Product Updates for UpdateMate.ai

Sep 01, 2024

ShopifyQL Integration

We just added support for ShopifyQL 🥳

ShopifyQL is a SQL-like query language for easily getting any kind of analysis and stats from your Shopify store.

Our integration allows you to create several metrics available to your AI Agents for analysis.

A metric can be a single number like yesterday's conversion rate or a table like total revenue over the last 12 months or last week's top sellers.

Only your imagination and ShopifyQL skills are the limit.

Aug 28, 2024

GPT-4o-mini now avaliable in our free plan

We have just added OpenAI's model gpt-4o-mini to our free plan.

Previously, only gpt-3.5-turbo was available for free users, but with its context window being only 16k tokens, many real-world use cases were not possible to test out simply due to them requiring more data to be analyzed by the model.

A context window is how much data a model can work on at once. The larger the context window, the more data a model can analyze.

Tokens are how generative AI breaks down data - for text data, a token is roughly a short word, e.g., "the", "from", etc. How exactly tokens are computed varies from model to model.

The benefits of gpt-4o-mini

With a context window of 128k, it can analyze just as big data loads as the flagship model gpt-4o, giving you a more accurate experience when testing your AI agents.
Being part of the gpt-4-class of models, it is significantly smarter than gpt-3.5-turbo.
It is a highly efficient model requiring very little compute, allowing you to run even more tests on your free plan.

So while gpt-4o-mini is not as smart as gpt-4o, it gives you a more accurate view of what your AI Agents can do for you while testing.

Try the new model right now.

Aug 26, 2024

HubSpot support conversations

Now you can get your AI Agents connected to all your support conversations in HubSpot with a single click.

This means that you can now get a full 360° view of what your customers are saying in both sales and support.

We have connected some of the most powerful support insights here.

Aug 22, 2024

Quick start with our most popular agents

Building an AI Agent from scratch can be a tall order—especially when we're at the cutting edge of human capabilities. Many of our customers are first movers, if not the very first, to use AI Agents to solve real problems.

But sometimes, it's nice to just get going instead of being first at everything 😅

So, we've created some great templates to start from when creating a new agent, based on what has been most popular among our customers.

One-click AI Agent Templates:

Won deals analysis: Why do customers choose us? Analyze your won deals in your CRM to learn what makes your customers choose you.
Lost deals analysis: Why do customers not choose us? Analyze your lost deals in your CRM to learn from your mistakes.
Why do customers need support?: Why do customers reach out for support, and what should you fix to reduce your support load?
Why do customers request refunds? Refunds directly impact your bottom line. Analyze why your customers request them to minimize your losses.
C-level direct customer feedback: Always be aligned with your customers. Get weekly updates on what customers love about you and what you should change immediately.
Team praise: Go home on a high note with a praise bot that shares your customers' best praise with your team at the end of the day.

You can also (as always) just build your own from scratch.

These are just the first ones to start out with. We will add more as we learn with you.

Aug 21, 2024

Filter Hubspot deals by real activity

Some of your most valuable data is the conversations your sales reps have with customers.

So we have added features to fine tune the data your agents work for.

Filter deals based on activity

Get deals with calls made within the last 1, 2, 3, 5, 7, 14 and 30 days.
Get deals with emails made within the last 1, 2, 3, 5, 7, 14 and 30 days.
Get deals with meetings made within the last 1, 2, 3, 5, 7, 14 and 30 days.
Get deals with notes made within the last 1, 2, 3, 5, 7, 14 and 30 days.
Get deals with tasks made within the last 1, 2, 3, 5, 7, 14 and 30 days.

You can also choose to include all or none of the above and filter out deals with no activity meeting that filter.

This allows you to get good data for analytics of calls, emails and other conversations on a daily, weekly or monthly basis.

Filter deals based on pipelines

You can also filter deals on deal stages across all of your pipelines.

This allows you to eg take all won deals in different pipelines and analyse why customers bought from you.

Aug 19, 2024

Claude 3.5 Sonnet now avaliable

We have added Anthropics Claude 3.5 Sonnet model to UpdateMate.ai

Claude 3.5 Sonnet is a great model for working on code and structured data.

It comes with a 200k context window so it can be a great replacement for OpenAIs GPT-4o or GPT-4-Turbo models (that only have 128k context window) without sacrificing quality.

Aug 18, 2024

Share your updates with the world

We just made any update from UpdateMate.ai shareble with everyone.

Any update can now be shared with a shareable link by just clicking the share button at the top right.

Sometimes a long report can be hard to read in slack or email. It just gets overwhelming.

Now you can choose if a Agent should send everything directly or if the update should be shared with a link and then only a small summary in the email or Slack message.

Aug 13, 2024

Trigger AI Agents with webhooks

One thing is getting AI Agents to keep you updated on a weekly or a daily basis - another thing is getting them to help you in real time.

What is webhooks?

Webhooks is how different web applications talk to each other.

Eg a support system can send be set up to send a message to a webhook in another system each time a user sends a new message in chat.

Webhooks is how different applications send messages to each other.

AI Agntes can both receive and send webhooks

AI Agents in UpdateMate can now both receive and send messages with webhooks.

AI Agents can be triggered to run by selecting their "schedudle" to be webhook. That gives you a unique webhook URL for that agent you can insert into whatever platform you want to.
AI Agents can send their outout to any webhook and you can ask the AI agent for format its resonse as you like being it plain text, JSON, XML etc.

This way agents can act as middleware that allows you to analyse data in real-time as it happens.

Get alerted in real-time

The most common usecase is real-time alert. When X happens alert Y.

This could be an alert when customers are really angry in support that gets triggered and send a ping to a slack channel so everyone can be ready to help them.

Aug 07, 2024