On Launch Llama
Caddi
For operations teams: Caddi learns your back-office process from one screen recording, then builds and runs the automation across your real tools so you stop doing repetitive work.
Built by Alejandro Castellano, Aditya Sastry, Jason Alafgani and 1 other
Freemium
Visit website → Upvotes · 305
Caddi is a Product Hunt listing on Launch Llama with 305 total upvotes, founded by Alejandro Castellano, Aditya Sastry, Jason Alafgani and 1 other who joined in Aug 2026, compared against 6 alternatives.
Product Hunt listing
Listing status
305upvotes
Community score
Alejandro Castellano, Aditya Sastry, Jason Alafgani and 1 other (Joined Aug 2026)
Founder
Compared against 6 alternatives
Market comparison
Real numbers
90d
-
0
Views
-
0
Visitors
-
0
Clicks
Public Launch Llama traffic for this listing.
Key Features
- Discover repetitive work across connected tools with evidence
- Train AI agents through screenshare without writing code
- Govern firm-wide visibility into every agent run and decision
- Integrate with 150+ tools without replacing existing systems
- Automate back-office tasks across your entire tool stack
About
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.
Use Cases
- Record invoice processing workflow, let Caddi build automation, monitor execution logs before deploying
- Use Caddi's plain English update feature to modify an existing back-office automation without developer involvement when your vendor's portal changes
- Create automation from employee onboarding checklist recording; Caddi handles repetitive HR and finance steps
- Show Caddi once how to gather data from multiple systems for reports; it runs on schedule with execution logging
- Record vendor payment approval process once; Caddi executes it deterministically with scoped permissions and audit trails
Pricing
Free Individual plan for one user. Team plan at $250/user/month for up to 10 employees. Business at $6,500/month. Enterprise custom pricing.
FAQ
How is Caddi different from Claude or ChatGPT?
Claude and ChatGPT reason through a task every time you run it, spending tokens to re-decide each step. Caddi uses models to build the automation and for the judgment steps inside a run, then runs every fixed step as deterministic code. The same input takes the same path every time, so every run is reliable and auditable out of the box, and it costs about a tenth as much to run, because execution does not spend tokens.
How is Caddi different from Zapier or Power Automate?
Zapier and Power Automate start from a blank canvas: you have to know what to automate and wire every step yourself. Caddi starts with Discover, which finds the repetitive work in your tools, and then anyone on the team can automate it by showing it on a screenshare or describing it in chat, with no flow builder. After that, Caddi governs and monitors every run, so a broken automation is flagged and fixed instead of failing quietly for weeks.
How is Caddi different from UiPath and traditional RPA?
RPA is built and maintained by IT or a developer, and a script breaks when a screen changes. In Caddi the person who does the work builds the automation, and when something drifts Caddi flags it after the run and proposes the fix for you to approve.
How is Caddi different from other AI agent platforms?
In a network of agents, each agent keeps its own memory of what it has seen, and together they form sharded knowledge bases spread across the network. That burns tokens on every handoff and slowly pulls data out of your firm's systems. Caddi is plumbing: each agent owns one process and moves data between the sources of truth you already own, so the same input takes the same path every time and every run can be replayed.
How is Caddi different from process mining tools like Celonis?
Process mining reads event logs and tickets, so it only sees work that is already tracked. Caddi's discovery is agentic: it starts from hypotheses grounded in deep industry expertise, then validates them in your tools. That finds the unknown work too, in the context of your industry and the process underneath it. Then Caddi automates what it finds and governs every run, in one product.
What happens when the work changes?
It always does. Tell Caddi what changed in plain English, or share your screen for the new step. Caddi updates the plan and you approve the new version before it runs.
Alternatives
- Rerun
For operations teams: Rerun builds visible no-code agents that chase invoices and qualify leads 24/7 with approval gates so sensitive tasks stay controlled.
- Just247Pipes
Teams use Just247Pipes to automate repetitive tasks across support, sales, marketing, and operations by connecting tools and building AI-driven workflows that run 24/7.
- Cronloop AI
For teams: Cronloop AI runs autonomous agents on schedules from 5 minutes to weekly, with durable memory and self-improvement so repetitive work happens automatically.
- Autonomous Product Delivery
Discover, plan, build, ship, repeat. Product teams run it
- Tines
For teams building automations: Tines is a vendor-agnostic platform to build, run, and monitor intelligent workflows across your tools.
- Jet Admin
For operations and support teams: Jet Admin builds AI agents without code that take action across 200+ tools via Slack, WhatsApp, or Telegram.
Ask AI
ChatGPT Claude Perplexity Grok
For agents
llms.txt · llms-full.txt · ai.txt · Live fact sheet · Full catalog (.md) · Endpoint index · API spec · REST access · Agent server · Server manifest · Server discovery