Getting Started with Chimera Chat¶
Chimera Chat is a conversational AI built into the Content Chimera web interface. It is a full agentic assistant that can do almost everything the Web UI and MCP interfaces can do — ask questions, create charts, run crawls, build reports, manage rules, and more — all through natural language conversation.
What You Need Before You Start¶
Chimera Chat works with data that has already been crawled and processed. Depending on the type of question you want to ask, different processing steps need to be complete:
Question type |
What needs to be ready |
Processing step |
|---|---|---|
Structured queries (counts, distributions, field values) |
The flattened table must exist |
Optimize step complete |
Semantic search (finding content by meaning) |
The vector database must be loaded |
Load Semantic DB step complete |
Graph queries (broken links, link depth, orphan pages) |
The graph database must be loaded |
Load Graph DB step complete |
If you ran a standard crawl pipeline, the Optimize step runs automatically. The semantic and graph databases may need to be loaded separately — you can load them from the My History page in the web UI, or by asking Chimera Chat itself (for example, “Load the semantic database”).
Tip
Not sure what is ready for your site? Ask Chimera Chat: “What data is available?” and it will tell you which query types are supported.
What Chimera Chat Can Do¶
Chimera Chat has access to the same set of tools as the MCP interface. Behind the scenes, it is an agentic AI loop that automatically selects the right tool for your request.
Ask Questions About Your Data¶
Structured queries — Ask about counts, distributions, averages, and field values from your crawl data. Chimera Chat translates your question into a query against the flattened table.
“How many pages did we crawl?”
“What are the top 10 folders by page count?”
“What percentage of pages have a meta description?”
“Which pages have a title longer than 70 characters?”
Semantic search — Search the actual content of your pages by meaning. Chimera Chat automatically chooses between RAG (specific facts from relevant pages) and Summarization (broad themes across many pages).
“What does the site say about return policies?”
“What topics does the blog cover?”
“Find pages that mention pricing”
Graph queries — Analyze the link structure using the graph database.
“Are there any broken links?”
“Which pages have no inbound links?”
“Show me redirect chains longer than 3 hops”
Note
Semantic search results are drawn from a sample of pages, not the entire site. They are excellent for exploration and hypothesis generation, but do not treat them as exhaustive. If you need precise counts, use a structured query instead.
Create Charts¶
Ask for a chart in natural language and Chimera Chat will create an interactive visualization.
“Show me a treemap of content by folder”
“Create a bar chart of status codes”
“Make a pie chart of content types”
Charts are returned as interactive links you can click to explore in the web UI.
Run Crawls and Pipelines¶
You can start crawls and processing pipelines directly from Chimera Chat.
“Crawl example.com”
“Run a Sprawl Report for this site”
“Load the graph database”
“Run the extraction patterns”
“Run the text analysis pipeline”
For operations that use significant resources (such as bulk LLM summarization or Sprawl Reports), Chimera Chat will ask for your confirmation before proceeding.
Build Reports¶
Create and assemble reports without leaving the conversation.
“Create a report called Q1 Content Audit”
“Add the treemap chart to the report”
“Add a text section summarizing the broken link findings”
Manage Rules and Decisions¶
Set up content classification rules, dispositions, and assignments.
“List the current rules”
“Add a rule that tags pages in /blog as Blog Posts”
“Run the assignment pipeline”
“What dispositions are available?”
View Page Details¶
Get comprehensive information about specific pages, including metadata, screenshots, LLM summaries, and technology detection.
“Show me details for example.com/about”
“What technologies does this site use?”
Work with AI Analysis¶
Manage LLM fieldsets, test prompts against pages, and run bulk summarization.
“What LLM fieldsets are configured?”
“Test the E-E-A-T fieldset against example.com/about”
“Run bulk summarization”
Add Annotations¶
Create and manage observations about specific pages.
“Add an annotation for example.com/pricing: pricing page needs review”
“List all annotations”
When to Use Chimera Chat vs. Other Interfaces¶
Chimera Chat can now do most of what the Web UI and MCP can do. Here is when each interface works best:
Use Chimera Chat when you want to…
Get quick answers without navigating menus
Explore data conversationally, with follow-up questions
Run a mix of tasks in one session (query, chart, report)
Work entirely within the browser
Use the Web UI when you want to…
Do manual page-by-page review with assignments
Configure crawl settings in detail
Import data from CSV or analytics sources
Manage projects, users, and permissions
See live progress bars on long-running pipelines
Use MCP when you want to…
Work in your own AI tool (Claude, ChatGPT, etc.)
Combine Chimera data with other tools and data sources
Automate multi-step workflows
Use a more powerful language model
Example Conversation¶
Below is a typical Chimera Chat session showing how questions build on each other.
You: How many pages did we crawl?
Chimera Chat returns a single number — for example, 4,218 pages.
You: Show me a treemap of content by folder
Chimera Chat creates an interactive treemap chart. You can see at a glance that
/blogdominates the site while/productsis comparatively small.
You: Are there any broken links?
Chimera Chat queries the graph database and reports the number of URLs returning 404 errors, along with the pages that link to them.
You: What topics does the blog cover?
Chimera Chat uses semantic search to summarize the main themes across a sample of blog posts.
You: Create a report called Site Audit and add the treemap to it
Chimera Chat creates a new report and adds the treemap chart as a component.
You: Add a text section summarizing the broken link findings
Chimera Chat adds a text block to the report with the broken link summary.
Each question takes seconds. The same work in the Web UI would involve navigating to different pages, configuring options, and switching between tools — Chimera Chat lets you stay in a single conversation flow.
Tips for Better Results¶
Be specific with structured queries. “How many pages have a word count above 500?” works better than “Tell me about word count.”
Name the chart type if you have a preference. “Show me a bar chart of status codes” is more predictable than “Show me status codes.”
Ask follow-up questions. Chimera Chat maintains context within a conversation, so you can refine results step by step.
Confirm before expensive operations. Chimera Chat will ask for confirmation before running operations that consume LLM credits or significant resources.