Prompt Engineering

Feeds to Scour
SubscribedAll
Scoured 139 posts in 25.3 ms

The AI Agents Stack (2026 Edition)

 🔍RAG  Content type: Blog
oreilly.com·

A free diagnostic for the Claude Certified Architect exam

 🎭Program Synthesis  Content type: Discussion  Content type: Tutorial

Prompt Caching on Claude: Cut Input Costs 78% (The Math Nobody Writes Down)

 🌊Streaming Lexers
pub.towardsai.net
·

You Only Index Once: Cross-Layer Sparse Attention with Shared Routing

 🗺️Region Inference  Content type: Academic
arxiv.org·

Show HN: LLM memory without context bleed; 100% precision vs. <10% vector search

 🔍RAG

wastedcode/truecast: The expert teammates Claude Code doesn't ship with

 💻Terminal Tools  Content type: Code
github.com··Hacker News

Prompt Caching

 💬Interactive REPLs
pub.towardsai.net
·

Declarative Skills for AI Agents in Knowledge-Grounded Tool-Use Workflows

 🧠Symbolic AI  Content type: Academic
arxiv.org·

Local LLMs, Buy a GPU, and the Case for Cognitive Security

 🏰Capability Machines

jianzhichun/permafrost: Freeze Claude Code's prompt prefix so DeepSeek's automatic cache always hits — alignment proxy + coalescing + keepalive, installable as a CC plugin. Measured 64% cheaper on real Claude Code traffic.

 🔄Subinterpreters  Content type: Code
github.com··Hacker News

Build a Basic AI Agent from Scratch: Long Task Planning

 🌙Lua  Content type: Blog
ruxu.dev··Hacker News

Dep-LLM: Training-Free Depression Diagnosis via Evidence-Guided Structured Multi-factor with Reliable LLM Reasoning

 🪜Recursive Descent  Content type: Academic
arxiv.org·

What Actually Happens When You Send a Prompt to Claude A Full Breakdown

 📝Computational Linguistics
pub.towardsai.net
·

Show HN: Built an open-source local firewall for AI coding agents

 🐦Wren  Content type: Discussion

manavgup/context-analyzer: Context window usage analyzer for Claude Code — MCP server + interactive dashboard

 🗄️SQLite  Content type: Code
github.com··Hacker News

Design a Knowledge Q&A System

 💬REPL Design

LLM-Based Code Documentation Generation and Multi-Judge Evaluation

 📚Self-Documenting Code  Content type: Academic
arxiv.org·

patriceckhart/zot: Yet another coding agent harness, lightweight and written in go.

 💻Terminal UIs  Content type: Code
github.com··Hacker News

How to cut the cost of long AI agent threads (without making the agent dumber)

 🧩Cognitive Science  Content type: Blog
viktor.com··Hacker News

MIRAGE: Mobile Agents with Implicit Reasoning and Generative World Models

 💻Terminal UIs  Content type: Academic
arxiv.org·

Keyboard Shortcuts

Navigation

Next / previous item
j/k
Open post
oorEnter
Preview post
v

Post Actions

Love post
a
Like post
l
Dislike post
d
Undo reaction
u
Save / unsave
s

Recommendations

Add interest / feed
Enter
Not interested
x

Go to

Home
gh
Interests
gi
Feeds
gf
Likes
gl
History
gy
Changelog
gc
Settings
gs
Browse
gb
Search
/

General

Show this help
?
Submit feedback
!
Close modal / unfocus
Esc

Press ? anytime to show this help