James Q Quick

CAREER UPDATE #2 - I'm beyond excited to announce that today is my first day as a FULLTIME Content Creator 🥳🥳🥳 I'm still exploring opportunities in the background, but at least for the next several months, I work for myself 💪

LOVE this feature from @Academy where it shows a full outfit to go with each color of shoes!

@j4w8n Me neither until it popped up several times. Weird!

@jamesqquick I didn't realize this was a thing.

What is this trend with converting profile pics to a woman? I've been offline for a while, but that's weird right? 👀

I am looking for a full-time job. Being independent in open source for 3.5+ years has been wonderful. I've gotten done most of the high-level goals I wanted to, and miss having people & structure around me. If you know of a staff TypeScript+web developer role, let me know! 🙂

@kvlly Subscribed!!!!

@jamesqquick Here! I'm up to 9 🎊 @the-modern-leader" target="_blank" rel="nofollow noopener">youtube.com/@the-modern-le…

Not to brag too much, but look how many subscribers I'm up to on the Modern Leader youtube channel. (There's no content on there yet. That's coming early next year.)

@bookercodes @mastra Shoot I missed it! Is a recording available by any chance?

tomorrow I'll be hosting a workshop on how to build your first AI agent with TypeScript and @mastra this is basically everything I learned about building agents as a beginner in my first 3 months at Mastra luma.com/event/manage/e…

@sandrinodm Honestly, I just think they lie...😅

@jamesqquick Your IT/Security team defines how long you stay signed in for! 🧐

The greatest lie every told!

Quick hands-on tutorial on building a Chat Bot with @nextjs @vercel AI SDK and the @BigCommerceDevs MCP server 🔥 developer.bigcommerce.com/resource-hub/a…

The AI SDK from @vercel doesn't yet support session management. Any idea when that will be available? Without this, I don't have a realistic way to support a chatbot that's deployed to serverless.

@ALAColombiaDev @brianmmdev Yeah that's basically what I've done as well. Glad we're on the same page!

@jamesqquick Ditto to @brianmmdev, I phase the check points or levels as branches so there is complete (main) but then a level 0 setting requirements, etc and the branch 1 is step one…

Any tips on supporting a "start" and an "end" branch in a Github repository that you're using for a course, workshop, guide, etc. It's always such a pain to make updates to one then propagate it to the other!

@pkellner Yeah I've done folders before too. It's also just hard to maintain. I think that's the reality regardless though lol

@jamesqquick Separate folders. Users never understand tags and branched. Global search and replace is your friend. github.com/pkellner/plura…

@BekahHW @continuedev Using an LLM to interpret a user request and convert to a tool call I'm good with. It's the return of the tool data that I'm debating how to handle rendering different UIs based on the tool call and the data returned. That make sense?

Idk if this applies to your use case, but we have AI agents you can create at @continuedev that work with MCPs using natural language. You can checkout our cookbooks to see some examples #mcp-integration-cookbooks" target="_blank" rel="nofollow noopener">docs.continue.dev/guides/overvie…. Quick example, I made a Posthog- GH agent that looks at my recent Posthog data (using the Posthog MCP) and creates GH issues on the repo based on the analysis of the Posthog data (done by Continue’s CLI).

If I write a chat bot that connects to an MCP server, should I be writing custom code to handle the response from the MCP server directly? For example, if I want to render a specific component based on a tool call, I have to explicitly know the type of the data right?

@seancdavis29 @cursor_ai Fun fact. The code it wrote before didn't work lol

@jamesqquick @cursor_ai Face it, Cursor. I didn’t read what you wrote before.

The equivalent of "per my last email" from an LLM. First time I've seen @cursor_ai try to get smart with me 😅

In today's episode of AI generated code...

@ryandotfurrer @cursor_ai Apparently 🤷‍♂️

@jamesqquick @cursor_ai Oh LLMs are getting sassy now?

Something tells me this is spam…