Skip to content
Notis

Know what to ask when an email is unclear

Get help spotting missing context and drafting the few questions that could move the conversation forward.

Trigger

New Email Received

Trigger for new emails in an AgentMail inbox

Action

Create Anthropic Message

Tool to create a model response using DeepSeek's Anthropic-compatible API format with support for system prompts, tool calling, streaming, and thinking mode. Use when you need to generate chat completions using the Anthropic Messages API format. Requires base_url='https://api.deepseek.com/anthropic' or metadata base_url ending with '/anthropic'. Supports extended thinking, function calling with tools, and streaming responses. Note: Images and documents are not supported in content blocks.

Why this helps

Vague requests can lead to guesswork, long reply threads, or work that needs to be redone.

  • Highlight ambiguity before you commit to a task.
  • Ask focused questions instead of sending a long back-and-forth.
  • Keep uncertain details visible rather than filling gaps with guesses.

Setup

Build it in a few focused steps.

  • 1Connect Agent mail and DeepSeek once in the Notis portal.
  • 2Create an automation in Automations, New Automation, or tell Notis from a channel.
  • 3In one instruction, ask Notis to identify missing information and draft no more than three concise clarifying questions.
  • 4Choose Agent mail's New Email Received trigger and select where run reports should go.
  • 5Test with one real email that has an ambiguous request.

Questions about this workflow

Will it decide what the sender meant?

The instruction should ask it to identify ambiguity and ask questions, rather than assume unstated intent.

Can I set a limit on the questions?

Yes. Include a limit, such as no more than three questions, in your instruction.

When this happens · Trigger

Do this · Action

Supported Triggers and Actions

Notis builds workflows that link Agent mail to DeepSeek. A trigger fires from one place; an action lands in another.

Agent mail triggers

DeepSeek actions

Recurring trigger

Notis starts this workflow on a schedule, such as daily, weekly, or during business hours.

TriggerScheduled

Create Anthropic Message

Tool to create a model response using DeepSeek's Anthropic-compatible API format with support for system prompts, tool calling, streaming, and thinking mode. Use when you need to generate chat completions using the Anthropic Messages API format. Requires base_url='https://api.deepseek.com/anthropic' or metadata base_url ending with '/anthropic'. Supports extended thinking, function calling with tools, and streaming responses. Note: Images and documents are not supported in content blocks.

ActionInstant

Webhook trigger

Notis starts this workflow when an external tool or custom backend sends an HTTP request.

TriggerInstant

Create Chat Completion

Tool to create a chat completion using DeepSeek models (deepseek-chat or deepseek-reasoner). Use when you need to generate AI responses to chat conversations. Supports streaming, tool/function calling, and various parameters to control generation behavior (temperature, max_tokens, etc.).

ActionInstant

New Email Received

Trigger for new emails in an AgentMail inbox

TriggerPolling

Get User Balance

Tool to get user's current account balance including granted and topped-up balances with detailed breakdown by currency (CNY or USD). Use when you need to check if the user has sufficient balance for API calls or to view detailed balance information.

ActionInstant

List Models

Tool to list currently available DeepSeek models and provides basic information about each one such as the owner and availability. Use when you need to discover which models are available for API calls.

ActionInstant

Connect any two apps with Notis in the middle.

Agent mail and DeepSeek, 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 DeepSeek.