Everyone's setting up Grok Bot. Then they look at the empty box and think: "ok... now what?"
So I made 5 ready-to-use bots you can copy and paste:
📥 Inbox brief
📅 Meeting prep
🧾 Weekly expense sweep
🔔 Price/listing watcher
📄 Research-to-doc
Free: https://t.co/q8BoKJitJu
Claude Code, Codex, AmpCode. Self-hosted orbs and runners, locally built inference, custom MCP servers.
TypeScript/Go underneath. Building an engineering operation where I set direction and fleets of agents execute in parallel. More throughput means more compute!
Have been in the SWE space for 15 years now. Based in Oceania.
reckon a lot of agent speed is gonna come from the boring tools getting rewritten, not just better models
apparently Opus 5.5 wrote tsrs too which is a bit funny 😅
anyone swapped their agent's tools for faster ones yet?
been thinking about why fast type checkers matter more for agents than for us
I run tsc a few times an hour. an agent runs it after basically every edit, reads the errors, tries again
so the checker's speed kinda is the agent's speed
say an agent checks 50 times in one task. that's ~12 mins sitting around on the old tsc vs ~20s on tsrs
and that's before linters, tests and builds, which agents hammer too