Caddi
Agent that builds agents by only showing your work only once
617 followers
Agent that builds agents by only showing your work only once
617 followers
Caddi turns narrated screenshares into production agents that run back-office work across your real tools. Show the task once, and Caddi learns the process, builds the automation, and lets you update it in plain English. Unlike RPA or workflow builders that require scoping, developers, and step-by-step setup, Caddi combines AI reasoning with deterministic execution, with every run logged and every permission scoped.
Free Options
Launch Team / Built With
Render: Get up to $100K in startup creditsCloud infrastructure for founders who want to move fast and NOT break things
Promoted
Hey Product Hunt 👋
I'm Jason, one of the makers of Caddi. Caddi is an agent that builds agents.
We build for law firms, RIAs and accounting firms, and the same thing kept coming up: the work isn't hard, it's just endless. A contract comes back signed, someone downloads it, renames it to the firm convention, files it to the matter, logs it in the CRM. Forty times a month. Every month.
Automating that has always meant a project. Scope it, spec it, configure it, get a developer. So it never happens, and people keep doing it by hand.
Caddi takes a different path, and it starts before you build anything: it reads your stack and tells you which work you repeat most, ranked by impact.
You pick one, and then you teach it like a new hire, except this new hire already knows the job. It follows your guidance or guides you with best practices, and probes for edge-cases: not just "download the contract", but "say how you tell an executed copy from a draft".
When it hits something ambiguous it stops and asks, with the options laid out and a confirm button. What if only one party has signed? Your answer doesn't disappear into a transcript. It becomes a rule in the agent.
What comes out reasons with AI where judgment is needed and runs deterministic code where it isn't, so the messy cases get handled without the exact parts going off-script. Then it runs in the cloud, executing thousands of actions at a time.
And you can see all of it. Every run is a log of what it decided, step by step, with the permission it used to do it: read, create, send.
We'd genuinely love your feedback, especially on where you'd trust an agent and where you wouldn't. That line is the whole product for us.
@jason_alafgani Congrats on the launch Jason. Really interesting project and sounds complex. Where do your law firm customers draw the trust line in practice? Read and create but never send?
@nicklaunches Sending is just one action that these agents can do, and lawyers trust their Caddies to do all the operational work that their associates and partners do. Client intake, keeping all of their tools talking to each other, conflict checks, pre-billing,...the list goes on and on.
If you can teach someone to do the job over a screenshare, then you can give that job to Caddi.
Would this work for healthcare use cases?
@prabhadublish Operational work, yes absolutely. We are have not received HIPAA compliance certification, so we don't recommend putting patient data through our systems. But across employees, dealing with insurance, and the broader health ecosystem, there's lots of operationally heavy (forms, spreadsheets, docs, lots of SaaS tools to jump between) work that Caddi can automate.
Wow, that's super cool. In most firms two people doing the same task do it differently so whose version becomes the rule? Does it even matter?
@tmaleh_ We see this frequently. Most teams build one Loop and share it so everyone runs the same version, though some prefer that each person set up their own. Both are easy within Caddi. One firm actually ran a "competition" to find the best way to automate timekeeping and made the winner the standard across all attorneys.
Congrats to the team. Good call having it stop and ask on the ambiguous ones instead of guessing.
@lucasjpols And it doesn't stop after the first build. It's what we call "self-improving" in that it's constantly identifying ways to get better, and then after your approval, implements those improvements.
what happenes if there is no api to use for a process? how can it handle that?
@nave_zakine there are often batch work arounds like csv uploads.
Here's a pure <60 sec demo of how Caddi discovers and automates repetitive work:
https://youtu.be/GdCP1bJp_3o?si=lcJFF1mE6S0l3DYK
I literally saw this and I said out loud: "No Way!". Early I was talking to someone on my team, this is literally my new assignmnet but with Copilot. I want to mention this tool to my team.