Reuse stable support guidance across AI calls
Keep recurring support instructions ready to reuse so each request can focus on the new customer context.
Trigger
Webhook received
Notis starts this workflow when an external tool or custom backend sends an HTTP request.
Action
Prompt Caching
Tool to cache and reuse prompt content to reduce costs and latency. use after you have static prompt portions you intend to reuse across calls.
Why this helps
Repeating long, stable guidance across AI calls adds friction and can increase request costs and latency.
- Reuse static support guidance across calls
- Reduce repeated prompt content for stable instructions
- Keep fresh customer details separate from reusable guidance
Setup
Build it in a few focused steps.
- 1Connect 2chat and Anthropic administrator once in the Notis portal.
- 2Create an automation in the portal or tell Notis in plain language from any channel.
- 3In one instruction, ask Notis to cache the static support guidance you provide for reuse across calls.
- 4Choose a webhook trigger and where run reports should go.
- 5Test with one real example and confirm the intended static content is the content being cached.
Questions about this workflow
What content should be cached?
Use stable prompt portions such as support policies or response guidelines. Keep changing customer messages out of static content.
Does caching write a reply to WhatsApp?
No. This action caches prompt content for reuse; it does not send a WhatsApp message.
When this happens · Trigger
Do this · Action
Supported Triggers and Actions
Notis builds workflows that link 2chat to Anthropic administrator. A trigger fires from one place; an action lands in another.
2chat triggers
Anthropic administrator actions
Recurring trigger
Notis starts this workflow on a schedule, such as daily, weekly, or during business hours.
Create Message
Tool to create a new message completion. use when you need to generate assistant text given a conversation history.
Webhook trigger
Notis starts this workflow when an external tool or custom backend sends an HTTP request.
Get Model
Tool to retrieve details of a specific model by its id. use after confirming the model id is valid.
List models
Tool to list available models. use when you need to see which models are available before selection.
Prompt Caching
Tool to cache and reuse prompt content to reduce costs and latency. use after you have static prompt portions you intend to reuse across calls.
Connect any two apps with Notis in the middle.
2chat and Anthropic administrator, or any other combination from 1,000+ integrations.
When this happens · Trigger
Do this · Action
Save your first hour today.
7-day trial of any paid plan, with 20$ of usage included.
No card. Works with personal or business Anthropic administrator.