i am not clear what exactly will these agents do? are they like ai sales rep for brand for talking to user if they want to explore the product further?

Yeah, basically this. Some people really do click on ads that are relevant to their interests and might want to learn more or be able to ask questions about the product. I'm not confident about how well it will work in practice, but I could imagine cases where this would be more helpful than clicking on the ad link and needing to explore the resulting website to find the information I want.

working on adding webmcp support to my new free tool https://easyanalytica.com/tools/gsc-insight , webmcp was recently added to codex desktop app and it would be interesting to see how users use it with ai, would it get good adoption or it would just go away.

what are you using for reading/writing pdf? is it some mcp plugin or some pdf lib in python/js and qwen is doing it via code?

i have same 255h and i was able to run it with low token speed 6-8tg/s with approx similar context window 60k

Interesting. What are you using? I was using ollama

i am using llama.cpp with pi harness on linux(cachyos). some of the things like coopmat are disabled in linux due to intel driver issues otherwise performance would be even better.

Don't bother with plans

I am building https://EasyAnalytica.com - single place for all your dashboards. It generates dashboards automatically from data without using ai. It supports getting data from google sheets, api's, url's etc. I have recently added support for gsc as data source and i plan to continue adding more in coming weeks.

+1. i have similar workflow and i use local models on igpu so token cost is free and electricity cost is in cents.

I cannot imagine local models running on an igpu could get anything close to either a useful plan or execution of a plan. I've tested Qwen 3.5 27B locally and its solutions to coding problems are usually flawed and running in thinking mode is too slow and that's on a discrete GPU. How do you get anything useful done on a model that runs on an igpu?

yeah, i dont understand, whatsoever, the folks who are running models locally other than for privacy/curiosity. It is surely FAR slower, more expensive (electricity + hardware costs), and worse quality. Better to outsource to providers who have optimized everything and costs are distributed/amortized across all users.

Perhaps someday local llms will be sufficient for coding etc, but it's going to be a while.