360SOFTY

Insights

Engineering Insights

Practical writing on software architecture, SaaS products, AI automation, legacy modernisation, and the business of building reliable systems.

RSS

Curated links from external sources — not 360Softy original articles.

ExternalSoftware Engineering
Google Developers Blog

Evolving Spec-Driven Development: Conductor Now Supports Antigravity

Conductor has evolved from a Gemini CLI extension into a portable plugin, bringing conversational Spec-Driven Development (SDD) to ecosystems like Antigravity CLI and Claude. Rather than relying on strict command sequences, developers can now chat naturally with their AI assistant while it dynamically manages persistent markdown artifacts (like spec.md and plan.md) in the background. This update eliminates workflow friction while ensuring your repository remains a version-controlled, single sour

Google Developers BlogRead original
ExternalSoftware Engineering
Google Developers Blog

Building scalable AI agents with modular prompt transpilation

To resolve the scaling bottlenecks and runtime errors caused by monolithic system prompts, engineering teams should treat prompts as build artifacts by modularizing instructions into reusable templates. By running these modular "skill files" through a transpiler, developers can enforce static validation, catch missing dependencies at build time, and integrate prompt generation directly into their CI/CD pipelines. This deterministic approach prevents code drift and ultimately establishes a safe f

Google Developers BlogRead original
ExternalSoftware Engineering
Google Developers Blog

Expanding Choice in Gemini Enterprise Agent Platform: Introducing Grounding with Parallel Web Search

Google Cloud has partnered with Parallel Web Systems to natively integrate Parallel's search infrastructure as a web grounding provider on the Gemini Enterprise Agent Platform. This integration enables developers to anchor their AI agents in verifiable, real-time web results, significantly improving factual accuracy for complex enterprise workflows. Additionally, the partnership offers expanded architectural flexibility, allowing users to programmatically extract, permanently cache, and process

Google Developers BlogRead original
ExternalSoftware Engineering
Google Developers Blog

Run Ray on TPU, Part 1: The foundations

Ray 2.55 introduces official, first-class support for Google Cloud TPUs, enabling developers to run distributed Python workloads on Google's accelerators using the familiar Ray task-and-actor APIs. To handle the strict networking requirement of keeping multi-host TPU "slices" together over their Inter-Chip Interconnect (ICI), the KubeRay Operator on GKE automatically provisions and labels the underlying hardware layout. Ray Core utilizes these labels via its slice_placement_group() primitive to

Google Developers BlogRead original
ExternalSoftware Engineering
Google Developers Blog

Scaling Agentic RL: High-Throughput Agentic Training with Tunix

Tunix is Google’s new JAX-native post-training library designed to eliminate TPU idling bottlenecks when training multi-turn, tool-using LLM reasoning agents. It maximizes hardware throughput by combining highly concurrent, asynchronous rollouts with a decoupled producer-consumer pipeline, ensuring the trainer is constantly fed even while agents wait on network I/O or environment steps. Additionally, Tunix provides plug-and-play abstractions and continuous macro-level profiling, allowing develop

Google Developers BlogRead original
ExternalSoftware Engineering
DEV Community

Incident Retrospectives Without Blame

I've run over 100 post-mortems. The worst ones end with 'Alice will be more careful.' The best ones end with 'we fixed the system.' Here's how you get from the first to the second. Ban these phrases from retros: 'Should have...' 'Alice forgot to...' 'If only...' Replace with: 'The system let this happen because...' 'The runbook didn't cover...' 'The signal was missing...' People make mistakes. Systems that allow those mistakes to reach production are the actual bug. Classic 5 whys often end at h

sredevopspostmortem
DEV CommunityRead original
ExternalSoftware Engineering
DEV Community

Your coding agent runs a shell on your machine. I audited mine.

A coding agent that can run bash on your laptop is a remote shell on localhost. It has that threat model whether or not anyone designed for it — browser drive-bys, DNS rebinding, curl | bash, the twenty years of localhost-daemon mistakes the web already made and wrote down. Last week wren.wtf published a teardown of opencode: Stop using opencode. Read it in full. The headline was a real CVE — a default HTTP server with permissive CORS and an endpoint that ran arbitrary shell commands, so any web

securityaiagents
DEV CommunityRead original
ExternalSoftware Engineering
DEV Community

Building a 13-Agent Marketing Society on Qwen Cloud — What Actually Broke, and What I Learned Fixing It

Written for the Qwen Cloud Global AI Hackathon 2026 — Track 3: Agent Society. Most "AI marketing" tools are one LLM wearing a lot of hats — a single prompt that agent society — specialized agents That's what I set out to build with Nexus AI: 13 specialized agents — Qwen-Max through Alibaba Cloud's . The moment it became a real "society" The feature I care about most isn't any single agent — it's what happens between two of them. Social Manager drafts a LinkedIn post. Before anything

aihackathonqwen
DEV CommunityRead original

Work with 360Softy

Building a SaaS product, AI system, or business platform?

Book a free consultation and we will tell you honestly whether we can help.

Book a consultationView our services →