I don't know if it's just my perception, but I think the "channels" feature is massively underestimated. I get that it's basically their response to openclaw, and people kind of had enough of that stuff, but having my agent in my favourite messenger is a game-changer for me.
It's different for me from just app chat, because I have some specific custom workflows and tools I gave to the agent, and, yes, all of the nice stuff mentioned in other comments
- Like normal software engineering - building small parts in isolation, verifying they work and then bringing them together to make the whole.
- Asking Claude to do things using sub-agents to keep the parent context clean. i.e. reviewing plans, research, code reviews
- If there's ever something you can have verification on - a test suite, a screenshot with pixel reading, a certain output to match. Then with `/goal` it tends to work very well with little guidance (in my experience)
- If it keeps getting things wrong, then I make it write a skill. i.e. for some reason it always had errors running playwright but would get there in the end, and it would always have trouble with auth on my NAS but with the skill it can follow the path that's worked for it in the past and not burn tokens
I do the same i would add sometimes when it gets stuck and gets things wrong i go to chatgpt to figure out the issues then go back to claude and it agrees and self correct. i have used claude to help me launch my project [https://thrivez.io].
I don't know if it's just my perception, but I think the "channels" feature is massively underestimated. I get that it's basically their response to openclaw, and people kind of had enough of that stuff, but having my agent in my favourite messenger is a game-changer for me.
It's different for me from just app chat, because I have some specific custom workflows and tools I gave to the agent, and, yes, all of the nice stuff mentioned in other comments
when you're doing that, do you have to use claude's cloud code system? Or can you link to a local repository?
A few things that have worked well for me:
I do the same i would add sometimes when it gets stuck and gets things wrong i go to chatgpt to figure out the issues then go back to claude and it agrees and self correct. i have used claude to help me launch my project [https://thrivez.io].
I've been finding that I don't even have to ask Claude to make subagents anymore. It does it by itself most of the time in Opus 4.8.
That's true
When you run into a bug/problem, asking it to find the source instead of asking it to fix it
Real-time web data access capability.