#workflow

36 items tagged #workflow.

GUIDE 2026-05-11

Pulling a GitHub issue into Aider: from URL to first commit

How to feed a GitHub issue directly into Aider, ask for a plan, execute, and close the issue with a properly tagged commit — and which issue types to avoid.

Owner · 6 min #aider #github

GUIDE 2026-05-11

Claude Code in a monorepo: directory roots, CLAUDE.md, and not getting lost across packages

Starting Claude Code at the wrong directory in a monorepo costs you context. Here's how to manage session roots, per-package CLAUDE.md files, and cross-package edits without losing your mind.

Owner · 7 min #claude-code #monorepo

GUIDE 2026-05-11

Claude Code permission modes: plan, edit, and auto-accept — and when to switch

Claude Code's three permission modes gate different levels of agent autonomy. Getting the mode wrong costs you either hours of unnecessary round-trips or a destructive operation you can't undo.

Owner · 6 min #claude-code #permissions

GUIDE 2026-05-11

Plan mode in Claude Code: the conversation step that prevents thrash

Claude Code's plan mode produces a written proposal with no file edits or commands. Here's when to use it, how to refine plans through dialogue, and when to skip it.

Owner · 5 min #claude-code #plan-mode

GUIDE 2026-05-11

Resuming Claude Code sessions without re-explaining the entire task

Claude Code stores conversation history locally. Here's how to resume sessions with --continue and session IDs, when it works well, when it doesn't, and one habit that makes re-entry fast.

Owner · 5 min #claude-code #sessions

GUIDE 2026-05-11

Claude Code subagents: when to dispatch and when to keep the main session

Subagents give Claude Code an isolated context window for grunt work. Here's when that matters, when parallel dispatch pays off, and when it backfires.

Owner · 7 min #claude-code #subagents

GUIDE 2026-05-11

Cursor plus Claude Code plus Aider: when running multiple AI tools at once pays off

Most days one AI coding tool is enough. This is about the narrower case where running three in parallel — each doing the thing it was built for — actually earns its cognitive overhead.

Owner · 8 min #ai-coding #multi-tool

GUIDE 2026-05-11

Zed multi-cursors plus AI: the pattern Cursor can't match

Zed lets you place cursors at dozens of callsites simultaneously, then invoke the inline AI assistant to transform each one with local context — a mechanical refactor pattern that Cursor's agent loop can't replicate.

Owner · 6 min #zed #multicursor

BLOG 2026-05-10

Why I run an AI chat aggregator alongside Cursor

AI editors like Cursor are great inside the editor. For email drafting, browser-side research, and quick model comparisons, a general AI aggregator does what coding-native tools weren't built for. Here's how I split the two.

Owner · 6 min #workflow #tooling

GUIDE 2026-05-08

A working Windsurf Cascade workflow for multi-file features

Cascade is Windsurf's agent. It can write 200 lines across 6 files in one go, or it can produce a tangled mess. The difference is how you brief it.

Owner · 9 min #windsurf #cascade

CASE STUDY 2026-05-04

A three-tool AI code review loop: Cursor, Copilot, and Aider on the same PRs

A small team tested Cursor, Copilot, and Aider as separate review passes before human review. The useful result was not more comments, but better self-review before opening PRs.

Editor · 8 min #code-review #workflow

GUIDE 2026-04-28

Cursor Composer for multi-file features: how to scope a session that works

Composer can produce a coherent 15-file diff or a sprawling mess. The variable is how much you constrain the session before you start typing.

Owner · 8 min #cursor #composer

GUIDE 2026-04-25

GitHub Copilot for PR review: a workflow that actually catches things

Copilot's auto-review feature misses real bugs and flags style nits. Here's a three-pass workflow that uses Copilot for what it's good at and humans for what it isn't.

Owner · 7 min #copilot #code-review

GUIDE 2026-04-20

AI-assisted debugging: a methodology that beats vibes-based prompting

Asking the AI 'why is this broken' produces plausible-but-wrong answers. A four-step structure produces useful ones. Here's the structure and what each step actually does.

Owner · 9 min #debugging #methodology

GUIDE 2026-04-18

Copilot Chat vs inline completions: a workflow split that saves 30 minutes a day

Most Copilot users mix the two surfaces randomly. There's a clear split that produces better output for both, and it's about a five-minute habit shift.

Owner · 6 min #copilot #workflow

GUIDE 2026-04-15

Cursor Tab vs Cmd+K vs chat: when to use which one

Cursor exposes three different ways to ask the model for help. They have different latencies, contexts, and failure modes. Pick the wrong one and the experience drops noticeably.

Owner · 5 min #cursor #workflow

GUIDE 2026-04-13

Windsurf Flows vs Cascade: when to use the deeper-context mode

Cascade is Windsurf's standard agent. Flows is the longer-running, deeper-context cousin. The two cost different amounts and fit different tasks.

Owner · 5 min #windsurf #workflow

GUIDE 2026-04-10

Cline Plan mode vs Act mode: the workflow that gets the most out of both

Cline's Plan/Act split is more useful than it looks. Plan mode is for thinking; Act mode is for doing. Mixing them at the right cadence makes the autonomous loop reliable.

Owner · 5 min #cline #workflow

GUIDE 2026-04-09

Zed's vim mode with AI: keyboard-driven coding without giving up the assistant

Zed's vim emulation is the best of any modern editor I've used. Combined with the AI panel, it produces a workflow that's faster than mouse-driven AI assistance.

Owner · 5 min #zed #vim

GUIDE 2026-04-08

Using AI tools for legacy code archaeology: explaining what 2014-vintage code does

Inheriting a 10-year-old codebase is its own kind of work. AI tools won't fix the legacy, but they can dramatically speed up the understanding-what-this-does phase.

Owner · 8 min #legacy-code #methodology

BLOG 2026-04-05

Why I stopped using AI for commit messages

AI-generated commit messages are technically accurate and almost always wrong in the way that matters. Here's what I noticed after six months of using them and why I went back to writing my own.

Owner · 5 min #git #workflow

GUIDE 2026-04-04

Aider's --watch mode: live coding with AI suggestions in your editor of choice

Aider --watch lets you keep coding in your normal editor and trigger Aider edits via AI! comments. The setup takes ten minutes and changes how Aider fits into a workflow.

Owner · 6 min #aider #workflow

GUIDE 2026-04-04

GitHub Copilot Chat slash commands: the ones that earn their keep

Copilot Chat ships with a dozen slash commands. Three of them are routinely useful; the rest are rarely worth the keystrokes. Here's the short list.

Owner · 4 min #copilot #workflow

CASE STUDY 2026-04-03

AI tools on a 3-developer team: coordination patterns that work

Three engineers working on the same codebase, all using AI tools heavily. The output looked inconsistent until we agreed on coordination patterns. Here's what we landed on.

Owner · 9 min #team #workflow

GUIDE 2026-04-02

Pair programming with AI: a structured approach that beats free-form chat

Free-form prompting feels like pair programming and often isn't. A four-role structure produces better outcomes and is closer to how human pairing actually works.

Owner · 7 min #pair-programming #methodology

GUIDE 2026-03-25

Integrating AI into your PR review workflow without making review worse

AI-generated PR reviews can catch real issues or flood your team with low-signal noise. The difference is in what you ask the AI to do and how you wire it into the human review.

Owner · 8 min #code-review #workflow

BLOG 2026-03-25

Why I still write tests by hand even when AI could write them faster

AI generates plausible tests fast. The plausibility is the problem. Tests are a specification, and outsourcing the specification removes the most valuable thing tests do.

Editor · 5 min #testing #opinion

BLOG 2026-03-23

Code review is now the bottleneck — and AI is making it worse

When AI lets one engineer ship 3x more code, the team's bottleneck moves to review. Most teams haven't adjusted. Here's what's happening and what to do.

Owner · 6 min #code-review #workflow

BLOG 2026-03-19

Why review-as-you-go beats batch review for AI-generated code

Reviewing AI output one chunk at a time feels slower than letting it produce a feature and reviewing the diff at the end. Across many sessions, the reverse turns out to be true.

Owner · 5 min #workflow #code-review

BLOG 2026-02-28

AI tools are forcing a README renaissance, in unexpected ways

Repos with detailed READMEs work better with AI tools. The market is responding. Here's how documentation expectations have shifted.

Owner · 4 min #documentation #workflow

GUIDE 2026-01-12

Cline's task decomposition: when to break a big task into smaller ones manually

Cline's autonomous loop can break tasks into steps. For complex work, manual decomposition by you produces better results than letting Cline figure it out.

Owner · 4 min #cline #workflow

GUIDE 2026-01-11

Cursor's streaming output: when to wait vs. when to interrupt

Cursor streams responses as they generate. Knowing when to interrupt mid-stream improves productivity meaningfully.

Owner · 3 min #cursor #workflow

BLOG 2026-01-09

The quiet skill of writing good prompts for code

Good prompts aren't magic phrases. They're a specific kind of clear thinking expressed in words. Here's the actual skill.

Owner · 3 min #prompts #workflow

BLOG 2026-01-08

The rise of personal coding agents: tools you build for yourself

Custom coding agents built for specific personal workflows are becoming a real category. The pattern, the tooling, and what's working.

Owner · 4 min #agents #workflow

BLOG 2026-01-07

The token efficiency game: optimizing AI tool costs without optimizing badly

Saving tokens means saving money. But over-optimizing tokens hurts output quality. Here's the line.

Owner · 3 min #cost #workflow

GUIDE 2025-12-12

Zed tasks and keybindings: turning your editor into a workflow runner

Zed's tasks system lets you bind common workflows to keys. Useful for repeated test/build/format cycles.

Owner · 3 min #zed #workflow