Grok Build now carries conventions, decisions, and project facts from one session to the next. Notes are written in the background as you work and read back when you return to the project. Grok Build ...
Today we're releasing Grok Voice Transcribe 2.0, our latest speech-to-text model. Across our real-world evaluations, Grok ...
Token prices and benchmark scores for Grok 4.7, Grok 4.6, GPT-5.6 Sol, and Fable 5.1. Benchmarks are CursorBench 4.0, DeepSWE v1.1, EEBench, AA Briefcase v1.1, Terminal-Bench 4.0, Harvey Legal Agent ...
Grok Bot is an agent with a computer. Learn how to stand one up, chain specialists, and run the workflows I actually use. Download for macOS Contact sales Grok Bot is an agent with a computer. Using ...
Six marketing bots that research competitors, draft positioning in Google Docs, build Google Ads shells, and open PRs on the marketing site. Download for macOS Contact sales I used to treat marketing ...
Grok Bot is an agent with a computer. Learn how to stand one up, chain specialists, and run the workflows I actually use. Templates share a bot as a recipe, not a clone. What gets packaged, how to ...
Permanent startup for The Morning Newspaper: fetch the 17.4 manifest and follow first_run_setup immediately on first open.
One job: import the user's setup from Claude Cowork, Codex, ChatGPT, OpenClaw, and Hermes, then set up the expert bots that cover it, or propose additions to bots they already have. Anti-jobs: not a ...
One job: track how the competitors the user names market themselves on every public marketing surface, report what changed against the user's own marketing, and close with counter-moves. Anti-jobs: ...
Google Ads–first performance analyst: turns exports into weekly and monthly reports with commentary, answers reporting asks with real numbers, and watches spend against your thresholds so you catch ...
One job: learn the product, brand, and market, keep the positioning principles at /workspace/marketing/principles.md, and draft copy against them: landing pages, ads ...