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.
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.
@kate_sleeman It is self-improving, so it's constantly looking for things that break and suggests fixes on it's own. But you can update the process with a simple message, then it'll test it, and if you like the results, it ships the new version.
@maklyen_may Most people don't even realize how much repetitive work that they do. Caddi has a "discover" function, where it proactively checks your tools and finds your most repetitive work, and then tries to automate it.
@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.
@aarav_pittman It is actually best at long-running, multi-step, multi-tool tasks. We're particularly proud of our accuracy at 6+ steps (and even tools).
Report
How well does Caddi handle exceptions when the real process differs slightly from the example?
@khaildnaseem It has AI reasoning steps to handle obvious exceptions, but for unobvious ones, it surfaces to the creator, suggests a fix, implements/tests it, and then deploys.
Caddi
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.
AstraPixels
@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?
Caddi
@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.
Hedy AI
How does it handle small change in the process? That's usually where automations break for me.
Caddi
@kate_sleeman It is self-improving, so it's constantly looking for things that break and suggests fixes on it's own. But you can update the process with a simple message, then it'll test it, and if you like the results, it ships the new version.
Serand
Talking out loud while doing the task feels way more natural than manually building a giant diagram.
Caddi
@maali_baali That's the beauty of it. Plus it asks questions back to clarify ambiguity or gaps in your explanation.
@jason_alafgani congrats on the launch, great product best of luck guys.
TrackerJam
I can see this being useful for all those boring admin tasks we keep doing every day.
Caddi
@maklyen_may Most people don't even realize how much repetitive work that they do. Caddi has a "discover" function, where it proactively checks your tools and finds your most repetitive work, and then tries to automate it.
Hubble
Would this work for healthcare use cases?
Caddi
@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.
Bababot
Can it handle workflows that hop across 3 or 4 different apps in one go?
Caddi
@aarav_pittman It is actually best at long-running, multi-step, multi-tool tasks. We're particularly proud of our accuracy at 6+ steps (and even tools).
How well does Caddi handle exceptions when the real process differs slightly from the example?
Caddi
@khaildnaseem It has AI reasoning steps to handle obvious exceptions, but for unobvious ones, it surfaces to the creator, suggests a fix, implements/tests it, and then deploys.