What is ShapBot?
ShapBot is a web crawler by Parallel that collects and structures web content to power its search, extraction, and deep research APIs, providing AI agents with high-accuracy web context and data. You can set up Agent Analytics to see when ShapBot visits your website.
Category
| Example User Agent | Mozilla/5.0 AppleWebKit/537.36 (KHTML, like Gecko); compatible; ShapBot/0.1.0 |
| Operated By | Parallel |
| Source | Official Website |
| Identity |
Verified
Verified Identification
Requests claiming to be this agent can be authenticated using its published verification method. |
| Triggered By | Customer request or automated indexing |
| Used for AI Model Training | Possibly |
| Affects AI Chat & Search Visibility | Possibly |
| Expected To Follow Robots.txt | Yes |
Why Is ShapBot Visiting My Website?
One of Parallel's customers may have requested data from your site, or your pages may be part of ShapBot's standing index. A single fetch can support multiple downstream applications.
Should I Block ShapBot?
It depends on which uses you want to support. ShapBot may supply your content to enterprises, including AI companies, or use it in consumer-facing products. Those uses can include AI training, search, and retrieval. Allowing it may expand your visibility across those products and services, while blocking it limits that reach without affecting traditional search rankings. For context, 11% of the top websites we track currently have robots.txt rules for ShapBot.
How Do I Block ShapBot Using Robots.txt?
Add this rule to your robots.txt file to block ShapBot from accessing your website, or use Automatic Robots.txt to block all AI data providers at once. You can customize which pages are blocked by swapping out / for a different path.
User-agent: ShapBot # https://knownagents.com/agents/shapbot
Disallow: /Insights for ShapBot
As of October 30, 2026, this data reflects agent visits measured across thousands of websites using Agent Analytics, combined with daily scans of the top 1000 websites and their robots.txt files.
Robots.txt Compliance
Country of Origin
Robots.txt Blocked Percentage
Frequently Asked Questions
What Traffic Patterns Should I Expect From ShapBot?
ShapBot supports several kinds of automated activity, so its traffic pattern depends on the task. It may perform broad crawls to collect content or build an index, make targeted requests for specific pages, or shift between these behaviors as demand changes.
Does ShapBot Follow Robots.txt Rules?
ShapBot is expected to follow robots.txt rules, so a disallow rule is the appropriate first step if you want to block it. Automatic Robots.txt can add and maintain that rule, while Agent Analytics lets you verify whether ShapBot respects it.
Is ShapBot Used for AI Model Training?
Possibly. ShapBot supplies data to other organizations, and its customers may use that data for AI training, search, retrieval, or other purposes.
Does Blocking ShapBot Affect AI Search or Citations?
Possibly. Blocking ShapBot can reduce your visibility in downstream AI products that depend on its data, including search or retrieval products operated by its customers.
Does ShapBot Access Private Content?
No special access. ShapBot can reach public pages, and some providers use proxy networks that can bypass rate limits or geographic restrictions. Protect sensitive content with authentication rather than relying on those softer barriers.
How Can I Verify a Request From ShapBot?
Agent Analytics tracks visits from ShapBot and every other known AI agent, crawler, and scraper, then authenticates each visit using ShapBot's published verification method. You can also check your server logs for requests whose user-agent string contains "ShapBot". Traffic may range from long crawl sequences across your site to isolated requests for specific pages, depending on whether it is collecting, indexing, or fetching content on demand. A matching log entry alone is not proof because any bot can claim to be ShapBot.
How Is ShapBot Different From Other Parallel Agents?
Parallel operates separate agents for different purposes, so each agent should be evaluated and controlled independently.
- Shap-User: Shap-User accesses web content on behalf of users of Parallel Web Systems products. It identifies user-initiated requests rather than automatic web crawling.