Introducing Strands Agent SOPs – Natural Language Workflows for AI Agents - Amazon Web Services (AWS)Introducing Strands Agent SOPs – Natural Language Workflows for AI Agents Amazon Web Services (AWS)
SK Telecom deepens customer connections with agentic workflows in Microsoft Foundry - MicrosoftSK Telecom deepens customer connections with agentic workflows in Microsoft Foundry Microsoft
Agents built into your workflow: Get Security Copilot with Microsoft 365 E5 - MicrosoftAgents built into your workflow: Get Security Copilot with Microsoft 365 E5 Microsoft
How to Use GitHub Copilot to Improve Your Coding Workflow - CourseraHow to Use GitHub Copilot to Improve Your Coding Workflow Coursera
Ask HN: is this a common LLM-assisted development workflow?I generally frame a problem for the agent and present a few solutions and ask if it can come up with some pros and cons of the solutions. I read the output and make a decision on the best approach based on that output.Then, I'll tell the LLM what I think the best step-by-step approach will be. It may have some tweaks that I'll read and either agree with or say "no let's keep it how I proposed." Then I ask the LLM to execute the first step. It generates code, which I review, and I either accept it, accept it but make tweaks, or reject it and tell the LLM why I don't think it's going down the right path.I iterate like this until the problem is solved to my liking.I see a bunch of people writing about vibe-coding and I can't fathom wholesale accepting model output. But this workflow seems to work really well for me. I would say I ship high-quality code and maybe 10x faster than I used to.
Microsoft 365 Copilot Gains App Builder, Workflows and Expanded Admin Controls - Redmondmag.comMicrosoft 365 Copilot Gains App Builder, Workflows and Expanded Admin Controls Redmondmag.com
Show HN: Pipelex – Declarative language for repeatable AI workflowsWe’re Robin, Louis, and Thomas. Pipelex is a DSL and a Python runtime for repeatable AI workflows. Think Dockerfile/SQL for multi-step LLM pipelines: you declare steps and interfaces; any model/provider can fill them.Why this instead of yet another workflow builder?- Declarative, not glue code: you state what to do; the runtime figures out how. - Agent-first: each step carries natural-language context (purpose, inputs/outputs with meaning) so LLMs can follow, audit, and optimize. Our MCP server enables agents to run pipelines but also to build new pipelines on demand. - Open standard under MIT: language spec, runtime, API server, editor extensions, MCP server, n8n node. - Composable: pipes can call other pipes, created by you or shared in the community.Why a domain-specific language?- We need context, meaning and nuances preserved in a structured syntax that both humans and LLMs can understand - We need determinism, control, and reproducibility that pure prompts can't deliver - Bonus:
Microsoft 365 Copilot now enables you to build apps and workflows - MicrosoftMicrosoft 365 Copilot now enables you to build apps and workflows Microsoft
How to build reliable AI workflows with agentic primitives and context engineering - The GitHub BlogHow to build reliable AI workflows with agentic primitives and context engineering The GitHub Blog
Show HN: Loopdesk – AI video editor with chat-based workflows and GPU renderingHey HN,We're launching Loopdesk Beta v2 today after 6 months of working with 300+ creators. It's an AI-powered video editor that uses chat-based prompting and genre-specific workflows.The Problem We're SolvingVideo editing is time-consuming, especially for content creators who need to produce videos regularly. The traditional timeline-based editing workflow requires manual sorting, organizing clips, adding captions, generating highlights, and applying effects. For podcasters and educational content creators, explaining jargon or adding visual annotations adds another layer of complexity. We wanted to automate the repetitive parts while keeping creative control.How We Got HereWe started this project because we were creating tutorial content ourselves and spending 4-5 hours editing a single 20-minute video. The bottleneck wasn't the creative decisions—it was the mechanical tasks: organizing footage, transcribing, captioning, finding key moments. We tried existing AI editors but found the
Mastering Spec-Driven Development with Prompted AI Workflows: A Step-by-Step Implementation Guide - Augment CodeMastering Spec-Driven Development with Prompted AI Workflows: A Step-by-Step Implementation Guide Augment Code
5 ways to integrate GitHub Copilot coding agent into your workflow - The GitHub Blog5 ways to integrate GitHub Copilot coding agent into your workflow The GitHub Blog
Actions: YAML anchors and non-public workflow templates - The GitHub BlogActions: YAML anchors and non-public workflow templates The GitHub Blog
GitHub Copilot coding agent 101: Getting started with agentic workflows on GitHub - The GitHub BlogGitHub Copilot coding agent 101: Getting started with agentic workflows on GitHub The GitHub Blog
Yardi launches Virtuoso AI agents to deploy AI-powered workflows - PR NewswireYardi launches Virtuoso AI agents to deploy AI-powered workflows PR Newswire
Launch HN: VibeFlow (YC S25) – Web app generator with visual, editable workflowsHi HN! We’re Alessia and Elia, the founders of VibeFlow (https://vibeflow.ai). VibeFlow lets semi-technical people (i.e. people with some technical skill but who are not professional programmers) build full-stack web apps from natural language prompts, while making the underlying business logic clear and editable as a visual workflow. Demo video: https://www.youtube.com/watch?v=-CwWd3-b1JI.The problem we’re trying to solve: today, people who want to build apps without coding often have to stitch together multiple tools, e.g. using Lovable for the frontend, n8n for workflows, and Supabase for the database. That creates data silos and leaves builders with fragile apps that break in production, don’t scale, and aren’t safe. We saw YouTube tutorials teaching people how to duct-tape these together just to get a functional app running. As engineers building no-code tools, we realized that people wanted the power of AI-generated UIs but also the ability to see and control their backend workfl
Ginkgo Datapoints, Tangible Scientific, and Indictive Bio Partner to Deploy AI-Driven Lab-In-The-Loop Workflows Across the Biopharma Industry - marketscreener.comGinkgo Datapoints, Tangible Scientific, and Indictive Bio Partner to Deploy AI-Driven Lab-In-The-Loop Workflows Across the Biopharma Industry marketscreener.com
Develop Agentic AI Workflows with Langflow and Oracle Database MCP, Vector RAG, NL2SQL/ - Oracle BlogsDevelop Agentic AI Workflows with Langflow and Oracle Database MCP, Vector RAG, NL2SQL/ Oracle Blogs
Adobe After Effects 25.4 Adds New Features and Workflow EnhancementsAdobe’s August 2025 After Effects update introduces easier ways to stagger animation timing, paste text formatting only, manage HDR color consistency, and benefit from workflow streamlining, including ...