BestHub
Sign in
Tagged articles

System Prompt

23 articles · Page 1 of 1
Architect
Architect
Sep 4, 2026 · Artificial Intelligence

What Is a Harness? Why the Same Model Behaves Differently Across Coding Agents

The article explains why swapping the Harness — the runtime environment around an AI model — changes agent behavior even when the model weights stay identical, covering system prompts, tool definitions, agentic loops, translation layers, execution boundaries, feedback fidelity, context compression vs. immutable event logs, and architectural trade-offs illustrated by Pi, Codex, DSH, and the claudex experiment.

AI agentsAgent RuntimeAgentic Loop
0 likes · 19 min read
What Is a Harness? Why the Same Model Behaves Differently Across Coding Agents
Old Zhang's AI Learning
Old Zhang's AI Learning
Aug 24, 2026 · Artificial Intelligence

What Is a Harness? The Runtime Environment That Lets You Own Your AI Agent

This article explains Harness as a software runtime that gives AI models a workspace — system prompt, tools, an agentic loop for self-directed reasoning, and a translation layer to swap models — using Pi Agent as a concrete example of a thin, user-extensible harness with over 5,000 community extensions.

AI AgentAgentic LoopHarness
0 likes · 8 min read
What Is a Harness? The Runtime Environment That Lets You Own Your AI Agent
PaperAgent
PaperAgent
Jul 27, 2026 · Artificial Intelligence

Why Dropping 80% of System Prompts Improves Claude 5: New Context Engineering Rules

Anthropic’s official Claude 5 guide reveals that removing most Claude Code system prompts has no measurable impact, overturning traditional context‑engineering practices and introducing six paradigm shifts that let the model rely on its own judgment and progressive context loading.

AI agentsAnthropicClaude-5
0 likes · 6 min read
Why Dropping 80% of System Prompts Improves Claude 5: New Context Engineering Rules
Black & White Path
Black & White Path
Jul 15, 2026 · Artificial Intelligence

Inside the 42K‑Word OpenAI Codex Desktop System Prompt Leak

A security researcher released over 42,000 words of OpenAI Codex desktop system prompts and tool definitions, revealing the AI's layered persona, dual‑channel workflow, skill‑calling mechanisms, tool set, and safety constraints, offering a rare window into AI agent design and security.

AI safetyCodexGitHub
0 likes · 8 min read
Inside the 42K‑Word OpenAI Codex Desktop System Prompt Leak
java1234
java1234
Jul 5, 2026 · Artificial Intelligence

9 Practical Tips for Efficient Spring AI 2.0 Agent Development

The article shares nine hands‑on tips for building Spring AI 2.0 agents—including using ChatClient as the entry point, delegating tool calls to ToolCallingAdvisor, defining tools with @Tool, crafting effective system prompts, leveraging Advisor chains, streaming responses early, managing conversation memory, limiting tool count, and adding observability—each illustrated with concrete code snippets.

ChatClientJavaObservability
0 likes · 12 min read
9 Practical Tips for Efficient Spring AI 2.0 Agent Development
AI Engineering
AI Engineering
Jun 14, 2026 · Artificial Intelligence

Can You Revive Claude Fable 5 in Four Simple Steps?

After Claude Fable 5 was disabled, the community shared a four‑step guide that uses a system‑prompt file with Opus 4.8 Max to mimic Fable 5’s style, demonstrates the results, and discusses why the approach only changes output style, not model capability.

AI modelClaudeFable 5
0 likes · 4 min read
Can You Revive Claude Fable 5 in Four Simple Steps?
James' Growth Diary
James' Growth Diary
Jun 4, 2026 · Artificial Intelligence

How to Inject Four‑Layer Memory into Every Dialogue with system_prompt.py

This article explains Hermes' three‑layer system prompt architecture—Stable, Context, and Volatile—detailing how ordered memory injection, snapshot freezing, SQLite caching, and ephemeral prompts dramatically improve LLM prefix‑cache hit rates while avoiding token waste and security risks.

HermesLLM cachingSystem Prompt
0 likes · 13 min read
How to Inject Four‑Layer Memory into Every Dialogue with system_prompt.py
Smart Sea Tide
Smart Sea Tide
May 29, 2026 · Artificial Intelligence

Exploring System Prompts of Leading AIs (ChatGPT, Claude, Gemini, Grok, Perplexity)

The open‑source “system_prompts_leaks” repository gathers and categorizes the system prompts of top AI models, analyzes each vendor's design philosophy—from OpenAI's personality‑utility split to Anthropic's engineering focus and xAI's role‑based approach—and shows how prompts serve as the complete product blueprint.

AI Product DesignAnthropicOpenAI
0 likes · 4 min read
Exploring System Prompts of Leading AIs (ChatGPT, Claude, Gemini, Grok, Perplexity)
Tencent Cloud Developer
Tencent Cloud Developer
May 26, 2026 · Artificial Intelligence

What Hidden Secrets Does the Agent’s System Prompt Code Reveal?

This article dissects OpenClaw's agent architecture, detailing how the System Prompt, Skill modules, and Agent Loop interact, explaining PromptMode variations, safety rules, tool definitions, skill loading pipelines, heartbeat handling, sub‑agent spawning, silent replies, and the context engine that assembles messages for LLMs.

Agent LoopContext EngineLLM
0 likes · 17 min read
What Hidden Secrets Does the Agent’s System Prompt Code Reveal?
Wu Shixiong's Large Model Academy
Wu Shixiong's Large Model Academy
Apr 30, 2026 · Artificial Intelligence

When Is Claude Code’s Memory Injected into system_prompt? Interview Insight

The article explains that Claude Code loads persisted memory once at REPL startup via _build_system(), inserts it as the 10th segment of system_prompt, enforces a 200‑line limit on MEMORY.md, deliberately avoids side‑effects in get_memory_dir(), and only refreshes the prompt with the /model command.

Claude CodeLLMMemory Injection
0 likes · 11 min read
When Is Claude Code’s Memory Injected into system_prompt? Interview Insight
High Availability Architecture
High Availability Architecture
Apr 24, 2026 · Artificial Intelligence

Claude’s Official Report Reveals Three Quality Degradation Issues and Fixes

Anthropic’s recent report details three independent changes that caused quality regressions in Claude Code and Agent SDK—lowered default reasoning effort, a caching bug that erased thinking history, and an overly restrictive system prompt—each fixed by April 20 in version v2.1.116+, with plans to prevent future incidents.

AIClaudeSystem Prompt
0 likes · 12 min read
Claude’s Official Report Reveals Three Quality Degradation Issues and Fixes
Design Hub
Design Hub
Apr 19, 2026 · Artificial Intelligence

What’s Inside the Leaked 70K‑Word Claude Design System Prompt?

The article verifies the authenticity of a 73 KB, 422‑line Claude Design system prompt leaked by the CL4R1T4S project, provides a faithful translation of its contents, and dissects the five‑layer design that enables high‑quality AI‑assisted design output.

AI designAnthropicClaude
0 likes · 23 min read
What’s Inside the Leaked 70K‑Word Claude Design System Prompt?
James' Growth Diary
James' Growth Diary
Apr 17, 2026 · Artificial Intelligence

Advanced System Prompt Design Patterns & Few-Shot Techniques for Reliable LLM Outputs

This article breaks down System Prompt engineering into a five‑layer contract, presents four design patterns—role anchoring, output schema, chain‑of‑thought steering, and guardrails—explains how to select effective few‑shot examples, provides production‑grade prompt templates with code snippets, and warns about common pitfalls such as token length, sample bias, and contradictory constraints.

AIFew-shotLLM
0 likes · 16 min read
Advanced System Prompt Design Patterns & Few-Shot Techniques for Reliable LLM Outputs
Architect Practice
Architect Practice
Apr 12, 2026 · Artificial Intelligence

What Engineering Problems Does Claude Code’s Harness Engineering Solve?

The article dissects Claude Code’s open‑source TypeScript implementation to reveal the five‑layer Harness Engineering architecture—Query Loop, system‑prompt assembly, tool orchestration, multi‑level context compression, and multi‑Agent coordination—showing how each layer solves concrete engineering challenges for reliable AI agents.

AI AgentContext CompressionHarness Engineering
0 likes · 20 min read
What Engineering Problems Does Claude Code’s Harness Engineering Solve?
Wu Shixiong's Large Model Academy
Wu Shixiong's Large Model Academy
Mar 29, 2026 · Artificial Intelligence

Mastering RAG Prompt Engineering: Prevent Hallucinations and Boost Accuracy

This article dissects the unique challenges of RAG prompting, presents a systematic System/User Prompt design with strong constraints and citation requirements, compares constraint strengths with quantitative hallucination rates, and offers long‑context compression strategies and rigorous testing methods to ensure reliable LLM answers.

Context CompressionLLMRAG
0 likes · 19 min read
Mastering RAG Prompt Engineering: Prevent Hallucinations and Boost Accuracy
Data Party THU
Data Party THU
Dec 22, 2025 · Artificial Intelligence

Unlock Gemini 3.0: The Complete System Prompt Blueprint for Better AI Answers

Gemini 3.0’s publicly released system prompt provides a detailed, step‑by‑step framework—including logical dependencies, risk assessment, abductive reasoning, outcome evaluation, information integration, precision, completeness, persistence and response inhibition—to guide the model toward safer, higher‑quality answers.

AI safetyArtificial IntelligenceGemini 3
0 likes · 10 min read
Unlock Gemini 3.0: The Complete System Prompt Blueprint for Better AI Answers
Volcano Engine Developer Services
Volcano Engine Developer Services
Aug 19, 2025 · Artificial Intelligence

How to Strengthen LLM System Prompts for Safer AI Agents

This guide explains how to reinforce system prompts for AI agents by optimizing their content and structure, using active defense, role‑based, and format constraints, providing practical examples, measurement methods, and experimental results that demonstrate up to 90% reduction in unsafe behavior.

AI safetyLLMSystem Prompt
0 likes · 13 min read
How to Strengthen LLM System Prompts for Safer AI Agents
CSS Magic
CSS Magic
Nov 1, 2024 · Artificial Intelligence

Refining System Prompts for LLMs: Practical Tips for Batch Automation

This article explains how to automate batch document processing with LLM APIs by mastering the messages parameter, defining system, user, and assistant roles, and iteratively polishing system prompts through scripts or OpenAI's GPTs editor and Playground interfaces.

AutomationChatGPTLLM
0 likes · 7 min read
Refining System Prompts for LLMs: Practical Tips for Batch Automation