Your AI coding agent comes with defaults: which model runs, what you pay, and what leaves your machine. You can turn those defaults into choices. In our new short course, AI Coding Workflows: From Cloud to Local, built in partnership with JetBrains and taught by Paul Everitt | @[email protected],... Developer Advocate at JetBrains, you'll rebuild the same app across cloud, hybrid, and fully local setups. Along the way, you'll split work across subagents, put cheaper models on the routine tasks, and finish with models running on your own machine. Enroll for free:show more

@jetbrains @paulweveritt Defaults hide decisions, whether it's a coding agent or a career. Back in 2016 I interviewed a startup co-founder for a founder interview show, and the pattern across guests like her was nobody explains their real decision process, they just show you the result.

@jetbrains @paulweveritt Amazing you are building @DeepLearningAI! It’s super useful

@jetbrains @paulweveritt 默认配置最容易被忽略，数据去哪儿确实该先搞清楚。

@jetbrains @paulweveritt Great practical guide for building smarter workflows

@jetbrains @paulweveritt Model choice looks like an intelligence decision. In practice it’s an infrastructure decision: cost ceiling, privacy boundary, latency, and whether your workflow survives a provider change. Local support isn’t a feature. It’s an exit option.

@jetbrains @paulweveritt Thread 1 What a timely drop ! As an educator in the vfx & animation industry I struggle with this everyday. please add chapters on how to improve local llm (gemma4) failure recovery. -

@jetbrains @paulweveritt The underrated part is making model choice boring. If switching clouds or going local changes the workflow, the abstraction leaked.

@jetbrains @paulweveritt Finally someone addressing the actual control issues—defaults hide a lot of decisions we should be making ourselves.