My next massive AI/automation project is to automate the research and drafting of my queer film database posts so a few of my main entry points trigger it all off - and it runs in the background to prepare compiled and review-ready posts for me to review and schedule. That means using Gmail labels as trigger (along with manual Airtable entry and IMDb or TMDb list additions) which then works through my IMDb API scraper, followed by a TMDb scraper, and lastly running through a few other scrapers/API checks for the streaming platform availability - all with a home base in Airtable. All to reduce the manual work it takes hours for me to do!

@Wendy Breakstone Yep! Last year I had a custom IMDb scraper built to specifically grab the many fields I use for my posts so they align. I know that Apify has existing scrapers for some of the other platforms I need to add into the entire system (although at least one is actually no longer current last I checked). The biggest crux I haven't quite sorted out with Claude Code yet is fitting all the pieces together in an organic way that works with how I would add films to the Airtable base for the drafting/research mode, batch the scraping when needed or triggered, and set it up in stages for where I need to add my personal input. All built out via n8n workflows to connect it. (Where I already have a workflow that pushes films from my Database Airtable base to my main Wordpress site, a second one that duplicates content to the Database domain as I'm prepping to launch that as its own "product", and then a third still being built that syncs it all back to Airtable). And as I type out even that summary, it's scary how massive the plan really is - but will be SUCH a timesaver when I get it up and running even partially!

I can't say that I've LOST a chat... which in general would be rather odd since even the Desktop App uses the claude. ai interface. (Something I learned when building my Cross-LLM Archive and Memory System!) When you open the list of all your chats, can you still not see it in there? There's even a search bar you can search, as well as a filter for whether it's a chat vs cowork session, or if it's been archived (mainly for cowork sessions, but with the merge I wouldn't be surprised if chats get archivability soon!) But I DO know that your local cowork sessions ARE actually local files, NOT in the cloud. So if a Cowork session disappears from your list, then it does exist. But not the easiest to find - and part why I built my archiving system in the first place!

SINGLE-STEP connectors, which is the crux of the players such as Relay.app, Pabbly, Make, and others are now at risk due to the rise of MCPs, absolutely! But for multistep workflows, or ones that connect more than one tool within the same workflow aren't going far. (n8n may not be the "hottest" ticket among all the "tech gurus" - but it's not going anywhere!) In fact, I recently had Claude help me migrate a single workflow I had on Pabbly's free plan over to my n8n workspace. While I have many more n8n workflows running now, I couldn't set up most of them in Pabbly even if I paid. So these connector tools are going to need to adapt - or they risk shutting down like Relay. Not everything requires AI tool to run. AI can certainly help set up webhooks, write scripts for automations that can link tools (looking at Airtable!) and more - but there's a hidden cost that many are not factoring in: AI tools themselves cost. Sure, the highest plans have a LOT of room before you hit limits, but that's with the current setup. With the massive increase of AI tools, the never-ending push to make them "better" and more autonomous, we've only just begun to see the "cost" impact they will be once things settle a bit. Just look at Fable - even with the Claude's Max plan, it's capped at 50% of your limits. And if you're not on the Max plan (like many who can get buy on the Pro plan), then it's not included in your plan at all! So there's now an extra cost in tokens or buying credits if you want to use Fable on lower plans. And I would expect to see that become more common as AI tools roll out their newest plans.

@Wendy Breakstone From what I can tell, there's still an unanswered questions of whether Cowork running via web/mobile will only be limited to what it can do online via web connectors/online info - or if it will also link to and can use your desktop files and Cowork tasks. Because the backend is still separate via where both Chat chats and Cowork sessions are stored locally - though whether it stays that way is yet to be determined.

Someone else had pointed this change out - and I immediately started digging into it, as it directly impacts my cross-LLM archive project that hinges on the desktop app (and the locally stored files!) The "merging" of project folders, yet the inability to move chats/sessions to a folder pulled in from the opposite interface is rather odd. Feel like it's more of a hiccup than intentional though, because why merge them if you cannot move chats & sessions into a project folder. (And I just realised that I haven't tried setting up a NEW project post merge yet - I wonder if a new project would have the structure to allow both in?) What I CAN add here is that for now, your the local file locations have NOT changed. Without getting too technical (partly because I only JUST understand enough of it myself!), the desktop app stores local history files for your Chat chats; it's not just a web interface pulling in the web chat history. Naturally Cowork has always kept its sessions saved locally thus why it requires the Desktop App. With this merge, it's currently only showing in the apps interface (and online when it's rolled out to all of us on lower plans). But unless they plan to FORCE the desktop app to relocate the physical locations of both chats and sessions, they will still stay separate on the backend. Or they may create a third location moving forward... oi! The renaming of "pulled-in" projects is irksome, but again so far on the backend, they remain separate.

One thing I've noted with Sonnet 5 is that all of the "thinking" in between responses (which you can click the down arrow to view and follow along - esp. as my Claude is well-known for disregarding rules that I have to babysit IT!) are now hidden. AND IT'S Not just from the interface either - if you open up the actual transcript of the chat, the entire thinking section is one encoded chunk! Actually thought some other setting had changed, but figured out that it's Sonnet 5 itself doing this. Starting a new chat in 4.8 showed the thinking steps as before.