home.social

#agenticengineering — Public Fediverse posts

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

  1. Detailed plans can make coding agents look aligned while hiding guesses.

    Architectural probes do the opposite: fake software that reveals structure before implementation, then evolves step by step.

    amolnotes.substack.com/p/stop-

  2. The 10x engineer is a lie (once more)

    Every new technology wave resurrects the 10x engineer myth. This time it's agentic engineering. Here's why the 10x engineer is real but will never be your employee - and why 2-3x is the honest, achievable goal worth chasing.

    #10xEngineer #AgenticEngineering #AIProductivity

    https://schlitt.info/blog/0798_10x_engineer_lie.html

  3. The 10x engineer is a lie (once more)

    Every new technology wave resurrects the 10x engineer myth. This time it's agentic engineering. Here's why the 10x engineer is real but will never be your employee - and why 2-3x is the honest, achievable goal worth chasing.

    #10xEngineer #AgenticEngineering #AIProductivity

    https://schlitt.info/blog/0798_10x_engineer_lie.html

  4. The 10x engineer is a lie (once more)

    Every new technology wave resurrects the 10x engineer myth. This time it's agentic engineering. Here's why the 10x engineer is real but will never be your employee - and why 2-3x is the honest, achievable goal worth chasing.

    #10xEngineer #AgenticEngineering #AIProductivity

    https://schlitt.info/blog/0798_10x_engineer_lie.html

  5. The 10x engineer is a lie (once more)

    Every new technology wave resurrects the 10x engineer myth. This time it's agentic engineering. Here's why the 10x engineer is real but will never be your employee - and why 2-3x is the honest, achievable goal worth chasing.

    #10xEngineer #AgenticEngineering #AIProductivity

    https://schlitt.info/blog/0798_10x_engineer_lie.html

  6. The 10x engineer is a lie (once more)

    Every new technology wave resurrects the 10x engineer myth. This time it's agentic engineering. Here's why the 10x engineer is real but will never be your employee - and why 2-3x is the honest, achievable goal worth chasing.

    #10xEngineer #AgenticEngineering #AIProductivity

    https://schlitt.info/blog/0798_10x_engineer_lie.html

  7. I wrote up how I think AppSec teams can adapt to and benefit from agentic engineering and its effects on the SDLC: Move from detection to mitigation. Become engineers, not gatekeepers. Partner with SRE and platform engineering.

    janbrennenstuhl.eu/appsec-agen

    #sdlc #appsec #agenticengineering

  8. I wrote up how I think AppSec teams can adapt to and benefit from agentic engineering and its effects on the SDLC: Move from detection to mitigation. Become engineers, not gatekeepers. Partner with SRE and platform engineering.

    janbrennenstuhl.eu/appsec-agen

    #sdlc #appsec #agenticengineering

  9. I wrote up how I think AppSec teams can adapt to and benefit from agentic engineering and its effects on the SDLC: Move from detection to mitigation. Become engineers, not gatekeepers. Partner with SRE and platform engineering.

    janbrennenstuhl.eu/appsec-agen

    #sdlc #appsec #agenticengineering

  10. I wrote up how I think AppSec teams can adapt to and benefit from agentic engineering and its effects on the SDLC: Move from detection to mitigation. Become engineers, not gatekeepers. Partner with SRE and platform engineering.

    janbrennenstuhl.eu/appsec-agen

    #sdlc #appsec #agenticengineering

  11. The new 10x Engineer with AI

    The idea of the “10x engineer” has always been a bit controversial. Some people see it as a myth. Some people see it as a harmful label that creates hero culture. Some people have worked with engineers who clearly create much more impact than others, and believe the idea is real. I sit somewhere in the middle. I don’t think a 10x engineer means someone who writes 10x more code than everyone else. That version of the idea was never useful to me. Writing more code is not the same as […]

    codeaholicguy.com/2026/05/13/t

  12. The new 10x Engineer with AI

    The idea of the “10x engineer” has always been a bit controversial. Some people see it as a myth. Some people see it as a harmful label that creates hero culture. Some people have worked with engineers who clearly create much more impact than others, and believe the idea is real. I sit somewhere in the middle. I don’t think a 10x engineer means someone who writes 10x more code than everyone else. That version of the idea was never useful to me. Writing more code is not the same as […]

    codeaholicguy.com/2026/05/13/t

  13. The new 10x Engineer with AI

    The idea of the “10x engineer” has always been a bit controversial. Some people see it as a myth. Some people see it as a harmful label that creates hero culture. Some people have worked with engineers who clearly create much more impact than others, and believe the idea is real. I sit somewhere in the middle. I don’t think a 10x engineer means someone who writes 10x more code than everyone else. That version of the idea was never useful to me. Writing more code is not the same as […]

    codeaholicguy.com/2026/05/13/t

  14. The new 10x Engineer with AI

    The idea of the “10x engineer” has always been a bit controversial. Some people see it as a myth. Some people see it as a harmful label that creates hero culture. Some people have worked with engineers who clearly create much more impact than others, and believe the idea is real. I sit somewhere in the middle. I don’t think a 10x engineer means someone who writes 10x more code than everyone else. That version of the idea was never useful to me. Writing more code is not the same as […]

    codeaholicguy.com/2026/05/13/t

  15. The new 10x Engineer with AI

    The idea of the “10x engineer” has always been a bit controversial. Some people see it as a myth. Some people see it as a harmful label that creates hero culture. Some people have worked with engineers who clearly create much more impact than others, and believe the idea is real. I sit somewhere in the middle. I don’t think a 10x engineer means someone who writes 10x more code than everyone else. That version of the idea was never useful to me. Writing more code is not the same as […]

    codeaholicguy.com/2026/05/13/t

  16. Ah, the mystical world of "Agentic Engineering" 🌟, where humans take a backseat and AI goes on a reckless coding joyride 🚗💨! Turns out, tossing your keyboard to a machine and hoping for the best isn't quite the disciplined engineering marvel some claim it to be. But hey, who needs precision when you can just vibe your way to a half-baked prototype? 🤷‍♂️
    addyosmani.com/blog/agentic-en #AgenticEngineering #AIJoyride #RecklessCoding #PrototypeVibes #TechHumor #HackerNews #ngated

  17. Ah, the mystical world of "Agentic Engineering" 🌟, where humans take a backseat and AI goes on a reckless coding joyride 🚗💨! Turns out, tossing your keyboard to a machine and hoping for the best isn't quite the disciplined engineering marvel some claim it to be. But hey, who needs precision when you can just vibe your way to a half-baked prototype? 🤷‍♂️
    addyosmani.com/blog/agentic-en #AgenticEngineering #AIJoyride #RecklessCoding #PrototypeVibes #TechHumor #HackerNews #ngated

  18. Ah, the mystical world of "Agentic Engineering" 🌟, where humans take a backseat and AI goes on a reckless coding joyride 🚗💨! Turns out, tossing your keyboard to a machine and hoping for the best isn't quite the disciplined engineering marvel some claim it to be. But hey, who needs precision when you can just vibe your way to a half-baked prototype? 🤷‍♂️
    addyosmani.com/blog/agentic-en #AgenticEngineering #AIJoyride #RecklessCoding #PrototypeVibes #TechHumor #HackerNews #ngated

  19. Ah, the mystical world of "Agentic Engineering" 🌟, where humans take a backseat and AI goes on a reckless coding joyride 🚗💨! Turns out, tossing your keyboard to a machine and hoping for the best isn't quite the disciplined engineering marvel some claim it to be. But hey, who needs precision when you can just vibe your way to a half-baked prototype? 🤷‍♂️
    addyosmani.com/blog/agentic-en #AgenticEngineering #AIJoyride #RecklessCoding #PrototypeVibes #TechHumor #HackerNews #ngated

  20. Ah, the mystical world of "Agentic Engineering" 🌟, where humans take a backseat and AI goes on a reckless coding joyride 🚗💨! Turns out, tossing your keyboard to a machine and hoping for the best isn't quite the disciplined engineering marvel some claim it to be. But hey, who needs precision when you can just vibe your way to a half-baked prototype? 🤷‍♂️
    addyosmani.com/blog/agentic-en #AgenticEngineering #AIJoyride #RecklessCoding #PrototypeVibes #TechHumor #HackerNews #ngated

  21. Now that vibe-coding and agentic engineering are converging, the marker of quality is shifting towards how extensively the application is actually being used in production.

    #AI #AgenticEngineering #vibecoding #softwaredevelopment #programming

    simonwillison.net/2026/May/6/v

  22. 🤖🎧 Oh wow, Simon discovered that saying "vibe coding" and "agentic engineering" enough times on a podcast means they're actually the same thing now. 🚀🔍 Apparently, talking out loud also reveals groundbreaking thoughts—who would've guessed?! 💡🙄
    simonwillison.net/2026/May/6/v #vibecoding #agenticengineering #podcastthoughts #groundbreakingideas #innovation #HackerNews #ngated

  23. Roche Linux, MCP, and Agentic Engineering: These were the three topics at the first TechTalkThursday of 2026. 🥳 Once again, the event took place on a Tuesday, making it a TechTalkTuesday. 📹 You can find the recording here youtube.com/watch?v=B9_weIWteGA on our YouTube channel. 👉 The next TechTalkThursday will take place on June 3 – register now: meetup.com/ninetechtalkthursda #techtalkthursday #rochelinux #mcp #agenticengineering #nine

  24. Roche Linux, MCP, and Agentic Engineering: These were the three topics at the first TechTalkThursday of 2026. 🥳 Once again, the event took place on a Tuesday, making it a TechTalkTuesday. 📹 You can find the recording here youtube.com/watch?v=B9_weIWteGA on our YouTube channel. 👉 The next TechTalkThursday will take place on June 3 – register now: meetup.com/ninetechtalkthursda #techtalkthursday #rochelinux #mcp #agenticengineering #nine

  25. Roche Linux, MCP, and Agentic Engineering: These were the three topics at the first TechTalkThursday of 2026. 🥳 Once again, the event took place on a Tuesday, making it a TechTalkTuesday. 📹 You can find the recording here youtube.com/watch?v=B9_weIWteGA on our YouTube channel. 👉 The next TechTalkThursday will take place on June 3 – register now: meetup.com/ninetechtalkthursda #techtalkthursday #rochelinux #mcp #agenticengineering #nine

  26. Roche Linux, MCP, and Agentic Engineering: These were the three topics at the first TechTalkThursday of 2026. 🥳 Once again, the event took place on a Tuesday, making it a TechTalkTuesday. 📹 You can find the recording here youtube.com/watch?v=B9_weIWteGA on our YouTube channel. 👉 The next TechTalkThursday will take place on June 3 – register now: meetup.com/ninetechtalkthursda #techtalkthursday #rochelinux #mcp #agenticengineering #nine

  27. Also what I noticed is somekind of regression while using the models (same version number). Maybe its paranoia but it's like someone constantly changing it.

    I have no proof of that but since it's a statistical random generator there is no way to be confidence about generated code.
    #AgenticEngineering

  28. Doing some Agentic Programming and it often just goes off the rails, without constant steering it. I have a really hard time to believe these claims as well.

    I also don't believe that writing a Spec (going back to Waterfall) is the solution since it's totally cutting out the feedback loop.

    We came to Agile since things and knowledge just give you a constant change of your perspective.
    #AgenticEngineering

  29. There are lots of misconceptions of what software engineering is, in the field trying to automate it. There are some things I want to make clear here.

    The purpose of software engineering is not to write code. Code is a liability, which will require maintenance for as long as it is used. Less code is better than more code. No code is the best.

    The purpose isn't even to solve tickets. Tickets are a representation of work to be done, yes, but this is from the time when the same people working in the same team, drinking the same coffee wrote and read the tickets, and discussed them freely without any boundaries. This representation of work leans on a mountain of shared silent knowledge. When the shared knowledge isn't shared, the text will be understood differently from how it was written.

    AI agents cannot know about your business unless someone takes time to bring them up to speed, chatting with them interactively. If they know this internally without interrogation, your business is redundant and has been done a thousand times before in the AI agent training materials.

    Removing the experience, the taste, the mentality from the picture will make systems regress to the mean.

    One of the most important processes in software engineering is the flow of knowledge into coded machine usable abstractions. This is not very different from how AIs are trained in general, garbage-in-garbage-out existed before AI models. So, the flow of knowledge needs to be not only of good volume, but also of high fidelity and quality. It is not all the same who you ask for how the cake is baked; it determines the outcome.

    Aggregating high volume, high quality knowledge in pragmatic forms will determine the business and technology topology of the near term future.

    We should not try to optimize for wrong things like numbers of tickets closed. In many things slow is smooth, smooth is fast. Especially in infrastructure and in production databases, changes should not be fast. Doing the correct things is way more important than the speed of doing things.

    If you try to hurry the process of interrogating the domain experts and the software engineers, you're just exhausting them and getting low quality as a result. You'll fail in mining and capturing what truly matters.

    Why not regress to the mean? The point is not only that we can observe the mean in our lives, and then focus on those things to make the next generation of systems better.

    Additionally, our distinctive tastes and ideas, ways of seeing things in themselves are a kind of a seed if nothing else, which allows us to not design the same restaurant with the same menu over and over, but to actually create true, informed variation, trying out different things by different approaches. If you plan a city using a single architect, you get those things where everything looks the same.

    There is value in tapping the uniqueness of vision, and add it on top of the dynamic power of agentic engineering.

    #AI #AgenticEngineering

  30. if you're a developer interested in agentic engineering, I'm starting a newsletter called The Agent Loop.

    I've been running AI agents at the core of my workflow since last summer. What works, what doesn't, and how to keep up in a landscape that's moving faster than ever.

    pixelfolio.app

    #AI #AgenticEngineering #ClaudeCode #Codex #SwiftLang

  31. The age of agentic engineering shifts the bottlenecks in software engineering.

    What we see clearly is that the new bottlenecks become to be about acceptance testing and gathering feedback. There are two sides to managing this new bottleneck:

    1. We need to collect feedback more efficiently and in higher volumes than in the past. User feedback buttons and meeting notes need to be completely utilized to maximize the volume of high quality feedback.

    2. Utilizing the feedback maximally. If you have a system with let's say a native app and a web application and you're trying to keep them in parity and in alignment, if you report a bug in one, Claude Code will happily fix it in one side, and not in the other. Also, it will not proactively look for other places with the same kind of a bug, or examples of similarly ill-designed items. You need to tell it to do these things. This is about maximal utilization of the feedback signal, to let it affect at larger blast radiuses.

    #AI #AgenticEngineering #ClaudeCode

  32. It feels like we’re rediscovering the old ways.

    Next, someone will build a multi-agent system (harness) around a Scrum Master agent who will conduct daily standups for the self-managing team of agents who are complaining about a broken coffee machine.

    youtube.com/watch?v=bJ8F43j1Fqw

    #AIEngineering #softwareengineering #agenticengineering #aiagents

  33. Die Experimente mit mehr als 10 Milliarden Tokens zeigen, dass aktuelle LLM-basierte Coding-Agenten zwar kurzfristig funktionierenden Code erzeugen können, aber deutlich Schwierigkeiten haben, Codequalität über viele Iterationen und Änderungen hinweg stabil zu halten.
    Damit wird gezeigt, dass die derzeitigen Modelle beim langfristigen Software-Maintenance-Problem noch weit hinter den Anforderungen realer Softwareentwicklung zurückliegen.
    #kicoding #agenticengineering
    arxiv.org/abs/2603.03823

  34. Die Experimente mit mehr als 10 Milliarden Tokens zeigen, dass aktuelle LLM-basierte Coding-Agenten zwar kurzfristig funktionierenden Code erzeugen können, aber deutlich Schwierigkeiten haben, Codequalität über viele Iterationen und Änderungen hinweg stabil zu halten.
    Damit wird gezeigt, dass die derzeitigen Modelle beim langfristigen Software-Maintenance-Problem noch weit hinter den Anforderungen realer Softwareentwicklung zurückliegen.
    #kicoding #agenticengineering
    arxiv.org/abs/2603.03823

  35. Die Experimente mit mehr als 10 Milliarden Tokens zeigen, dass aktuelle LLM-basierte Coding-Agenten zwar kurzfristig funktionierenden Code erzeugen können, aber deutlich Schwierigkeiten haben, Codequalität über viele Iterationen und Änderungen hinweg stabil zu halten.
    Damit wird gezeigt, dass die derzeitigen Modelle beim langfristigen Software-Maintenance-Problem noch weit hinter den Anforderungen realer Softwareentwicklung zurückliegen.
    #kicoding #agenticengineering
    arxiv.org/abs/2603.03823

  36. Die Experimente mit mehr als 10 Milliarden Tokens zeigen, dass aktuelle LLM-basierte Coding-Agenten zwar kurzfristig funktionierenden Code erzeugen können, aber deutlich Schwierigkeiten haben, Codequalität über viele Iterationen und Änderungen hinweg stabil zu halten.
    Damit wird gezeigt, dass die derzeitigen Modelle beim langfristigen Software-Maintenance-Problem noch weit hinter den Anforderungen realer Softwareentwicklung zurückliegen.
    #kicoding #agenticengineering
    arxiv.org/abs/2603.03823

  37. Die Experimente mit mehr als 10 Milliarden Tokens zeigen, dass aktuelle LLM-basierte Coding-Agenten zwar kurzfristig funktionierenden Code erzeugen können, aber deutlich Schwierigkeiten haben, Codequalität über viele Iterationen und Änderungen hinweg stabil zu halten.
    Damit wird gezeigt, dass die derzeitigen Modelle beim langfristigen Software-Maintenance-Problem noch weit hinter den Anforderungen realer Softwareentwicklung zurückliegen.
    #kicoding #agenticengineering
    arxiv.org/abs/2603.03823