DEV Community

#harness

Posts

đź‘‹ Sign in for the ability to sort posts by relevant, latest, or top.
Fail-Before-Fix in AI Coding Agents: Speculative Patching vs. a Reproduction-First Gate (-95.3% Input Tokens, 100% Accuracy)

Fail-Before-Fix in AI Coding Agents: Speculative Patching vs. a Reproduction-First Gate (-95.3% Input Tokens, 100% Accuracy)

Comments
6 min read
Stop Returning Bare Linter Error Codes to Coding Agents: Opaque Error Codes vs. Actionable Fix-Hint Linters (-69.6% Input Tokens)

Stop Returning Bare Linter Error Codes to Coding Agents: Opaque Error Codes vs. Actionable Fix-Hint Linters (-69.6% Input Tokens)

1
Comments 1
6 min read
Escaping Sunk-Cost Retry Loops in Coding Agents: Single-Session Retries vs. a Parallel Best-of-N Tournament (-67.2% Input Tokens)

Escaping Sunk-Cost Retry Loops in Coding Agents: Single-Session Retries vs. a Parallel Best-of-N Tournament (-67.2% Input Tokens)

Comments
6 min read
Why LLMs Fail at Unified Diffs: Standard Diff Hunks vs. Line-Number-Free SEARCH/REPLACE Blocks (2.41x Faster)

Why LLMs Fail at Unified Diffs: Standard Diff Hunks vs. Line-Number-Free SEARCH/REPLACE Blocks (2.41x Faster)

Comments
6 min read
Why Long System Prompts Can't Enforce Code Architecture: Prompt Rules vs. Deterministic Pre-Commit AST Hooks

Why Long System Prompts Can't Enforce Code Architecture: Prompt Rules vs. Deterministic Pre-Commit AST Hooks

Comments
6 min read
Why Self-Review Fails in AI Coding Agents: Single-Agent Self-Review vs. an Adversarial Critic (0% vs. 100% Mutant Kill Rate)

Why Self-Review Fails in AI Coding Agents: Single-Agent Self-Review vs. an Adversarial Critic (0% vs. 100% Mutant Kill Rate)

Comments
6 min read
Stop Letting Your Coding Agent Blindly Grep Decoy Files: Raw Grep vs. a 0-Token AST Dependency Map (3.15x Faster)

Stop Letting Your Coding Agent Blindly Grep Decoy Files: Raw Grep vs. a 0-Token AST Dependency Map (3.15x Faster)

Comments
6 min read
Vibe Coding vs. Spec-First SDD: How Locking an Executable Spec Eliminates Rework and Cuts Input Tokens by 32.9%

Vibe Coding vs. Spec-First SDD: How Locking an Executable Spec Eliminates Rework and Cuts Input Tokens by 32.9%

Comments
6 min read
Eliminating Goal Drift in Multi-File Coding Agents: In-Chat Loops vs. Code-Mode Dynamic Workflows

Eliminating Goal Drift in Multi-File Coding Agents: In-Chat Loops vs. Code-Mode Dynamic Workflows

Comments
6 min read
Why AI Agents Write Weak Tests for Their Own Code: Single-Agent TDD vs. Two-Agent Blind TDD (0% vs. 100% Mutant Kill Rate)

Why AI Agents Write Weak Tests for Their Own Code: Single-Agent TDD vs. Two-Agent Blind TDD (0% vs. 100% Mutant Kill Rate)

Comments
5 min read
Single Loops vs. Directed Graphs for AI Coding Agents: Cutting Input Tokens by 74.4% Without Losing Accuracy

Single Loops vs. Directed Graphs for AI Coding Agents: Cutting Input Tokens by 74.4% Without Losing Accuracy

Comments
6 min read
Why Role-Based Subagents Slow Down Coding Agents: Subagent Folding + Progressive Skill Disclosure (2.66x Faster)

Why Role-Based Subagents Slow Down Coding Agents: Subagent Folding + Progressive Skill Disclosure (2.66x Faster)

Comments
6 min read
AI Helps Teams Write Code Faster. Why Isn't It Getting Shipped Any Faster?

AI Helps Teams Write Code Faster. Why Isn't It Getting Shipped Any Faster?

Comments
9 min read
Harness Engineering for Dummies

Harness Engineering for Dummies

2
Comments
7 min read
MCP For Using Another Agent inside an Agent.

MCP For Using Another Agent inside an Agent.

Comments
2 min read
đź‘‹ Sign in for the ability to sort posts by relevant, latest, or top.