I have used Github copilot since their beta release in 2023 and I don't find it anywhere near good these days. Automplete was good, but the industry has moved way beyond 2025. Copilot is slightly worse than Cursor which is itself a pretty average tool now. If you use truly agentic code generation, you won't be able to go back to Github Copilot.

You don't consider copilots agent mode to be agentic? I've had some pretty great results with agent mode + mcp to have it check it's own work.

Yes, in this case. $120 is worth as it woudl have cost me $500+ otherwise. But, I was quite careful. In a large organization, this can quickly get out of control.

I have been using the Claude Code for about 48 hours now and nearly done with one full MVP. It did both my FastAPI side, building all the models guiding me through the Postgres part as well as a well polished React frontend. Burnt about $25 in 2 days [I have a lot of Anthropic credits] and created about 10k lines of good quality code all the way to a deployment. It is scary how much it can do to the point I'm not sure how long I will be needed.