Team @mainframe doing awesome stuff as always

2026 is the year agents move to the cloud, and top startups like ramp already live in this future. unfortunately many companies are unprepared. to help, we @mainframe wrote down all we know about making codebases cloud agents ready. hope it's useful!

if you’re in NYC, we’d love for you to stop by our @mainframe office in near Flatiron to chat DM me

if you've got thoughts about code review at a company of any size and are willing to chat to help us build something, please reply or DM!

fable produced 60+ (!) ready to merge prs for @mainframe overnight. here's how you can set up a software factory using fable as an orchestrator. prompt included! 1. narrate your *entire* todo list — everything that's top of mind — using dictation. i used @usemonologue and my prompt was ~10K words! you have to use voice because we want excruciating levels of detail. 2. locally, tell fable to plan all the work and put it in @linear. the goal is to make it such that a dumb model dropped in linear knows *exactly* what to do. aka all issues should have a clear DAG, plan, and optimize for max. parallelizability. i recommend running fable on high and having it fan out to codex subagents on xhigh (using the cc codex plugin.) to save usage. just make sure that fable itself is doing the architecture for the hardest issues! 3. now switch to @DevinAI. we'll use devin to run our factory because our orchestrator needs to be a cloud agent (it's going to run for a long time!), and be able to spin up other cloud subagents. 4. hook up the @linear @SlackHQ mcps. this will let your agents read the fable planned work, and communicate with you/your teammates. e.g. it can talk to your coworkers to make sure it's not stepping on anyone's feet! 5. a good feedback loop is *crucial.* before starting, make sure you have a bug bot (we use @cursor_ai.) and that your agents can test all its changes. e.g. we use the fantastic @limrun to make sure our agents can do ios development e2e. 6. create a devin ultra (fable) agent — this will be your orchestrator or 'middle manager.' we're going to tell it to look at linear and dispatch subagents for all tasks. the middle manager's goal is to keep spinning up subagents with the right level of intelligence until all the work is done. and keep all agents unblocked while you're sleeping, hanging out in the park, whatever! the reason the middle manager is able to orchestrate all of this is because fable planned everything in linear. and because the middle manager itself is also fable (contrary to most of its subagents.) 7. to prompt your middle manager, attach the middle manager prompt i'll post in the comments, modified for your repo. it's important that we *attach* the middle manager's prompt to our conversation vs. typing it out, so it never gets compacted. the middle manager's context window is holy. so our prompt tells it to spin up subagents — instead of doing things itself — for pretty much everything. 8. the prompt has some other cool, non-obvious details. firstly, every agent is told to keep working until it's met the burden of proof. in our case that's a (self)-review, bug bot being green, bug bot fixes being elegant, and a recording. we tell our middle manager to enforce this. secondly, we ask the middle manager to make sure linear stays up to date and communicate via the slack mcp. specifically, it should tag coworkers in slack whenever it has a question and post heartbeat updates in the eng channel. 9. your software factory is ready to go! in our case, it worked for 12+ hours without getting blocked. and produced extremely high quality prs. addendum: all of this is possible because with @AnthropicAI fable, models are finally smart enough to orchestrate/navigate large sets of work and their dependencies. and fable is a great software architect! now of course the 'downside' is that you're now review bottlenecked. we have 60+ PRs to review! but i think as an industry we should be able to come up with some innovation there. we'll certainly try our best to help here with @mainframe too! hope this is helpful! happy to answer any qs.

icon for upcoming @mainframe app

drowning in agent prs? watch videos instead! swap github dot com with pr.video to generate a video for any pull request.

pull requests are getting harder to keep up with as agents write more code @mainframe now turns any GitHub PR into a narrated video walkthrough so you can understand what changed without starting from the raw diff try it at pr.video

my daily Poke updates get delivered in iMessage as videos made by @mainframe

github checks

Agents are doing more of our work -- shipping code, writing documents, creating designs & campaigns. This creates a new problem: understanding what happened. @mainframe helps agents generate a short videos on what changed -- seems especially useful for opensource projects where many people are contributing independently (usually with the help of @claude)

wedding planning in the agentic era™: 1. dictate todo list using @usemonologue 2. codex /goal "save my wedding using the google workspace cli" 3. watch 2-3 minute @mainframe video recap with your fiancée

New Website Inspiration: Dark-schemed One Pager announcing @mainframe that turns agent work into recap videos for your team. Credit: @jsngr @vinvan @atlou_ Typeface: Inter → onepagelove.com/mainframe

the past year has been overwhelming. agents are always running, and it feels impossible to stay up to date on what they've done. unfortunately, this will happen in every area we introduce agents to. there has to be a better way?! at @mainframe, we think the answer is video.

Your agents, now playing:

The future belongs to designers who build. Watch your agents work with @mainframe

love this vision for @mainframe review is the new bottleneck and we need tools to stay happy and sane while reviewing tons of work