> For the complete documentation index, see [llms.txt](https://tembi.gitbook.io/tembi-knowledge-base/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://tembi.gitbook.io/tembi-knowledge-base/product-news/ai-agents/account-management-agent.md).
# Account Management Agent
The Account Management Agent helps KAM teams review existing clients more efficiently. When you open a client in Tembi, the agent analyses their current setup and surfaces what matters most: what has changed, what looks healthy, and where there are opportunities worth acting on.
Rather than spending time navigating multiple data views to build a picture of an account, you get a structured summary the moment you open them — grounded in the priorities your organisation has defined.
### What you see when you open a client
When you open a webshop in Tembi, and activate the Account Management Agent, it runs and returns an assessment in the AI summary view. Here's what's included:
**Plain-language account summary** \
A concise overview of the client's current setup, covering the signals most relevant to account management: their checkout configuration, which delivery providers are present, how visible your services are at checkout, and any notable changes to how they're operating. The summary is designed to give you the context you need before a client conversation, without having to piece it together yourself.
**Structured assessment** \
The agent highlights the key findings from its review - what's working well, what has changed recently, and where there may be gaps or opportunities. Each point is tied to a specific data signal, so you understand what's driving the observation and can bring it into your client conversation with confidence.
For example, the agent might flag that a client has added a new delivery provider since your last review, that your service has dropped in checkout visibility, or that they've expanded into a new market - all of which are signals that warrant follow-up.
**Data source transparency** \
The assessment shows which data points were used in the analysis and flags any that weren't available. This helps you understand the confidence level of the output and know where you might want to verify or dig deeper before meeting with the client.
***
### How the agent is configured
The Account Management Agent is set up by your organisation's Tembi admin through a guided configuration flow in Agent Studio. It works by answering a series of questions that help the agent understand your KAM priorities - no technical knowledge required.
These questions cover things like:
* What account health looks like for your business
* Which signals matter most - checkout visibility, delivery presence, service position, changes over time
* What your team is trying to protect, grow, or optimise within existing relationships
* How you want the agent to reason about follow-up and upsell opportunities
The answers shape how the agent interprets what it finds. Two clients with a similar setup might get different assessments depending on how your organisation has defined what's important - and that's intentional. The agent should reflect your priorities, not a generic framework.
If your account management approach evolves, your admin can update the configuration and all future assessments will reflect the new direction.
***
### *A practical example*
You're preparing for a quarterly review with an existing client. You open them in Tembi and the Account Management Agent runs its assessment.
It surfaces that the client recently added one new delivery providers to their checkout. Your brand is still present, but has moved from first position to third. It also notes that they've expanded their product catalogue significantly over the past quarter, suggesting growth that could be relevant to your conversation.
From that, you generate a meeting prep outline. It frames the checkout visibility change as something worth addressing directly, suggests some talking points around the catalogue expansion, and gives you a clear structure for the conversation. You go into the meeting knowing what's changed, why it matters, and what you want to walk away with.
***
### Getting started
The Account Management Agent is available to all Tembi users once a template has been configured by your admin.
* **Admins**: Go to Agent Studio and select **+ New Template** under Account Management Agent to begin. You'll be guided through a set of questions about your KAM priorities and what account health looks like for your business.
* **End users**: Open any client webshop in Tembi and look for the AI summary view. If it shows "Not configured," reach out to your admin to get the agent set up for your team.
---
# Agent Instructions
This documentation is published with GitBook. GitBook is the documentation platform designed so that both humans and AI agents can read, navigate, and reason over technical content effectively. Learn more at gitbook.com.
## Querying This Documentation
If you need additional information that is not directly available in this page, you can query the documentation dynamically by asking a question.
Perform an HTTP GET request on the current page URL with the `ask` query parameter:
```
GET https://tembi.gitbook.io/tembi-knowledge-base/product-news/ai-agents/account-management-agent.md?ask=
```
The question should be specific, self-contained, and written in natural language.
The response will contain a direct answer to the question and relevant excerpts and sources from the documentation.
Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.