# Search for Agents > An encyclopedia on search for agents Canonical site: https://www.searchforagents.com Content API: https://www.searchforagents.com/api/v1/content OpenAPI: https://www.searchforagents.com/openapi.json Full export: https://www.searchforagents.com/llms-full.txt Change feed: https://www.searchforagents.com/api/v1/changes ## When to use this site - Explain source discovery, parsing, retrieval, reranking, and evidence checks using the [encyclopedia](https://www.searchforagents.com/encyclopedia). - Find documented search providers and source collections in [Lay of the Land](https://www.searchforagents.com/market-map); verify current capabilities against each provider's cited source. This directory is not a performance ranking. - Retrieve worked examples of source verification from [field notes](https://www.searchforagents.com/blog) and cite the original source documents, not just summaries. - Read the [developer and agent quickstart](https://www.searchforagents.com/developers) before calling the public API. Anonymous reads need no API key; editorial changes require scoped access. ## Public API - Search: https://www.searchforagents.com/api/v1/search?q=web%20search - Topics: https://www.searchforagents.com/api/v1/topics - Authors: https://www.searchforagents.com/api/v1/authors - Research: https://www.searchforagents.com/api/v1/research - Datasets: https://www.searchforagents.com/api/v1/datasets ## Encyclopedia - [Sources & coverage](https://www.searchforagents.com/encyclopedia/sources): Source selection decides where an agent looks: the public web, a specialist collection, or an internal corpus. Coverage includes which records are searchable, how much content is accessible, and how recently it was updated. Finding a document in an index does not necessarily mean receiving its full text. - [Parsing & extraction](https://www.searchforagents.com/encyclopedia/parsing): Parsing converts a page or file into usable text and structure. It may recover headings, tables, reading order, and text from scanned images. The aim is to preserve meaning and source locations so downstream search can find a passage and the answer can point back to it. - [Chunking](https://www.searchforagents.com/encyclopedia/chunking): Chunking divides extracted content into units that can be indexed and retrieved. Small chunks can isolate a precise fact but lose surrounding context; large chunks retain context but may mix unrelated material. Boundaries, overlap, and document structure influence which evidence reaches the agent. - [Embeddings](https://www.searchforagents.com/encyclopedia/embeddings): An embedding model represents an input as a vector of numbers. A retrieval system compares query and document vectors to find useful semantic matches, including passages without the exact query words. The representation depends on the model and its training; similarity does not establish that a passage is correct. - [Keyword, vector & hybrid search](https://www.searchforagents.com/encyclopedia/retrieval): Retrieval selects candidates from an index. Keyword search uses lexical matches; vector search uses similarity between representations. Hybrid search combines their results, often by fusing ranked lists. Filters constrain eligible records, while the candidate limit controls how much material later stages can inspect. - [Reranking](https://www.searchforagents.com/encyclopedia/reranking): A reranker reorders an existing candidate set for a query. Cross-encoder rerankers examine query and document together, allowing closer relevance judgments than independently encoded vectors alone. Reranking can improve the material selected for context, but it cannot add missing evidence or verify the truth of a source. - [Evidence & citations](https://www.searchforagents.com/encyclopedia/evidence): Evidence connects an answer's claims to supporting passages. A citation provides a route to the source; it does not by itself prove support. Verification checks whether the passage entails the claim, whether qualifications were preserved, and whether the source is appropriate and current enough for the question. - [Evaluation](https://www.searchforagents.com/encyclopedia/evaluation): Evaluation tests retrieval and answers against representative questions and explicit criteria. Retrieval checks whether relevant evidence was found and ranked usefully. Answer evaluation checks support and task completion. Track latency and cost alongside quality, then trace failures to the layer that caused them. ## Topics - [Web Search](https://www.searchforagents.com/topics/web-search/llms.txt): topic-specific machine index (1 field notes) - [Industry Search](https://www.searchforagents.com/topics/industry-search/llms.txt): topic-specific machine index (4 field notes) - [Finance](https://www.searchforagents.com/topics/industry-search/finance/llms.txt): topic-specific machine index (1 field notes) - [Life Sciences](https://www.searchforagents.com/topics/industry-search/life-sciences/llms.txt): topic-specific machine index (1 field notes) - [Paper Search](https://www.searchforagents.com/topics/industry-search/paper-search/llms.txt): topic-specific machine index (1 field notes) - [Search Infrastructure](https://www.searchforagents.com/topics/search-infrastructure/llms.txt): topic-specific machine index (1 field notes) ## Tags - [Clinical Trials](https://www.searchforagents.com/tags/clinical-trials.md): Registered studies, eligibility, treatment arms, recruitment status, and original trial records. - [Context](https://www.searchforagents.com/tags/context.md): Selecting and structuring the information an agent needs for its next decision. - [Earnings Call](https://www.searchforagents.com/tags/earnings-call.md): Earnings-call transcripts, management commentary, and source-backed pre-earnings research. - [Evals](https://www.searchforagents.com/tags/evals.md): Controlled tests that measure agent behavior, outcomes, and operational quality. - [Finance](https://www.searchforagents.com/tags/finance.md): Financial filings, market records, and dated evidence for research agents working with company data. - [Harnesses](https://www.searchforagents.com/tags/harnesses.md): The runtime infrastructure that controls an agent around its underlying model. - [Health](https://www.searchforagents.com/tags/health.md): Biomedical evidence, regulatory records, and source checks for health-related search claims. - [Infrastructure](https://www.searchforagents.com/tags/infrastructure.md): Search APIs, retrieval systems, and operational foundations for dependable agent workflows. - [Integrations](https://www.searchforagents.com/tags/integrations.md): Dependable connections between agent runtimes and external products or services. - [Law](https://www.searchforagents.com/tags/law.md): Court opinions, legal records, jurisdiction, and dated evidence for legal search questions. - [MCP](https://www.searchforagents.com/tags/mcp.md): Model Context Protocol concepts and implementation guidance for tool builders. - [Orchestration](https://www.searchforagents.com/tags/orchestration.md): Coordinating model turns, tools, state, retries, and completion conditions. - [Paper Search](https://www.searchforagents.com/tags/paper-search.md): Scholarly discovery, paper versions, citation trails, and claim-level checks against original research. - [Protocols](https://www.searchforagents.com/tags/protocols.md): Shared interfaces and contracts for interoperable agent systems and tools. - [RAG](https://www.searchforagents.com/tags/rag.md): Retrieval-augmented generation patterns for grounding model output in evidence. - [Reliability](https://www.searchforagents.com/tags/reliability.md): System properties that keep agent behavior predictable, recoverable, and verifiable. - [Search](https://www.searchforagents.com/tags/search.md): Query, ranking, and discovery systems that supply agents with relevant evidence. - [Tools](https://www.searchforagents.com/tags/tools.md): Structured capabilities that let agents inspect, compute, and change external state. - [Verification](https://www.searchforagents.com/tags/verification.md): Independent checks that establish whether an agent action produced the intended result. ## Contributors - [Ada Vale](https://www.searchforagents.com/authors/ada-vale.md): Technical writer - [Search for Agents Editorial Desk](https://www.searchforagents.com/authors/editorial-desk.md): Editorial team - [Eliot Reed](https://www.searchforagents.com/authors/eliot-reed.md): Research writer - [Mara Finch](https://www.searchforagents.com/authors/mara-finch.md): Industry writer ## Field notes - [Does the cited paper actually support the claim?](https://www.searchforagents.com/blog/does-the-cited-paper-actually-support-the-claim.md): A citation can lead to the right paper and still misstate its finding. Three source-level checks show how to test a claim against the paper's methods, results, and limits. - [How to use an agent to find clinical trials for a research question](https://www.searchforagents.com/blog/how-to-use-an-agent-to-find-clinical-trials.md): A worked clinical-trial search: discover candidate studies, narrow by design and recruitment status, and inspect the original registry records. - [How to use an agent to research a company before earnings](https://www.searchforagents.com/blog/how-to-use-an-agent-to-research-a-company-before-earnings.md): Build a useful pre-earnings brief with search and filings libraries: find the latest reports, revisit the prior call, and decide what to watch next. - [What should a search API return to an agent?](https://www.searchforagents.com/blog/what-should-a-search-api-return-to-an-agent.md): Valyu, Exa, and Parallel return different combinations of links, passages, dates, and diagnostics. Here is the evidence contract an agent needs to build around their results. - [How to Verify Search Results Across Finance, Biomedical, and Law](https://www.searchforagents.com/blog/how-to-verify-search-results-across-finance-biomedical-and-law.md): A number in a filing, a disease in a paper title, and a court ruling each require a different source check. Three worked cases show where search ends and evidence begins. - [When can an agent trust a web search result?](https://www.searchforagents.com/blog/when-can-an-agent-trust-a-web-search-result.md): A 2026 UK holiday calendar says Scotland has nine bank holidays; official records list ten. Follow a search result to its source and learn a five-check method for verifiable answers. ## Research - [Evidence-first evaluation for tool-using AI agents](https://www.searchforagents.com/research/evidence-first-agent-evaluation.md): A compact research brief connecting state-based agent evaluation to reproducible fixtures, permission checks, and independently inspectable outcomes. ## Datasets - [Agent evaluation state and permission fixture](https://www.searchforagents.com/datasets/agent-evaluation-fixture.md): A small versioned JSON fixture for testing whether tool-using agents produce inspectable state while respecting publication and credential boundaries. ## Approved translations ## Editorial standards - [Editorial policy](https://www.searchforagents.com/editorial-policy.md) - [Research methodology](https://www.searchforagents.com/methodology.md) - [Corrections](https://www.searchforagents.com/corrections.md)