> For the complete documentation index, see [llms.txt](https://help.paxton.ai/help/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://help.paxton.ai/help/paxton-ai/research-in-the-ai-assistant.md).
# Research in the AI Assistant
Important: To see the full legal research library included with your subscription, visit our coverage page: https\://www\.paxton.ai/coverage
### Research Built Into Every Conversation
Legal research isn't a separate mode you switch on — it's part of every conversation you have with Paxton. Ask an issue-based question and Paxton surfaces relevant case law, statutes, and governing standards from your matter's jurisdiction, with citations you can verify and pull straight into a draft. Research, analysis, and drafting happen in one thread, against the same set of matter files.
***
#### Getting Started
1. **Open your matter**\
Research is scoped to the matter you're working in, so it draws on the same files and jurisdiction as the rest of your work. See [Conversations with Paxton](https://help.paxton.ai/help/ai-assistant/using-the-ai-assistant) for the basics of starting a chat.
2. **Check the jurisdiction**\
The jurisdiction appears under the matter name (for example, **Texas**). Every authority Paxton returns is drawn from it. To research a different jurisdiction for one question, just say so in your prompt — *"How would this come out under New York law?"*
3. **Ask your question**\
Type any issue, rule, or fact pattern in plain language. No search syntax, no boolean operators, no citation format required.
4. **Follow up**\
Narrow, expand, or apply the results in the same thread. Paxton keeps the research and your matter's facts in context across the whole conversation.
***
#### What a Research Answer Includes
Every research response comes back with:
* **Relevant cases** from your matter's jurisdiction
* **Statutes and legal principles** that govern the issue
* **A concise rule statement** you can quote or adapt
* **An explanation tied to your jurisdiction** — not a generic summary
* **Citations and source links** for verification
***
#### What You Can Do with Research
**📚 Retrieve Case Law and Governing Rules**
Ask for the legal standard, the controlling precedent, or the elements of a claim.\
**Example**:\
*"What is the California rule for establishing liability in a rear-end collision?"*
**⚖️ Summarize Cases and Statutes**
Get concise summaries of holdings, rules, and reasoning.\
**Example**:\
*"Summarize the key cases involving aggravation of pre-existing injuries."*
**📝 Insert Authorities Into Drafts**
Because research and drafting share a thread, you can go from authority to document without re-explaining anything.\
**Example**:\
*"Draft a demand letter and include supporting California cases."*
**📄 Apply Authority to Your Matter Files**
Paxton can test the rule it just found against the record already in the matter.\
**Example**:\
*"Apply that standard to the facts in the deposition transcript and tell me where we're exposed."*
**🔍 Narrow or Expand Research**
Refine with follow-up instructions rather than starting a new search.\
**Examples**:\
*"Narrow this to premises liability cases."*\
*"Show additional authority from the last 10 years."*
**📑 Verify Sources**
Select **Sources** below any response to see the full list of cases and statutes referenced, direct citations, and links to each source. Run authority through the [AI Citator](https://help.paxton.ai/help/legal-research/citations-and-ai-citator) to confirm it's still good law before you rely on it.
***
#### From Research to Work Product
Anything the research produces stays in the matter. Ask Paxton to turn a thread into a memo, a letter, or a summary, and the draft lands in **Recent Drafts** on the Matter Overview, ready to open in [Canvas](https://help.paxton.ai/help/ai-assistant/editing-drafts-with-canvas). The chat itself stays in **Chat History**, so the research trail behind a document is always recoverable.
***
#### Tips for Better Results
* **Ask in plain language.** You don't need perfect phrasing.\
*"What's the duty of care for a landowner in Texas?"*\
*"Cases about unsafe conditions inside retail stores."*
* **Let the matter carry the jurisdiction.** Set it once on the matter instead of restating it in every prompt — and name a different one only when you deliberately want to look outside it.
* **Use follow-up questions.** Keep refining until you have the exact angle, timeframe, or case type you need.
* **Ask Paxton to apply the rule to your facts.**\
*"Apply the rule to a rear-end collision with a sudden stop scenario."*
* **Bring your files into the question.** Research answers get sharper when Paxton can read the record — reference a document by name and ask how the authority applies to it.
***
#### Best Practices
* **Review every citation before relying on it.** Verify authority through **Sources** and the AI Citator.
* **Keep research and drafting in the same thread.** Context continuity is what lets Paxton carry a rule into a document accurately.
* **Use Paxton to explore theories, not just find cases.** Validate an argument, find the counter-authority, or stress-test a position.
* **Turn research into work product.** Ask for a memo, letter, or summary rather than copying results by hand.
---
# 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://help.paxton.ai/help/paxton-ai/research-in-the-ai-assistant.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.
