Forge

There is a dark truth you hit quickly when you start building with agents: more agents ≠ more work getting done. more work getting done ≠ progress you can trust. Forge is built for serious agentic engineering. Stop babysitting terminals. Start governing the work.

@JuiceSharp What workflow do you use to solve this? And how often do you find yourself setting up for new projects?

@ForgeBuildsIt Any good workflow solves that exhaust …

Specs are not the whole truth of a build. As your project grows, architecture evolves, features morph, and surface gaps emerge mid-build. Your tools completely disregard that or bury context in chat history, no binding effect on implementation. Forge workflow solves that.

@trq212 Specs are not the whole truth of a build. As a project grows, architecture evolves, features morph, and surface gaps emerge mid-build. Current tools bury that context in chat history, with no binding effect on implementation. This is a core reason we're building Forge.

a prompt I've been using a lot recently: implement <SPEC> and while you do, keep a running implementation-notes.html file (or markdown) with decisions you had to make weren't in the spec, things you had to change, tradeoffs you had to make or anything else I should know

@yesh Will use of Claude Code on your be affected by Anthropic's latest subscription usage changes?

alright kiri now has "terminal" mode and supports all terminals including claude code there is some jank with moving between sessions. just need to iron it out

@ConsortiumAI This is like the coach playing in the game.

OpenAI just launched a consulting company. $4B initial investment. Acquired Tomoro (150 engineers). Partnered with Bain, TPG, Advent, and 16 others. The frontier labs aren't selling models anymore. They're selling implementation. What are you implementing?