@devstackdaily.bsky.socialHumanize proposes a multi-agent orchestration workflow for agentic coding that uses judgement engineering with 72 mechanical gates and a Markov-chain framing over repository states. It enforces plan…
#AgenticCoding #SoftwareEngineering #AItools #DeveloperTools
https://arxiv.org/abs/2610.08900
@ocmatos.comSymphonika is my take on orchestrating coding agents: it picks up GitHub issues, runs agents in separate workspaces and follows each one through a workflow that lives in the repo. Scheduled Routines cover work that has no ticket.
@m1ch.euNew post: No Assignment, No Code: Planning with a Coding Agent in OpenProject
Using the issue tracker as the contract between me and a coding agent
https://blog.m1ch.eu/posts/20261007-openproject-coding-agent/
#m1ch20261007OpenprojectCodingAgent #ai #AgenticCoding #openproject #selfhost #boxgent
@marcel-more.deWhat does an AI agent need to truly understand a FileMaker solution?
Find out today at #EngageU:
➡️ Building an AI Coding Harness for FileMaker
🕐 16:00 · Room 1
Learn how to turn raw AI power into agentic FileMaker development.
engageu.eu/agenda/
@aidailypost.comOpenAI’s new GPT‑6.1 Sol can code like Astra but at a fraction of the token cost. Think agentic coding with cheaper computer use—plus a peek at Claude Opus 5.5’s cached‑token tricks. Curious? Dive in! #GPT61Sol #AgenticCoding #TokenPricing
@aidailypost.comClaude Sonnet 5.5 is raising the bar—faster agentic coding, smarter visual QA, and tighter token usage. If you build coding agents or need visual work, this LLM upgrade is a game‑changer. Dive into the details! #ClaudeSonnet5_5 #AgenticCoding #VisualQA
@veit-schiele.deNVIDIA OpenShell runs each agent in its own sandbox, with the policy being enforced and logged via process and network controls: docs.nvidia.com/openshell/ab...
#NVIDIA #OpenShell #AgenticCoding #ITSecurity
@marcel-more.deAgents have superpowers. But is that enough? 🕵️
This Thursday at #EngageU:
➡️ Building an AI Coding Harness for FileMaker
From Code Analysis to Agentic Development
@ocmatos.comSix months after JSSE's first release: 47 of 48 JetStream workloads now run (up from 22), 2.9x faster on the ones March could run, and still 100% on test262. This post is about the guardrails that kept it honest.
#JavaScript #Rust #AgenticCoding #Claude
@rotecodefraktion.bsky.socialGetting started with Claude Code
www.rotecodefraktion.de/en/blog/erst...
Step by step: from an empty folder to a tested Python script in one hour, with a plan, tests, and CLAUDE.md. Easy to follow, with all the real output.
@plone.orgTorben Baumgartner offers Introduction to Agentic Development and AI Tooling
@js-days.bsky.socialScheitern Coding-Agenten wirklich am Modell?
Thorsten Rinne zeigt, wie Feedback-Loops und fehlender Kontext Agenten ausbremsen – und wie du ein TypeScript-Monorepo agententauglich machst.
👉 https://javascript-days.de/javascript/modernes-js-tooling-fuer-agentic-coding/
@elijahlucian.bsky.socialGrowing up in the 80s means I like extremely hard to read fonts.
It gets me a lot of complaints from people, so now I just give people the option to change the entire brand of my sites, becasue why not?
@5troop.bsky.social
@neciudan.dev5️⃣ Anthropic's docs ship a PreToolUse hook that rewrites npm test to pipe through grep, so only failures reach the model. Copy the hook into the settings file (link in comments) Did I miss anything? #AI #ClaudeCode #AgenticCoding #SoftwareEngineering #DevProductivity
@heristop.bsky.socialMy coding agents can finish six features before I’ve reviewed the first.
Now each merge request comes with a short before-and-after video. I see what changed, then dig into the code.
Here’s the workflow:
heristop.github.io/blog/2026-09... #AgenticCoding
@haravirtualai.bsky.socialClaude Fable 5.1 is built for long coding, research, and knowledge-work projects—without constant back-and-forth. #ClaudeFable #ClaudeAI #AgenticCoding #AIResearch #KnowledgeWork
@mikapeltokorpi.bsky.socialIMO: hyperscaling is not the solution*) in the long run. You can run open competitive enough models in your own PC. If not now, in very near future yo will be.
*) For governmental/national security tasks, for sure, they are. But not for e.g. coding.