AI coding agents

54 stories tagged AI coding agents.

AI Coding Agents Produce More Code, Not Always More Software

AI coding agents can produce patches fast, but teams still face review, testing and upkeep. Track defects and total effort to see whether more code means better software.

Claude Code Projects Automates the Pull Request Churn

Yuki Okonkwo6 days ago

AI. Yuki Okonkwo6 days ago

Claude Code Projects Automates the Pull Request Churn

Claude Code Projects can keep working on pull requests after opening them. Here’s how that compares with VS Code Agent Merge, and what teams still need to decide.

Claude Sonnet 5.5's Coding Gains Put Review Costs in Focus

Dev Kapoor2 weeks ago

AI. Dev Kapoor2 weeks ago

Claude Sonnet 5.5's Coding Gains Put Review Costs in Focus

Anthropic says Claude Sonnet 5.5 improves coding at the same token price. For open-source maintainers, review time, retries and governance shape the real cost.

Claude Opus 5.5 Turns the AI Model Race Toward Price

Bob Reynolds3 weeks ago

AI. Bob Reynolds3 weeks ago

Claude Opus 5.5 Turns the AI Model Race Toward Price

Anthropic cut Claude Opus 5.5 prices, but workload cost depends on tokens, cache use and safeguards. What buyers should test before switching.

MiniCPM5 Shows the Promise and Fragility of Local AI

Rachel "Rach" Kovacs1 month ago

AI. Rachel "Rach" Kovacs1 month ago

MiniCPM5 Shows the Promise and Fragility of Local AI

MiniCPM5-2B posts striking coding scores on local hardware, but benchmark gaps and fragile sampling defaults complicate claims that it rivals larger models.

Astra for Coding and the Treadmill of AI Agent Rebrands

Zara Chen1 month ago

AI. Zara Chen1 month ago

Astra for Coding and the Treadmill of AI Agent Rebrands

A new AI coding agent launches, dev Twitter shrugs. Inside the launch-cycle loop and the benchmarks that would actually settle whether these tools work.

Google's Mantis Gives Coding Agents a Full Security Feedback Loop

Dev Kapoor1 month ago

AI. Dev Kapoor1 month ago

Google's Mantis Gives Coding Agents a Full Security Feedback Loop

Google open-sourced Mantis, an Apache 2.0 toolkit that lets AI coding agents find, reproduce, and patch vulnerabilities. What it does, and what's unproven.

Cognition's $48 Billion Valuation and the Economics of AI Coding

Bob Reynolds1 month ago

AI. Bob Reynolds1 month ago

Cognition's $48 Billion Valuation and the Economics of AI Coding

Cognition's reported $48 billion valuation puts AI coding agents at the center of a costly bet. What the numbers say, and what would have to be true.

Orange robot pushes a vertical slider downward beneath bold Turn It Down text

Claude Fable 5.1: Seven Prompting Changes That Actually Move Results

Yuki Okonkwo1 month ago

AI. Yuki Okonkwo1 month ago

Claude Fable 5.1: Seven Prompting Changes That Actually Move Results

AI Labs tested Claude Fable 5.1 on real client work. Here's what their seven tips reveal about effort settings, hidden model switches, and token costs.

Six Claude Code Skills That Change How Agents Decide

Yuki Okonkwo1 month ago

AI. Yuki Okonkwo1 month ago

Six Claude Code Skills That Change How Agents Decide

Six Claude Code skills covering task memory, marketing flows, Karpathy's agent rules, web automation, UI variation, and pre-build validation.

Grok 4.6 and Grok Bot: A Solo Developer's Overnight Test

Bob Reynolds2 months ago

AI. Bob Reynolds2 months ago

Grok 4.6 and Grok Bot: A Solo Developer's Overnight Test

Ray Fernando ran Grok 4.6 overnight on real projects and reviewed the results live. Here's what actually shipped, and what it means for how software gets built.

Woman wearing headphones against blue tech background with pixelated robot characters and GitHub interface elements…

GitHub Stacks Brings Stacked PRs to Copilot Agents

Dev Kapoor2 months ago

AI. Dev Kapoor2 months ago

GitHub Stacks Brings Stacked PRs to Copilot Agents

GitHub's new gh-stack skill lets Copilot agents automatically split large AI-generated pull requests into reviewable stacked PRs. Here's what it looks like in practice.

Man in glasses next to file folder diagram showing AI branching into multiple agents with "Best Feature Yet" text

Claude Code Sessions Can Now Message Each Other

Dev Kapoor2 months ago

AI. Dev Kapoor2 months ago

Claude Code Sessions Can Now Message Each Other

Claude Code's new inter-session messaging unlocks peer session workflows that challenge the dominance of subagents. Here's what that shift actually looks like in practice.

Man in brown shirt stands before a performance benchmark chart comparing AI models, with text overlay reading "Benchmarks…

AI Coding Agents Still Need a Human in the Loop

Bob Reynolds2 months ago

AI. Bob Reynolds2 months ago

AI Coding Agents Still Need a Human in the Loop

Dexter Horthy built a fully automated software factory—then watched it corrupt his codebase. His case for keeping humans in the loop is harder to dismiss than most.

Man speaking into microphone against blue background with text "BUILD AGENT WORKFLOWS" overlaid on left side

Agent Skills vs Python Scripts: A Developer's Trade-Off

Samira Barnes2 months ago

AI. Samira Barnes2 months ago

Agent Skills vs Python Scripts: A Developer's Trade-Off

A developer argues for replacing Python scripts with AI agent skill workflows. The technical case is compelling — the governance questions it quietly raises are more interesting.

Orange and black YouTube thumbnail with pixelated brick text reading "CLAUDE CODE" and white text "7x Better Results" with…

Claude Code Skills: What Seven Upgrades Reveal

Bob Reynolds3 months ago

AI. Bob Reynolds3 months ago

Claude Code Skills: What Seven Upgrades Reveal

A YouTube tutorial on Claude Code skill configuration raises a deeper question: how much of this configuration layer will Anthropic eventually absorb into the product itself?

AI Agents That Fix Slow Code Before You Notice

Bob Reynolds3 months ago

AI. Bob Reynolds3 months ago

AI Agents That Fix Slow Code Before You Notice

May Walter of Hud built an AI agent that hunts production performance problems weekly and hands engineers verified fixes. Here's what that actually looks like.

Person in red shirt with microphone next to computer screen displaying code and task lists, with text overlay "Watch him code

How One Solo Developer Manages 30 AI Agents at Once

Bob Reynolds3 months ago

AI. Bob Reynolds3 months ago

How One Solo Developer Manages 30 AI Agents at Once

Kun Chen, a former big tech engineer, built a multi-agent orchestration system to manage dozens of AI coding sessions solo. Here's how it actually works.

Man with surprised expression against black and white spiral background with text "CODE LESS LOOP MORE

AI Coding Agents That Run Their Own Loops

Marcus Chen-Ramirez4 months ago

AI. Marcus Chen-Ramirez4 months ago

AI Coding Agents That Run Their Own Loops

Developer Theo explores a shift in AI coding workflows: instead of prompting agents yourself, you design loops that let agents prompt each other autonomously.

Man wearing headphones with finger to lips in a thoughtful pose against black background, with "/visual-plan" text displayed

Visual Plans for Claude Code Change Agent Reviews

Yuki Okonkwo4 months ago

AI. Yuki Okonkwo4 months ago

Visual Plans for Claude Code Change Agent Reviews

Builder.io's Steve Sewell introduces visual-plan and visual-recap skills for Claude Code, turning AI-generated markdown walls into interactive MDX diagrams and wireframes.