Skip to content
Navigation menu
Search
Powered by Algolia
Search
Log in
Create account
DEV Community
Close
#
harness
Follow
Hide
Posts
Left menu
đź‘‹
Sign in
for the ability to sort posts by
relevant
,
latest
, or
top
.
Right menu
Fail-Before-Fix in AI Coding Agents: Speculative Patching vs. a Reproduction-First Gate (-95.3% Input Tokens, 100% Accuracy)
tappers
tappers
tappers
Follow
Nov 21
Fail-Before-Fix in AI Coding Agents: Speculative Patching vs. a Reproduction-First Gate (-95.3% Input Tokens, 100% Accuracy)
#
ai
#
harness
#
tdd
#
testing
Comments
Add Comment
6 min read
Moderation
Stop Returning Bare Linter Error Codes to Coding Agents: Opaque Error Codes vs. Actionable Fix-Hint Linters (-69.6% Input Tokens)
tappers
tappers
tappers
Follow
Nov 21
Stop Returning Bare Linter Error Codes to Coding Agents: Opaque Error Codes vs. Actionable Fix-Hint Linters (-69.6% Input Tokens)
#
ai
#
harness
#
softwareengineering
#
agenticai
1
 reaction
Comments
1
 comment
6 min read
Moderation
Escaping Sunk-Cost Retry Loops in Coding Agents: Single-Session Retries vs. a Parallel Best-of-N Tournament (-67.2% Input Tokens)
tappers
tappers
tappers
Follow
Nov 20
Escaping Sunk-Cost Retry Loops in Coding Agents: Single-Session Retries vs. a Parallel Best-of-N Tournament (-67.2% Input Tokens)
#
ai
#
harness
#
git
#
python
Comments
Add Comment
6 min read
Moderation
Why LLMs Fail at Unified Diffs: Standard Diff Hunks vs. Line-Number-Free SEARCH/REPLACE Blocks (2.41x Faster)
tappers
tappers
tappers
Follow
Nov 20
Why LLMs Fail at Unified Diffs: Standard Diff Hunks vs. Line-Number-Free SEARCH/REPLACE Blocks (2.41x Faster)
#
ai
#
harness
#
coding
#
agenticai
Comments
Add Comment
6 min read
Moderation
Why Long System Prompts Can't Enforce Code Architecture: Prompt Rules vs. Deterministic Pre-Commit AST Hooks
tappers
tappers
tappers
Follow
Nov 19
Why Long System Prompts Can't Enforce Code Architecture: Prompt Rules vs. Deterministic Pre-Commit AST Hooks
#
ai
#
harness
#
architecture
#
softwareengineering
Comments
Add Comment
6 min read
Moderation
Why Self-Review Fails in AI Coding Agents: Single-Agent Self-Review vs. an Adversarial Critic (0% vs. 100% Mutant Kill Rate)
tappers
tappers
tappers
Follow
Nov 19
Why Self-Review Fails in AI Coding Agents: Single-Agent Self-Review vs. an Adversarial Critic (0% vs. 100% Mutant Kill Rate)
#
ai
#
harness
#
testing
#
agenticai
Comments
Add Comment
6 min read
Moderation
Stop Letting Your Coding Agent Blindly Grep Decoy Files: Raw Grep vs. a 0-Token AST Dependency Map (3.15x Faster)
tappers
tappers
tappers
Follow
Nov 18
Stop Letting Your Coding Agent Blindly Grep Decoy Files: Raw Grep vs. a 0-Token AST Dependency Map (3.15x Faster)
#
ai
#
harness
#
contextengineering
#
python
Comments
Add Comment
6 min read
Moderation
Vibe Coding vs. Spec-First SDD: How Locking an Executable Spec Eliminates Rework and Cuts Input Tokens by 32.9%
tappers
tappers
tappers
Follow
Nov 18
Vibe Coding vs. Spec-First SDD: How Locking an Executable Spec Eliminates Rework and Cuts Input Tokens by 32.9%
#
ai
#
harness
#
softwareengineering
#
coding
Comments
Add Comment
6 min read
Moderation
Eliminating Goal Drift in Multi-File Coding Agents: In-Chat Loops vs. Code-Mode Dynamic Workflows
tappers
tappers
tappers
Follow
Nov 17
Eliminating Goal Drift in Multi-File Coding Agents: In-Chat Loops vs. Code-Mode Dynamic Workflows
#
ai
#
harness
#
python
#
automation
Comments
Add Comment
6 min read
Moderation
Why AI Agents Write Weak Tests for Their Own Code: Single-Agent TDD vs. Two-Agent Blind TDD (0% vs. 100% Mutant Kill Rate)
tappers
tappers
tappers
Follow
Nov 17
Why AI Agents Write Weak Tests for Their Own Code: Single-Agent TDD vs. Two-Agent Blind TDD (0% vs. 100% Mutant Kill Rate)
#
ai
#
harness
#
tdd
#
testing
Comments
Add Comment
5 min read
Moderation
Single Loops vs. Directed Graphs for AI Coding Agents: Cutting Input Tokens by 74.4% Without Losing Accuracy
tappers
tappers
tappers
Follow
Nov 16
Single Loops vs. Directed Graphs for AI Coding Agents: Cutting Input Tokens by 74.4% Without Losing Accuracy
#
ai
#
harness
#
architecture
#
agenticai
Comments
Add Comment
6 min read
Moderation
Why Role-Based Subagents Slow Down Coding Agents: Subagent Folding + Progressive Skill Disclosure (2.66x Faster)
tappers
tappers
tappers
Follow
Nov 16
Why Role-Based Subagents Slow Down Coding Agents: Subagent Folding + Progressive Skill Disclosure (2.66x Faster)
#
ai
#
harness
#
contextengineering
#
multiagent
Comments
Add Comment
6 min read
Moderation
AI Helps Teams Write Code Faster. Why Isn't It Getting Shipped Any Faster?
binith
binith
binith
Follow
Nov 14
AI Helps Teams Write Code Faster. Why Isn't It Getting Shipped Any Faster?
#
ai
#
architecture
#
testing
#
harness
Comments
Add Comment
9 min read
Moderation
Harness Engineering for Dummies
Carsten Behrens
Carsten Behrens
Carsten Behrens
Follow
Nov 13
Harness Engineering for Dummies
#
ai
#
productivity
#
harness
#
mcp
2
 reactions
Comments
Add Comment
7 min read
Moderation
MCP For Using Another Agent inside an Agent.
Fahim
Fahim
Fahim
Follow
Nov 13
MCP For Using Another Agent inside an Agent.
#
ai
#
multiharness
#
harness
#
mcp
Comments
Add Comment
2 min read
Moderation
đź‘‹
Sign in
for the ability to sort posts by
relevant
,
latest
, or
top
.
We're a place where coders share, stay up-to-date and grow their careers.
Log in
Create account