Coding assistants

Effective workflows

https://missing.csail.mit.edu/2026/development-environment/#ai-powered-development

And coding agents:

https://missing.csail.mit.edu/2026/agentic-coding/

iterative with multiple agents (2026)

https://www.aymannadeem.com/artificial/intelligence,/developer/tools/2026/09/24/plan-mode-is-dead.html

• discusses the limits of planning mode with multi-agent setups
• iterative, tight feedback loops

build wide, ship narrow (2026)

https://adapt.com/blog/build-wide-ship-narrow

1. Grill the plan until it has real decisions in it
2. Commit the spec before any code, when the design is novel
3. Build wide, committing save points as you go
4. Demo and iterate before anyone reads the code
5. Split into PRs along the boundaries the code revealed
6. Merge, cleanup last: pure deletion in its own final PR

”mini waterfall” (2025)

https://blog.lmorchard.com/2025/06/07/semi-automatic-coding/

For each session

• plan (plan.md)
• execute
• consolidate (notes.md)

Cost optimization

https://claude.com/blog/maximizing-the-value-of-your-claude-code-sessions

• cache expiration
• /clear
• /compact
• /rewind
• changing /model and /effort

Configuration

To format and lint produced code

https://benword.com/how-to-make-claude-code-automatically-format-and-lint-files

Tools

Cambrian explosion, it’s not just GH Copilot:

https://github.com/sourcegraph/awesome-code-ai

Self-hosted

https://github.com/TabbyML/tabby

Internals

Lifecycle of code completions

https://sourcegraph.com/blog/the-lifecycle-of-a-code-ai-completion

Pros and cons

https://addyo.substack.com/p/the-70-problem-hard-truths-about

Effective use of LLMs / coding assistants

https://www.shayon.dev/post/2025/164/pitfalls-of-premature-closure-with-llm-assisted-coding/#menial-tasks-where-ai-excels