl

    #InfoQ #SoftwareArchitecture #Caching #Migration

  23. #Cloudflare moved its main blog from WordPress to EmDash - its #opensource TypeScript CMS.

    A proxy Worker shifted traffic from 1% to 100% in a single day, with automatic fallback to WordPress.

    Running on Cloudflare Workers, the setup uses dual caching layers and was load-tested to 7,000 RPS.

    🔗 Read more: infoq.com/news/2026/09/cloudfl

    #InfoQ #SoftwareArchitecture #Caching #Migration

  24. #Cloudflare moved its main blog from WordPress to EmDash - its #opensource TypeScript CMS.

    A proxy Worker shifted traffic from 1% to 100% in a single day, with automatic fallback to WordPress.

    Running on Cloudflare Workers, the setup uses dual caching layers and was load-tested to 7,000 RPS.

    🔗 Read more: infoq.com/news/2026/09/cloudfl

    #InfoQ #SoftwareArchitecture #Caching #Migration

  25. #Cloudflare moved its main blog from WordPress to EmDash - its #opensource TypeScript CMS.

    A proxy Worker shifted traffic from 1% to 100% in a single day, with automatic fallback to WordPress.

    Running on Cloudflare Workers, the setup uses dual caching layers and was load-tested to 7,000 RPS.

    🔗 Read more: infoq.com/news/2026/09/cloudfl

    #InfoQ #SoftwareArchitecture #Caching #Migration

  26. moved its main blog from WordPress to EmDash - its TypeScript CMS.

    A proxy Worker shifted traffic from 1% to 100% in a single day, with automatic fallback to WordPress.

    Running on Cloudflare Workers, the setup uses dual caching layers and was load-tested to 7,000 RPS.

    🔗 Read more: infoq.com/news/2026/09/cloudfl

  27. Nuevo video en el canal 🚀 Si te interesa el mundo de Linux, los entornos terminal-driven y la arquitectura de software, esto te va a volar la cabeza.

    Miralo completo acá 💻👇
    🔗 youtu.be/KZnNbuUwtTM

    #Linux #ArchLinux #DevLife #SoftwareArchitecture

  28. Nuevo video en el canal 🚀 Si te interesa el mundo de Linux, los entornos terminal-driven y la arquitectura de software, esto te va a volar la cabeza.

    Miralo completo acá 💻👇
    🔗 youtu.be/KZnNbuUwtTM

    #Linux #ArchLinux #DevLife #SoftwareArchitecture

  29. 𝗧𝗵𝗲 𝗶𝗦𝗔𝗤𝗕 𝗚𝗲𝗻𝗲𝗿𝗮𝗹 𝗔𝘀𝘀𝗲𝗺𝗯𝗹𝘆 2026 𝗶𝘀 𝘂𝗻𝗱𝗲𝗿𝘄𝗮𝘆 𝗶𝗻 𝗘𝗿𝗳𝘂𝗿𝘁, 𝗚𝗲𝗿𝗺𝗮𝗻𝘆!🤝
    Today and tomorrow, 28–29 September, our members are coming together for the annual General Assembly of iSAQB e.V.

    We are looking back at the past year, discussing the challenges ahead and shaping our strategy for the future.

    We look forward to two days of thoughtful discussion and exchange. Thank you to all our members for contributing their time and expertise. 🙏

    #iSAQB #SoftwareArchitecture #Certification #GeneralAssembly

  30. 𝗧𝗵𝗲 𝗶𝗦𝗔𝗤𝗕 𝗚𝗲𝗻𝗲𝗿𝗮𝗹 𝗔𝘀𝘀𝗲𝗺𝗯𝗹𝘆 2026 𝗶𝘀 𝘂𝗻𝗱𝗲𝗿𝘄𝗮𝘆 𝗶𝗻 𝗘𝗿𝗳𝘂𝗿𝘁, 𝗚𝗲𝗿𝗺𝗮𝗻𝘆!🤝
    Today and tomorrow, 28–29 September, our members are coming together for the annual General Assembly of iSAQB e.V.

    We are looking back at the past year, discussing the challenges ahead and shaping our strategy for the future.

    We look forward to two days of thoughtful discussion and exchange. Thank you to all our members for contributing their time and expertise. 🙏

    #iSAQB #SoftwareArchitecture #Certification #GeneralAssembly

  31. 𝗧𝗵𝗲 𝗶𝗦𝗔𝗤𝗕 𝗚𝗲𝗻𝗲𝗿𝗮𝗹 𝗔𝘀𝘀𝗲𝗺𝗯𝗹𝘆 2026 𝗶𝘀 𝘂𝗻𝗱𝗲𝗿𝘄𝗮𝘆 𝗶𝗻 𝗘𝗿𝗳𝘂𝗿𝘁, 𝗚𝗲𝗿𝗺𝗮𝗻𝘆!🤝
    Today and tomorrow, 28–29 September, our members are coming together for the annual General Assembly of iSAQB e.V.

    We are looking back at the past year, discussing the challenges ahead and shaping our strategy for the future.

    We look forward to two days of thoughtful discussion and exchange. Thank you to all our members for contributing their time and expertise. 🙏

    #iSAQB #SoftwareArchitecture #Certification #GeneralAssembly

  32. 𝗧𝗵𝗲 𝗶𝗦𝗔𝗤𝗕 𝗚𝗲𝗻𝗲𝗿𝗮𝗹 𝗔𝘀𝘀𝗲𝗺𝗯𝗹𝘆 2026 𝗶𝘀 𝘂𝗻𝗱𝗲𝗿𝘄𝗮𝘆 𝗶𝗻 𝗘𝗿𝗳𝘂𝗿𝘁, 𝗚𝗲𝗿𝗺𝗮𝗻𝘆!🤝
    Today and tomorrow, 28–29 September, our members are coming together for the annual General Assembly of iSAQB e.V.

    We are looking back at the past year, discussing the challenges ahead and shaping our strategy for the future.

    We look forward to two days of thoughtful discussion and exchange. Thank you to all our members for contributing their time and expertise. 🙏

    #iSAQB #SoftwareArchitecture #Certification #GeneralAssembly

  33. “Same input, same output.” Then we put LLMs in the middle. 🤷

    At #BaselOne26, Sepehr Samadi shows five architecture patterns for reducing non-determinism and building reliable, auditable systems around probabilistic #AI behaviour.

    No #ML expertise required – this is systems architecture for engineers integrating LLMs into production systems.

    👉 Programme: baselone.org/#programm
    🎟️ Tickets: eventfrog.ch/BaselOne26

    #SoftwareArchitecture #LLM #AIEngineering #BaselOne

  34. “Same input, same output.” Then we put LLMs in the middle. 🤷

    At #BaselOne26, Sepehr Samadi shows five architecture patterns for reducing non-determinism and building reliable, auditable systems around probabilistic #AI behaviour.

    No #ML expertise required – this is systems architecture for engineers integrating LLMs into production systems.

    👉 Programme: baselone.org/#programm
    🎟️ Tickets: eventfrog.ch/BaselOne26

    #SoftwareArchitecture #LLM #AIEngineering #BaselOne

  35. “Same input, same output.” Then we put LLMs in the middle. 🤷

    At #BaselOne26, Sepehr Samadi shows five architecture patterns for reducing non-determinism and building reliable, auditable systems around probabilistic #AI behaviour.

    No #ML expertise required – this is systems architecture for engineers integrating LLMs into production systems.

    👉 Programme: baselone.org/#programm
    🎟️ Tickets: eventfrog.ch/BaselOne26

    #SoftwareArchitecture #LLM #AIEngineering #BaselOne

  36. “Same input, same output.” Then we put LLMs in the middle. 🤷

    At #BaselOne26, Sepehr Samadi shows five architecture patterns for reducing non-determinism and building reliable, auditable systems around probabilistic #AI behaviour.

    No #ML expertise required – this is systems architecture for engineers integrating LLMs into production systems.

    👉 Programme: baselone.org/#programm
    🎟️ Tickets: eventfrog.ch/BaselOne26

    #SoftwareArchitecture #LLM #AIEngineering #BaselOne

  37. “Same input, same output.” Then we put LLMs in the middle. 🤷

    At #BaselOne26, Sepehr Samadi shows five architecture patterns for reducing non-determinism and building reliable, auditable systems around probabilistic #AI behaviour.

    No #ML expertise required – this is systems architecture for engineers integrating LLMs into production systems.

    👉 Programme: baselone.org/#programm
    🎟️ Tickets: eventfrog.ch/BaselOne26

    #SoftwareArchitecture #LLM #AIEngineering #BaselOne

  38. #Cloudflare just redesigned the in-memory representation of its Big Pineapple DNS cache, dropping memory footprint by 56% per entry & freeing ~100 TB fleetwide.

    Key highlights:
    ➤ 43% higher cache insertion throughput
    ➤ 19% lower lookup latency
    ➤ More cache capacity without more memory

    🔗 Full write-up on #InfoQ - infoq.com/news/2026/09/cloudfl

    #RustLang #SoftwareArchitecture #DistributedSystems #Performance #DNS

  39. #Cloudflare just redesigned the in-memory representation of its Big Pineapple DNS cache, dropping memory footprint by 56% per entry & freeing ~100 TB fleetwide.

    Key highlights:
    ➤ 43% higher cache insertion throughput
    ➤ 19% lower lookup latency
    ➤ More cache capacity without more memory

    🔗 Full write-up on #InfoQ - infoq.com/news/2026/09/cloudfl

    #RustLang #SoftwareArchitecture #DistributedSystems #Performance #DNS

  40. #Cloudflare just redesigned the in-memory representation of its Big Pineapple DNS cache, dropping memory footprint by 56% per entry & freeing ~100 TB fleetwide.

    Key highlights:
    ➤ 43% higher cache insertion throughput
    ➤ 19% lower lookup latency
    ➤ More cache capacity without more memory

    🔗 Full write-up on #InfoQ - infoq.com/news/2026/09/cloudfl

    #RustLang #SoftwareArchitecture #DistributedSystems #Performance #DNS

  41. #Cloudflare just redesigned the in-memory representation of its Big Pineapple DNS cache, dropping memory footprint by 56% per entry & freeing ~100 TB fleetwide.

    Key highlights:
    ➤ 43% higher cache insertion throughput
    ➤ 19% lower lookup latency
    ➤ More cache capacity without more memory

    🔗 Full write-up on #InfoQ - infoq.com/news/2026/09/cloudfl

    #RustLang #SoftwareArchitecture #DistributedSystems #Performance #DNS

  42. just redesigned the in-memory representation of its Big Pineapple DNS cache, dropping memory footprint by 56% per entry & freeing ~100 TB fleetwide.

    Key highlights:
    ➤ 43% higher cache insertion throughput
    ➤ 19% lower lookup latency
    ➤ More cache capacity without more memory

    🔗 Full write-up on - infoq.com/news/2026/09/cloudfl