Launching today
Yedric.ai
Let users control your SaaS with natural language
520 followers
Let users control your SaaS with natural language
520 followers
Your users shouldn't have to learn where every feature lives. Yedric adds an embeddable AI agent to your SaaS that turns natural-language requests into actions your product already knows how to perform. Users simply say what they want done and Yedric handles the interaction. Instead of building and maintaining your own agent experience, developers can make their existing product AI-native in under 30 minutes.
Building my own in-app assistant for a field-sales app taught me the hard part isn't understanding the request, it's deciding what the agent is allowed to do without asking. Reading data is easy, but deleting a customer or changing a contract is not. How do you handle confirmation for destructive actions? Is that set per action by the developer?
MESA
@richysem
You can try to be clever about it and require extra confirmation in the chat before allowing destructive actions.
But if you're really concerned about destructive actions, I think the safest approach is to use the AI to guide the user to the appropriate place in the UI, where they have to perform the destructive action themselves.
For instance, if a user asks the AI to delete something, instead of deleting it directly, the AI can point them to where they can delete it in the UI. That way, the AI is still assisting the customer and helping them accomplish what they want, without actually performing the destructive action on their behalf.
The embeddable approach caught my attention. Being able to add this without building a whole agent experience from scratch could save a lot of development time.
MESA
@manisha_bhil Yedric is very simple to set up, and even if you’re just pointing it at your documentation, it takes almost no development effort to get started. If you want to take it a step further, setting up custom actions can elevate the experience to an entirely new level. I’d recommend starting with the documentation integration first, getting a feel for how it works, and then experimenting with custom actions from there.
the idea of making ai agents feel more natural is really interesting especially when they can actually handle task instead of just chatting
MESA
@shivam_kushwaha16 Thanks, that's the part we're most excited about! Writing clear step-by-step help docs is tough, and following them can be just as frustrating. It's so much nicer when the assistant just does the task instead of explaining how to do it.
Mailwarm
Nice approach, letting users just say what they want instead of hunting through menus is where most SaaS products lose people. Does the embedded agent map requests onto existing actions you define, or does it try to infer new ones?
MESA
@karimbenkeroum The prompts aren’t inferred automatically, so you do have to set them up yourself. However, if a user asks a question and the answer is available in your documentation, the AI can answer it for them automatically. It’s really just the suggested prompts that you need to configure and map to the appropriate pages.