Skip to main content
Scour
Browse
Getting Started
Login
Sign Up
You are offline. Trying to reconnect...
Copied to clipboard
Unable to share or copy to clipboard
Prompt Engineering
💬 Prompt Engineering
LLM Optimization, Few-shot Learning, Chain-of-Thought, AI Prompts
Filter Results
Timeframe
Fresh
Past Hour
Today
This Week
This Month
Feeds to Scour
Subscribed
All
Scoured
139
posts in
25.3
ms
The
AI
Agents Stack (2026 Edition)
🔍
RAG
Content type:
Blog
oreilly.com
·
2d
2 days ago
Actions for The AI Agents Stack (2026 Edition)
A free diagnostic for the
Claude
Certified
Architect
exam
🎭
Program Synthesis
Content type:
Discussion
Content type:
Tutorial
claudecertifiedarchitects.com
·
1d
1 day ago
·
Hacker News
Actions for A free diagnostic for the Claude Certified Architect exam
Prompt
Caching on
Claude
: Cut Input Costs 78% (The Math Nobody Writes Down)
🌊
Streaming Lexers
pub.towardsai.net
·
8h
8 hours ago
Actions for Prompt Caching on Claude: Cut Input Costs 78% (The Math Nobody Writes Down)
You Only Index Once: Cross-Layer Sparse Attention with Shared Routing
🗺️
Region Inference
Content type:
Academic
arxiv.org
·
5d
5 days ago
Actions for You Only Index Once: Cross-Layer Sparse Attention with Shared Routing
Show
HN:
LLM
memory without context bleed; 100% precision vs. <10% vector search
🔍
RAG
tenureai.dev
·
5d
5 days ago
·
Hacker News
,
Hacker News
Actions for Show HN: LLM memory without context bleed; 100% precision vs. <10% vector search
wastedcode/truecast: The expert teammates
Claude
Code doesn't ship with
💻
Terminal Tools
Content type:
Code
github.com
·
2d
2 days ago
·
Hacker News
Actions for wastedcode/truecast: The expert teammates Claude Code doesn't ship with
Prompt
Caching
💬
Interactive REPLs
pub.towardsai.net
·
18h
18 hours ago
Actions for Prompt Caching
Declarative Skills for
AI
Agents in Knowledge-Grounded Tool-Use Workflows
🧠
Symbolic AI
Content type:
Academic
arxiv.org
·
2d
2 days ago
Actions for Declarative Skills for AI Agents in Knowledge-Grounded Tool-Use Workflows
Local LLMs, Buy a GPU, and the Case for Cognitive Security
🏰
Capability Machines
briefing.forwardfuture.ai
·
6d
6 days ago
Actions for Local LLMs, Buy a GPU, and the Case for Cognitive Security
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
·
17h
17 hours ago
·
Hacker News
Actions for 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.
Build a Basic
AI
Agent from Scratch: Long Task Planning
🌙
Lua
Content type:
Blog
ruxu.dev
·
2d
2 days ago
·
Hacker News
Actions for Build a Basic AI Agent from Scratch: Long Task Planning
Dep-LLM
: Training-Free Depression Diagnosis via Evidence-Guided Structured Multi-factor with Reliable
LLM
Reasoning
🪜
Recursive Descent
Content type:
Academic
arxiv.org
·
19h
19 hours ago
Actions for Dep-LLM: Training-Free Depression Diagnosis via Evidence-Guided Structured Multi-factor with Reliable LLM Reasoning
What Actually Happens When You Send a
Prompt
to
Claude
A Full Breakdown
📝
Computational Linguistics
pub.towardsai.net
·
5d
5 days ago
Actions for What Actually Happens When You Send a Prompt to Claude A Full Breakdown
Show
HN: Built an open-source local firewall for
AI
coding agents
🐦
Wren
Content type:
Discussion
news.ycombinator.com
·
1d
1 day ago
·
Hacker News
Actions for Show HN: Built an open-source local firewall for AI coding agents
manavgup/context-analyzer: Context window usage analyzer for
Claude
Code — MCP server + interactive dashboard
🗄️
SQLite
Content type:
Code
github.com
·
19h
19 hours ago
·
Hacker News
Actions for manavgup/context-analyzer: Context window usage analyzer for Claude Code — MCP server + interactive dashboard
Design
a Knowledge Q&A
System
💬
REPL Design
newsletter.systemdesign.one
·
6d
6 days ago
Actions for Design a Knowledge Q&A System
LLM-Based
Code Documentation Generation and Multi-Judge Evaluation
📚
Self-Documenting Code
Content type:
Academic
arxiv.org
·
19h
19 hours ago
Actions for LLM-Based Code Documentation Generation and Multi-Judge Evaluation
patriceckhart/zot: Yet another coding agent harness, lightweight and written in go.
💻
Terminal UIs
Content type:
Code
github.com
·
1d
1 day ago
·
Hacker News
Actions for patriceckhart/zot: Yet another coding agent harness, lightweight and written in go.
How to cut the cost of long
AI
agent threads (without making the agent dumber)
🧩
Cognitive Science
Content type:
Blog
viktor.com
·
2d
2 days ago
·
Hacker News
Actions for How to cut the cost of long AI agent threads (without making the agent dumber)
MIRAGE: Mobile Agents with Implicit Reasoning and Generative World
Models
💻
Terminal UIs
Content type:
Academic
arxiv.org
·
6d
6 days ago
Actions for MIRAGE: Mobile Agents with Implicit Reasoning and Generative World Models
« Page 1
·
Page 3 »
Log in to enable infinite scrolling
Keyboard Shortcuts
Navigation
Next / previous item
j
/
k
Open post
o
or
Enter
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
g
h
Interests
g
i
Feeds
g
f
Likes
g
l
History
g
y
Changelog
g
c
Settings
g
s
Browse
g
b
Search
/
Pagination
Next page
n
Previous page
p
General
Show this help
?
Submit feedback
!
Close modal / unfocus
Esc
Press
?
anytime to show this help