A content system that drafts blog posts, social posts for six platforms and a weekly newsletter in your brand voice, schedules them, and waits for a person to approve before anything goes out.
The problem
Content takes hours of writing before anyone can judge whether it's good, and every platform wants its own format. Most teams end up posting less, or posting the same text everywhere.
What it does
A system that writes the first draft of everything in your voice, adapts it per platform, checks it, and queues it. People spend their time deciding and editing instead of starting from a blank page.
Built for
Founder-led B2B companies that post on LinkedInSmall marketing teams covering several channelsTeams with a weekly newsletter and a blog
An AI agent that triages your inbox, drafts replies from how you answered before, sends action items to your task app, and never sends anything without your approval.
The problem
Most inbox time goes on the first pass: working out what each email is, what it needs, and writing the same kinds of answers again. Important threads get buried under newsletters and promotions, and action items live only in your head.
What it does
An agent that does the first pass for you. It sorts and summarises every email, drafts the replies that need one in your voice, puts action items in your task list, and waits for your approval before anything is sent.
Built for
Founders and operators who live in their inboxOps and account managers handling customer threadsSmall teams that share a support or ops mailbox
AI code review on every pull request: comments on the exact changed lines, a summary, and the tests worth adding. A GitHub Action, a CLI and a web UI.
The problem
Reviewers spend their attention on things a careful first pass would catch: an unparameterised query, a missing await, a secret in a log line. Most AI review bots either post noise or fail silently when GitHub rejects a comment.
What it does
A reviewer that comments only on real problems, on lines GitHub will accept, with suggested fixes and the tests worth adding, so human review starts from the important questions.
Built for
Small teams without a dedicated reviewer for every PROpen-source maintainers triaging outside contributionsTeams that want a security pass on every change
Scaffold production-ready Next.js, Node, Python and Salesforce DX projects, preview every file before you download, and write READMEs from your code with AI.
The problem
Starting a new service means an hour of copying config from the last project: lint rules, test setup, Dockerfile, CI. Half of it is out of date, and the README is the last thing anyone writes.
What it does
A generator that produces a current, working project for each stack you use, shows you every file first, and writes the README from the code when you're done.
Built for
Teams that start new services oftenAgencies and consultancies with a house styleSalesforce teams that want LWC tests and linting from day one
