> For the complete documentation index, see [llms.txt](https://docs.planetcrust.com/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.planetcrust.com/human-agents/integration-with-taq-automations.md).
# Integration with TAQ Automations
### Introduction
[TAQ (Trigger/Action/Query) Automations](/human-automations/human-automations.md) are designed to integrate directly and safely with @Human Agentic. They also act as a fulcrum between @Human Agentic and [@Human Connections](/human-connections/readme.md).
Integration between Agentic and TAQ Automations is two-way:
* An Agent may invoke one or more TAQ Automations ("TAQ")
* A TAQ may invoke one or more @Human Agents
### Agentic Invocation of TAQ
Any Agent can be permitted to invoke a TAQ by clicking on the "Allowed TAQs" dropdown menu in the Agent configuration panel.
The permitted TAQ will then be added to the MCP (Model Context Protocol) Policy for the Agent in question.
On the TAQ side of the equation, the Trigger type should be set to "Agent Invoked" and the nature of the Agentic output to be received (usually a text string) should be defined in the parameters of the TAQ Trigger.
### TAQ Invocation of Agents
An independently triggered TAQ Automation can invoke one or more Agents.
The Agent can also hand output back to the TAQ and the conversation can be continued.
### Different Agents - Different Models?
You may find it useful to select different LLM models depending on the Agent's purpose. For more programmatic or simple actions, a cheaper LLM model will usually suffice.
However, for more nuanced communication (e.g. replying to customer enquiry), it makes sense to use more advanced models. In the diagram above, different Agents could employ different LLM models without impacting the design of the TAQ.
---
# 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, and the optional `goal` query parameter:
```
GET https://docs.planetcrust.com/human-agents/integration-with-taq-automations.md?ask=&goal=
```
`ask` is the immediate question: it should be specific, self-contained, and written in natural language.
`goal` is optional and describes the broader end goal you are ultimately trying to accomplish on behalf of the user. GitBook uses it to tailor the answer towards what is most useful for that goal.
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.