Home
Feed

Extend

Hashnode Pro
Hashnode for Agents

Resources

The foreword
Hashnode gql skill

Buildful - AI coding agent that delivers frontier-level results at a fraction of the cost Bug0 - The AI-native e2e QA regression testing Hackathons Changelog Brand @hashnode on X Hashnode on LinkedIn Support - hello+support@hashnode.com Code of Conduct Terms Privacy Sitemap

Search Hashnode

Search posts, tags, users, and pages

Discussion on "Don't Build Agents for Everything: The Procurement Mindset for AI Use Cases" | Hashnode

Feed/

Discussion

N Chandra Prakash Reddy

AWS Community Builder | Cloud | DevOps Engineer | Blogger

Oct 10

Don't Build Agents for Everything: The Procurement Mindset for AI Use Cases

I had a great opportunity to attend AWS Community Day, Bengaluru on 11th July 2026. The energy was outstanding, and while there were dozens of amazing presentations covering everything from cloud infr

devopstour.hashnode.dev9 min read

#aws #amazon-web-services #ai-agents #agentic-ai #serverless #aws-community-day-bengaluru-2026 #acdblr26 #cloud-computing #ai #machine-learning #generative-ai

Responses2

Markdown supported · ⌘↵ to post

Kartik N V J K

AI Developer | Making AI reliable, trustworthy & accessible to everyone | Active community contributor

That procurement framing is a useful filter, and the Gartner number about 40% of agentic projects getting cut by end of 2027 is going to age into a lot of post-mortems. Half the agents I see could be a scheduled function with one model call, and the agent framing is what makes them fragile and heavier to run than they need to be. What is the first question you ask to tell real autonomy apart from plain automation?

Oct 12

Deniafe

I build browser automations that don't break.

Oct 10

This is such an important distinction. The push to make everything a pure Agentic Loop ignores how expensive and slow it gets to have an LLM reason through every single step. I got so tired of the latency that I started building a visual tool (Selonate) based exactly on this Workflow Pipeline concept, using deterministic browser automation for the fast/repeatable steps, and only calling the AI surgically when a selector breaks or data needs unstructured extraction. Really well written piece!