> ## Documentation Index > Fetch the complete documentation index at: https://docs.parallel.ai/llms.txt > Use this file to discover all available pages before exploring further. # Glossary > Key terms and concepts used throughout Parallel's documentation
For AI agents: a documentation index is available at [https://docs.parallel.ai/llms.txt](https://docs.parallel.ai/llms.txt). The full text of all docs is at [https://docs.parallel.ai/llms-full.txt](https://docs.parallel.ai/llms-full.txt). You may also fetch any page as Markdown by appending `.md` to its URL or sending `Accept: text/markdown`.
| Term | Definition | | ---------------------------- | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | | API key | A unique identifier used to authenticate requests to Parallel APIs. Generate your API key at [platform.parallel.ai](https://platform.parallel.ai). | | Asynchronous API | An API that returns a run ID immediately and processes the request in the background. Task, FindAll, and Monitor APIs are asynchronous. Poll for status or use webhooks to receive results. | | Cadence | The frequency at which a monitor executes: `hourly`, `daily`, or `weekly`. | | Candidate | A potential entity discovered during a FindAll run. Candidates are generated from web data and evaluated against match conditions. | | Chat API | A synchronous API that provides OpenAI-compatible streaming chat completions with web-grounded responses. Supports both speed-optimized and research-grade models. | | Citation | A reference to a web source that contributed to an output field. Includes the URL and relevant excerpts from the source. | | Confidence level | A reliability rating for each output field: **high** (strong evidence from multiple authoritative sources), **medium** (adequate evidence with some inconsistencies), or **low** (limited or conflicting evidence). | | Enrichment | Additional structured data extracted for matched candidates using the Task API. Enrichments run automatically on candidates that pass all match conditions. | | Event | A detected change or update that matches a monitor's query. Events include the detected information, event date, and source URLs. | | Event group | A collection of related events detected during a single monitor execution. | | Excerpt | A focused portion of page content that's relevant to your objective. Optimized for LLM consumption. | | Extract API | A synchronous API that converts any public URL into clean, LLM-optimized markdown. Handles JavaScript-heavy pages and PDFs. | | Fast processor | A processor variant optimized for speed over data freshness. Append `-fast` to any processor name (e.g., `core-fast`) for 2-5x faster response times. | | FieldBasis | The specific object containing citations, reasoning, and confidence for an individual output field within the research basis. | | FindAll API | An asynchronous API for web-scale entity discovery. Turns natural language queries into structured, enriched databases by generating candidates, validating them against criteria, and optionally enriching matches. | | FindAll run | A single execution of a FindAll query. Includes candidate generation, evaluation, and optional enrichment. | | Generator | The engine that determines the quality and thoroughness of FindAll run results. Options include `preview`, `base`, `core`, and `pro`. | | Match condition | A criterion that candidates must satisfy to be included in FindAll results. Defined in natural language as part of the query. | | Match status | The state of a candidate after evaluation: `matched` (satisfies all conditions), `unmatched` (fails one or more conditions), or `generated` (not yet evaluated). | | MCP (Model Context Protocol) | A protocol for connecting AI models to external tools and data sources. Parallel provides MCP servers for Search and Task APIs. | | Monitor | A scheduled query that continuously tracks the web for changes relevant to a specific topic. | | Monitor API | An asynchronous API for continuous web tracking. Creates scheduled queries that detect relevant changes and deliver updates via webhooks. | | Objective | A natural language description of what you're looking for. Used by Search and Extract APIs to focus results on relevant content. | | Processor | The engine that executes Task Runs. Processors vary in performance characteristics, latency, and reasoning depth. Options include `lite`, `base`, `core`, `core2x`, `pro`, `ultra`, `ultra2x`, `ultra4x`, and `ultra8x`. Each is available in standard and fast variants. | | Rate limit | The maximum number of API requests allowed within a time period. See [Rate limits](/getting-started/rate-limits) for default quotas. | | Research Basis | The structured explanation detailing the reasoning and evidence behind each Task Run result. Includes citations, reasoning, and confidence levels. | | SDK | Software Development Kit. Parallel provides official SDKs for [Python](https://pypi.org/project/parallel-web/) and [TypeScript](https://www.npmjs.com/package/parallel-web). | | Search API | A synchronous API that executes natural language web searches and returns LLM-optimized excerpts. Replaces multiple keyword searches with a single call for broad or complex queries. | | Search query | A specific search term or phrase used to find relevant pages. Multiple search queries can be combined in a single Search API request. | | Source policy | Configuration that controls which web sources can be accessed during research. Can include or exclude specific domains. | | Synchronous API | An API that returns results immediately in the response. Search, Extract, and Chat APIs are synchronous. | | Task API | An asynchronous API that combines AI inference with web search and live crawling to turn complex research tasks into repeatable workflows. Returns structured outputs with citations and confidence levels. | | Task Group | A collection of Task Runs that can be executed and tracked together. Useful for batch processing multiple inputs. | | Task Run | A single execution of a task specification. Each Task Run processes one input and produces one output with its associated research basis. | | Task spec | The definition of what a Task Run should accomplish. Includes input schema, output schema, and optional instructions. | | Webhook | An HTTP callback that delivers notifications when specific events occur (e.g., task completion, monitor event detection). |