---
schema_version: "newruntime-reader-dossiers-v1"
type: "reader_dossier"
slug: "shapbot"
kind: "ai_answer"
operator: "Parallel Web Systems"
researched_at: "2026-10-23"
confidence: "high"
json_url: "https://newruntime.com/readers/shapbot.json"
canonical_url: "https://newruntime.com/readers/shapbot/"
---

# ShapBot

> Parallel Web Systems' crawler; it collects publicly available web content to build and maintain Parallel's search index (Parallel sells web search/research APIs for AI agents). A separate Shap-User agent handles user-triggered fetches and does not crawl automatically.

## Dossier

- Kind: AI search & answer engines
- Operator: Parallel Web Systems (https://parallel.ai/)
- Documentation: https://parallel.ai/parallel-web-systems-bots
- robots.txt tokens: ShapBot
- Feeds: search index
- Respects robots.txt: Partly, per its documentation. Docs name robots.txt (User-agent: ShapBot) as the way to manage its access but do not explicitly state compliance.
- Verification: Published IP ranges (https://docs.parallel.ai/resources/shapbot.json)
- Labels matched in our logs: shapbot

## Why it matters to New Runtime (our interpretation)

Parallel's index feeds agent search/research APIs, so being crawled makes our stories retrievable by third-party agents built on Parallel.

## Observed behaviour

- Baseline 2026-10-23 (93-day window): 602 requests on 3 days; first seen 2026-09-30, last seen 2026-10-22; Returning.
- Live numbers: https://newruntime.com/bot-traffic-history.json and https://newruntime.com/crawler-journeys.json

## Sources

- https://parallel.ai/parallel-web-systems-bots

Identity: A family name is what a client claims in its user agent. It is verified only when its request came from the operator's published IP ranges or passed forward-confirmed reverse DNS, as reported per family in /crawler-journeys.json. Anyone can claim any name.

All dossiers: https://newruntime.com/readers.md