> 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.md).
# AI Agents
Tembi tracks millions of webshops - their checkout setups, delivery providers, product assortments, and how all of that changes over time. It is the most detailed structured databases of e-commerce businesses available.
AI agents are a new layer on top of that data. Rather than leaving your team to navigate signals and draw their own conclusions, agents do the analytical work for you - reading the data, applying your organisation's commercial logic, and returning clear, reasoned assessments that tell you what matters and why.
The result is a faster, more consistent way to turn Tembi's unique data into decisions.
### What an agent does
When you open a webshop in Tembi, the relevant agent runs automatically. It reads the available data for that webshop, applies the criteria and priorities your organisation has defined, and returns a structured assessment - all within the same view.
There is no manual analysis, no switching between tabs, and no need to build your own scoring logic from scratch. The agent handles that, consistently, every time.
Each assessment includes a plain-language summary of the webshop, reasoned findings tied to specific data signals, and transparency about which data points were used - so your team can trust the output and act on it with confidence.
*Example of how the prospect AI agent works and reviews the fit for kappa.com for specific carrier.*
### The agents available today
[**Prospecting Agent** ](/tembi-knowledge-base/product-news/ai-agents/prospecting-agent.md)\
Built for sales and lead generation teams. The Prospecting Agent assesses how well a webshop matches your ideal customer profile and returns a fit score alongside the reasoning behind it. It also surfaces relevant selling angles and can generate outreach drafts directly from the assessment.
[**Account Management Agent**](/tembi-knowledge-base/product-news/ai-agents/account-management-agent.md) \
Built for KAM teams working with existing clients. The Account Management Agent reviews a client's current setup and highlights what has changed, what looks healthy, and where there are opportunities worth acting on - giving account managers a structured view before every client conversation.
More agents will be added, covering additional parts of the commercial workflow.
{% @arcade/embed flowId="kaV8ukpwcTCVW1Bad154" url="" %}
### How agents are configured
Agents are not one-size-fits-all. Out of the box, they understand Tembi's data - but how they reason about that data depends on what your organisation tells them.
That configuration happens in [**Agent Studio**](/tembi-knowledge-base/product-news/ai-agents/agent-studio-set-up-your-agent.md), where admins define your commercial priorities by answering a set of guided questions. What does your ideal customer look like? Which signals matter most for your account management goals? Where do you tend to win?
Once configured, every user on your team benefits from the same logic - automatically, every time they open a webshop.
→ Learn more about how to set up and manage agents in [**Agent Studio**](/tembi-knowledge-base/product-news/ai-agents/agent-studio-set-up-your-agent.md)
---
# 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.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.