@ekon-konferenz.bsky.socialWhat if you could build your own coding agent? 🤖
@vintagedave.bsky.social takes you behind the scenes of CodeBot and shows how a Delphi-aware coding agent is built.
👉 Discover the session: https://entwickler-konferenz.de/frameworks-and-tools/codebot-how-a-coding-agent-is-built/
@reliasoftware.bsky.socialYour AI coding agent can read files, run commands, and access external tools. But can it tell a developer's instructions from an attacker's?
Here's how prompt injection exploits that gap and how to secure your agents. 👇️
@devstackdaily.bsky.socialCUA-SWE introduces a benchmark for evaluating agents that combine coding and computer-use skills to diagnose runtime failures by linking visual GUI feedback with source code changes. It targets the underexplored…
#AI #codingagents #softwareengineering #benchmark
https://arxiv.org/abs/2609.32600
@vicky-grok.bsky.socialYour agents become an actual team — not 20 random terminal windows.
OpenRig runs as a local daemon + CLI + TUI + MCP server, with tmux underneath.
đź”— github.com/mvschwarz/o...
#OpenRig #AIAgents #ClaudeCode #Codex #AI #DeveloperTools #Automation #OpenSource #CodingAgents
@softwarearchsummit.bsky.socialCoding Agents schreiben den Code. Wer hält die Architektur zusammen?
Das neue Whitepaper von Mario Herb zeigt, wie taktisches #DDD fachliche Grenzen fĂĽr #CodingAgents schafft.
👉 kostenlos: https://software-architecture-summit.de/downloads/whitepaper-ddd-coding-agents-ki-architektur/
@softwarearchsummit.bsky.socialCoding Agents schreiben Code – und treffen Architekturentscheidungen ungefragt mit. Modul AGENTA zeigt, wie du Qualität und Leitplanken im Griff behältst.
📅 09.–11.11.2026, Berlin.
→ https://software-architecture-camp.de/modul-agenta-architektur-fuer-agentic-software-engineering
@aidailypost.com🚀 Nvidia’s new SoL‑Pi cuts coding‑agent token use in half with an evidence‑preserving reducer. Think faster Claude Code & Codex runs without the token bloat. Curious? Dive in! #SoLPi #TokenOptimization #CodingAgents
@leanpub.bsky.socialFrom the Leanpub Blog: Leanpub Book LAUNCH 🚀 The Code Is Lying: Engineering with Coding Agents by Alen Joy
#books #leanpublishing #selfpublishing #CodingAgents #AIEngineering #AgenticAI
@leanpub.bsky.socialNEW! Leanpub Book LAUNCH 🚀 The Code Is Lying: Engineering with Coding Agents by Alen Joy
#books #leanpublishing #selfpublishing #CodingAgents #AIEngineering #AgenticAI #SoftwareArchitecture #CodeReview
@cdevmkt.bsky.socialquick one for indie builders
when your coding agent opens a PR, do you still read every line or just skim + ship?
i still force myself to read it. caught dumb stuff twice this week.
curious how y'all handle this.
chuongle.dev
#indiehackers #codingagents #devtools
@axialis.comFinding code is easy.
Finding the *right* code in a large C++ project is harder.
Our new Axialis article explores text search vs. semantic symbol navigation, and how to benchmark their impact on coding agents.
@upsun.comOptimizing AI coding agents is useless if your team does not share context 🤖. Giving humans and agents the same repo, docs, and vocabulary is where true speed comes from 💡. 👉 upsun.com/blog/context... #AIEngineering #DevOps #SoftwareArchitecture #CodingAgents
@aiengineeringsu.bsky.socialMehr AI-Output, aber weniger Kontrolle? đź‘€
Mit mehreren Coding Agents steigen Output und Herausforderungen. Julius Mischok zeigt im neuen Blogartikel, wie Architektur, Tests und Quality Gates helfen.
👉 https://ai-engineering-summit.de/blog/agentic-engineering-vibe-coding/
@softwarearchsummit.bsky.socialKann KI-generierter Code wirklich architekturkonform sein? đź‘€
Taktisches DDD gibt Coding Agents Leitplanken und hilft, ihren Code gezielt zu prĂĽfen.
👉 Jetzt kostenlos downloaden: https://software-architecture-summit.de/downloads/whitepaper-ddd-coding-agents-ki-architektur/
@hackernoon.comLearn how orchestrator skills and sub-agents keep coding-agent contexts clean while handling complex debugging, research, migrations, and audits. #codingagents
@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/
@shiftinbits.comSame agent. Same question. Two very different bills.
75% fewer tokens. 72% lower cost. Same model, same prompt. The only thing that changed is the agent could finally see the structure of the codebase instead of guessing from text.
@tidb-hq.bsky.socialEvery AI coding agent resets. These files don't.
Here's how persistent workspaces keep your agent coherent across sessions: link
@saaro.netđź“ť Neuer Blog-Beitrag: Nicht weiterprompten: Gib dem Agenten ein Ziel
Der entscheidende Shift für produktive Arbeit mit Coding Agents: Gib dem Agenten ein Ziel und Akzeptanzkriterien, statt Schritt-für-Schritt-Anleitungen. Mit konkreten Beispielen für C…
@securityonline.bsky.socialPlugin4Shell is a zero-click RCE hitting every major AI coding agent via a SHA pinning bypass. Claude Code and Codex are patched; Copilot and Gemini CLI are not.
#Plugin4Shell #AIsupplychain #CodingAgents #ClaudeCode #ZeroClickRCE #SHApinning #AIsecurity