AI Guardrails by Zapier Gives Teams Inline Safety Checks for Every AI-Powered Workflow - Business WireAI Guardrails by Zapier Gives Teams Inline Safety Checks for Every AI-Powered Workflow Business Wire
Microsoft Introduces WinApp CLI to Unify Windows App Development Workflows - infoq.comMicrosoft Introduces WinApp CLI to Unify Windows App Development Workflows infoq.com
Global Breakthrough: 5,000 Alteryx Workflows migrated to Microsoft Fabric with 91% Automation using Pulse Convert - The Destin LogGlobal Breakthrough: 5,000 Alteryx Workflows migrated to Microsoft Fabric with 91% Automation using Pulse Convert The Destin Log
Dropzone 5: A Faster Drag-and-Drop Workflow [Sponsor] - MacStoriesDropzone 5: A Faster Drag-and-Drop Workflow [Sponsor] MacStories
New Powerful NotebookLM Updates for Workflow, Outputs, Slide Decks, Mind Maps & More - Geeky GadgetsNew Powerful NotebookLM Updates for Workflow, Outputs, Slide Decks, Mind Maps & More Geeky Gadgets
Agentic AI for Business Workflows | Windows for Business - MicrosoftAgentic AI for Business Workflows | Windows for Business Microsoft
Show HN: Show HN: GitHub Pages for Agents with GitHub Agentic Workflows (Gh-Aw)I built AgentPages, an experiment in running AI agents entirely inside GitHub.https://github.com/idorozin/AgentPagesThe idea is simple: instead of just hosting a static site on GitHub Pages, the site is maintained by an AI agent that lives in the repo.You define what you're interested in (topics, goals, style), and the agent periodically researches those topics and updates the site.Everything runs inside GitHub:A GitHub Agentic Workflow (gh-aw) runs on a cron scheduleThe agent performs web research (using Tavily search)It updates its knowledge baseIt edits the Astro source filesThe site is rebuilt and deployed to GitHub PagesThe whole thing is transparent because everything happens in the repo:user/ files you control (research topics, requests, feedback) agent/ the agent’s knowledge and memory website/src/ the site the agent edits docs/ the built static site served by GitHub Pages You can steer the agent by editing files like:user/profile.md what the agent should researchuser/feedback.
Show HN: SimplAI – Build and deploy AI agents and workflows without boilerplateHey HN,I've been building SimplAI for the past several months — it's a platform for building, testing, and deploying LLM-powered agents and multi-step workflows.The problem I kept running into: spinning up an AI agent pipeline means stitching together prompt management, tool calling, memory, evals, and deployment — often from scratch every time. SimplAI tries to be the layer that handles all of that so you can focus on what your agent actually does.What it does: - Visual + code-first workflow builder for chaining LLM calls, tools, and APIs - Built-in prompt versioning and A/B testing - Supports multiple LLM providers (OpenAI, Anthropic, Gemini, etc.) - Evaluation and observability built in, not bolted on - Deploy agents as APIs in one clickIt's not trying to be LangChain or LlamaIndex — the focus is on speed to production and giving non-ML engineers a sane path forward.Happy to answer questions about the architecture, design decisions, or anything else. Critical feedback especially wel
Show HN: Aidevshield NPM audit for AI coding tool workflowsI built aidevshield, a free open-source security scanner that catches vulnerabilities in AI coding tool configurations things like Cursor, Copilot, and Cline setups.The problem: AI coding assistants are becoming attack surfaces. In the past year we've seen real exploits:Clinejection (Dec 2025): Prompt injection via GitHub issue titles → AI triage bot executes shell commands → malicious npm package published to 5M users tj-actions/changed-files (Mar 2025): Tag repointing attack hit 23,000 repos via pull_request_target Shai-Hulud (2025): First self-propagating npm worm using postinstall hooks Rules File Backdoor (Feb 2025): Hidden Unicode characters in .cursorrules for invisible prompt injection Existing tools cover parts of this — Zizmor and actionlint for GitHub Actions, Socket.dev for npm — but nothing scans across all four domains: workflows + AI configs + npm packages + prompt injection.aidevshield does. One command, zero dependencies beyond js-yaml, fully offline:npx aidevshield sc
Vector DB Read & Write Nodes in Workflow AgentsVector DB Read & Write Nodes in Workflow Agents Oracle Blogs
Show HN: FadNote – Zero-knowledge secret sharing for your CLI and AI workflowsHi HN,I built FadNote because I realized that while services like Privnote or Yopass exist, they often feel like an "interruption" to a developer's flow. You have to leave your terminal, open a browser, paste, and copy again.FadNote is designed for integration, not just web-visiting. The goal is to provide a zero-knowledge "utility layer" that lives where you already work:OpenClaw Skill: For AI-powered workflow automation.CLI First: A zero-dependency Node.js script to pipe secrets directly from your terminal (echo "secret" | fadnote).Obsidian Plugin (In Dev): To share snippets directly from your knowledge base.The Security Model (Trust-less):Local Encryption: Secrets are encrypted via AES-256-GCM with 600,000 PBKDF2 iterations before they leave your machine.The URL Fragment: The decryption key is stored in the URL fragment (#key). Since browsers never send fragments to the server, I literally cannot read your data even if I wanted to.One-Time & Faded: The encrypted blob is deleted from
Production Vibe Coding Workflow: From Prompt to Deploy - SitePointProduction Vibe Coding Workflow: From Prompt to Deploy SitePoint
Show HN: Agent-Rules – Opinionated Rules and Workflows for Claude CodeLast year I was skeptical about coding AI. Now, they can produce much better quality output, so I started using them more often, specifically claude code. During this transition, I felt unsatisfied with the prompting UX:- Outputs are either noisy, or lacking important details.- Trade-offs aren't fully listed when the agents provide options.- Limited context length, and the inability to share context between sessions means I often have to repeat the same info multiple times when iterating through a problem.So, I defined some custom workflows that make the agent persist the context to markdown files, where I can thoroughly review, answer inline, cross-reference, or delegate another agent for more analysis. The agent and I keep iterating the discussion until we resolve every blocker. This builds an auditable trail of discussions and decision making.I believe these problems and preferences aren't only mine. There are likely some existing tools or skills that provide similar mechanics (e.g.
RIP GitHub Actions : Long Live Agentic Workflows in 2026GitHub is reshaping CI/CD pipeline management with the introduction of Agentic Workflows, as detailed by Better Stack. This approach integrates natural language programming and AI-driven ...
Show HN: CodeRocket Deploy – AI generates GitHub Actions workflows in 60 secondsHey HN,I built CodeRocket Deploy because I was tired of the CI/CD setup ritual every developer knows: search for a workflow template, copy YAML, tweak it, watch it fail, debug, repeat.What it does: - Install as a GitHub App - Analyzes your repo (package.json, requirements.txt, config files, etc.) - Detects language, framework, and deploy target automatically - Uses Claude to generate a workflow optimized for your specific stack - Creates a PR so you can review before mergingTechnical details: - Deep static analysis using GitHub's Contents API - 20+ framework detectors (Next.js, Django, FastAPI, Rails, Spring Boot, etc.) - Few-shot prompting with production-ready workflow examples - Fallback templates for edge cases - YAML validation with security scanning (no hardcoded secrets)Stack: Django + DRF backend, React + TypeScript frontend, PostgreSQL, Redis for Celery tasks.Free tier: 100 generations/month, 3 repos. No credit card.GitHub Marketplace: https://github.com/marketplace/coderocket
Why the start of the year exposes true cost of manual workflows in SA businesses - ITWebWhy the start of the year exposes true cost of manual workflows in SA businesses ITWeb
Automate repository tasks with GitHub Agentic Workflows - The GitHub BlogAutomate repository tasks with GitHub Agentic Workflows The GitHub Blog
GitHub Agentic Workflows are now in technical preview - The GitHub BlogGitHub Agentic Workflows are now in technical preview The GitHub Blog
How an AI agent is redefining executive workflows at Cemex - Microsoft SourceHow an AI agent is redefining executive workflows at Cemex Microsoft Source
AI Agents That Execute Business Workflows (Claude Code for ERP)TL;DR: Built an ERP where AI agents execute workflows like procurement and invoice processing. Uses Cases (workspaces) and Tasks (sessions) like Claude Code. Agent completes one task, automatically triggers the next. Mac app live, looking for early users.Mac App: https://apps.apple.com/be/app/swiftly-ai-native-erp/id6755155607?mt=12TestFlight: https://testflight.apple.com/join/aYc16FmATHE PROBLEMAfter 8 years implementing ERPs across Europe, I kept seeing the same issue: ERP systems store data but can't execute processes. Employees still manually click through forms for invoicing, procurement, onboarding.WHAT WE BUILTAI agents that execute multi-step business workflows autonomously.Example: Vendor Procurement Case: "Source Steel Pipes - Q1 2026" Task 1: Research Suppliers → finds 3 vendors Task 2: Compare Pricing → creates comparison Task 3: Negotiate → drafts proposal, waits for approval Task 4: Create PO → auto-triggered after approval Each task has specific instructions. Status chan