Skip to main content

Specialized Search Providers

Connect agents to external web and research search services including Perplexity, Tavily, Exa, Brave, You.com, Harvey, and custom providers.

Overview

Specialized Search Providers give agents access to live web search and AI-synthesized research beyond the knowledge base. Unlike Azure AI Search (which queries your internal documents), specialized search providers call external APIs to retrieve up-to-date information from the web.

Once configured, a provider appears as a tool agents can call during task execution - for example, searching for current news, looking up competitor pricing, or synthesizing research from multiple sources.

Supported Providers

ProviderTypeBest For
PerplexityAI-synthesized answersResearch questions needing cited summaries
TavilyWeb searchFactual lookups with source links
ExaNeural searchSemantic similarity-based web retrieval
BraveWeb/news searchPrivacy-focused web search
You.com ResearchAI researchCited answers across 5 effort tiers
You.com SearchWeb/news searchRaw results with optional live page crawl
HarveyLegal researchSpecialized legal document retrieval
CustomHTTP endpointAny search API behind a custom endpoint

Adding a Specialized Search Provider

The setup wizard walks you through selecting a provider, entering credentials, and creating the search tool in one flow.

  1. Navigate to Configuration > Tools & Integrations > Specialized Search
  2. Click Add Provider to open the setup wizard
  3. Select your provider from the card grid
  4. Enter your API key and provider-specific settings
  5. Click Test Connection to verify credentials
  6. Click Save - the search tool is created automatically

Via the Form Page

For full access to all configuration options, use the form page directly:

  1. Navigate to Configuration > Tools & Integrations > Specialized Search
  2. Click New Provider (form view)
  3. Fill in the name, display name, provider type, and credentials
  4. Configure provider-specific fields (see sections below)
  5. Click Test Connection, then Save

You.com Research

You.com Research returns AI-synthesized answers with citations, drawn from live web sources. It supports five effort tiers that trade cost and latency for answer depth.

Configuration Fields

FieldRequiredDescription
API KeyYesYour You.com API key
Effort TierYeslite, standard, deep, exhaustive, or frontier
Include DomainsNoComma-separated domains to restrict results (e.g., fda.gov, nih.gov)
Exclude DomainsNoComma-separated domains to filter out
FreshnessNoRecency filter: any, past day, past week, past month, past year
CountryNoISO 3166-1 alpha-2 country code (e.g., US)
Output SchemaNoJSON Schema for structured outputs (ignored on lite tier)

Effort Tiers

TierSpeedCostUse When
liteFastLowestQuick fact checks, simple questions
standardModerateLowGeneral research tasks
deepSlowerMediumThorough research with multiple sources
exhaustiveSlowHighComprehensive reports requiring broad coverage
frontierSlowestHighestMaximum depth, complex multi-step reasoning

Structured output via Output Schema is not available on the lite tier.

You.com Search returns raw web and news search results. An optional livecrawl feature fetches the full page content at query time.

Configuration Fields

FieldRequiredDescription
API KeyYesYour You.com API key
Result CountNoNumber of results to return (1-100, default 10)
FreshnessNoRecency filter: any, past day, past week, past month, past year
CountryNoISO 3166-1 alpha-2 country code (e.g., US)
LanguageNoBCP 47 language tag (e.g., en-US)
SafesearchNooff, moderate, or strict
LivecrawlNooff, always, or fallback
Livecrawl FormatsNoComma-separated subset of html, markdown (active when livecrawl is on)
Crawl TimeoutNoSeconds before livecrawl times out per page
Include DomainsNoComma-separated domains to restrict results
Exclude DomainsNoComma-separated domains to filter out

Livecrawl Costs

Enabling livecrawl causes ExecAssist to fetch the full contents of each result page at search time. This adds approximately $0.001 per page returned and increases response latency. Use fallback mode to crawl only when cached content is unavailable, or always to force fresh crawls on every search.

The Livecrawl Formats field is disabled when livecrawl is set to off.

Exa

Exa is a neural search engine over a curated web index. It is optimized for semantic, similarity-based retrieval rather than keyword ranking, making it a strong choice when agents need to find pages that are conceptually related to a query rather than pages that contain exact words.

Configuration Fields

FieldRequiredDescription
API KeyYesYour Exa API key
Result CountYesNumber of results to return (1-10, default 10)
Search TypeYesauto (Exa picks), neural (embedding-based), or keyword (traditional matching)
Use AutopromptNoLet Exa rewrite the query for better neural recall (recommended for neural type)
CategoryNoRestrict results to a content category (see table below)
Include DomainsNoComma-separated domains to restrict results (e.g., nytimes.com, bbc.com)
Exclude DomainsNoComma-separated domains to filter out
Start Crawl DateNoOnly return pages first crawled on or after this date (YYYY-MM-DD)
End Crawl DateNoOnly return pages first crawled on or before this date (YYYY-MM-DD)
Start Published DateNoOnly return pages published on or after this date (YYYY-MM-DD)
End Published DateNoOnly return pages published on or before this date (YYYY-MM-DD)
Include Page TextNoFetch the full page text with each result
Max CharactersNoMaximum characters of page text to return per result (1-100,000, default 1,000)
Include HTML TagsNoKeep HTML tags in the returned page text

Search Types

TypeDescriptionUse When
autoExa selects neural or keyword based on the queryGeneral use - good default
neuralEmbedding-based semantic retrievalFinding pages semantically similar to a concept
keywordTraditional keyword matchingExact phrase lookups, proper nouns

Content Categories

Restrict results to a specific content type by setting Category:

CategoryDescription
companyCompany home pages and profiles
research paperAcademic and scientific papers
newsNews articles
linkedin profileLinkedIn user profiles
githubGitHub repositories and code
tweetTwitter/X posts
movieMovie pages
songSong and music pages
personal sitePersonal websites and blogs
pdfPDF documents
financial reportAnnual reports, 10-Ks, investor documents

Leave Category blank to search across all content types.

Page Text and Cost

Enabling Include Page Text causes ExecAssist to fetch the full text of each result page. This increases response latency and may affect Exa billing. Use Max Characters to cap the text size per result when full pages are not needed. Set Include HTML Tags only if downstream processing requires structured HTML.

Getting Your Exa API Key

  1. Sign up at exa.ai and go to your developer dashboard
  2. Create an API key under API Keys
  3. Copy the key and paste it into the API Key field in ExecAssist

Getting Your You.com API Key

  1. Sign up or log in at you.com and navigate to your developer dashboard
  2. Create an API key under API Access
  3. Copy the key and paste it into the API Key field in ExecAssist

Both You.com Research and You.com Search use the same API key.

Tavily

Tavily is a web search API built for AI agents. It returns factual results with source links and optional AI-extracted answers, without the synthesized narrative of Perplexity or You.com Research. Pick Tavily when agents need fast, reliable factual lookups with transparent source attribution and a straightforward per-call pricing model. For LLM-synthesized cited prose, prefer Perplexity or You.com Research instead; for semantic similarity retrieval, prefer Exa.

Getting Your Tavily API Key

  1. Sign up at tavily.com and verify your email
  2. Open the Tavily dashboard and navigate to API Keys
  3. Copy your key (it begins with tvly-)
  4. Paste the key into the API Key field in ExecAssist

Configuration Fields

FieldRequiredDescription
API KeyYesYour Tavily API key (tvly-...), sent as api_key in the JSON request body
Search DepthNobasic (faster, lower cost) or advanced (deeper crawl, higher cost). Default basic
TopicNogeneral or news - scopes the index queried. Default general
Result CountNoNumber of results to return (1-20, default 5)
Include AnswerNoWhen enabled, Tavily appends an AI-generated direct answer above the source list
Include Raw ContentNoWhen enabled, each result includes the full page text
Include ImagesNoWhen enabled, results include related image URLs
Include DomainsNoComma-separated domains to restrict results (e.g., reuters.com, apnews.com)
Exclude DomainsNoComma-separated domains to filter out
DaysNoFor news topic only - limits results to pages published within the last N days

Pricing

Tavily bills on API credits. One credit equals one search call.

PlanCredits IncludedApprox. Cost per CallNotes
Free1,000 credits/month$0Non-commercial evaluation only
Starter10,000 credits/month~$0.004Light production workloads
Growth50,000 credits/month~$0.002Volume discount
EnterpriseCustomCustomDedicated support, SLAs

advanced search depth consumes more credits per call than basic. Enabling Include Raw Content also increases cost because Tavily fetches and trims full page text server-side. Confirm current rates on the Tavily pricing page before committing to high-volume usage.

Gotchas

  • The Days field is only respected when Topic is set to news. Setting it on a general search has no effect.
  • Include Answer and Include Raw Content add latency as well as credit cost. Leave them off unless the agent needs to reason over full page content or wants a direct answer string.
  • Tavily does not enforce domain-level authentication. Any valid API key can query any public URL, so rotate keys if they are exposed.
  • The free tier is for non-commercial evaluation. Move to a paid plan before pointing production agents at Tavily.
  • Include Domains and Exclude Domains are mutually exclusive in practice - combining both on the same provider narrows results unpredictably. Use one or the other.
  • Tavily's index skews toward English-language content. For non-English research tasks, evaluate result quality before committing.

Exa

Exa is a neural search engine that retrieves results by semantic similarity rather than keyword match. Pick this provider when agents need to discover content based on meaning - "find pages like this one", research-grade discovery across curated web content, or category-scoped lookups (research papers, GitHub repos, company sites). For LLM-synthesized cited answers, prefer Perplexity or You.com Research instead; for raw keyword web search, prefer Brave or Tavily.

Configuration Fields

FieldRequiredDescription
API KeyYesYour Exa API key, sent as x-api-key on every request to https://api.exa.ai/search
Result CountNoNumber of results to return (1-10, default 10)
Search TypeNoneural (semantic), keyword (lexical), or auto (Exa picks per query). Default auto
Use AutopromptNoWhen true, Exa rewrites the query for better neural retrieval. Default true. Only meaningful for neural or auto
CategoryNoRestrict results to a content category: company, research paper, news, linkedin profile, github, tweet, movie, song, personal site, pdf, or financial report
Include DomainsNoComma-separated domains to restrict results (e.g., arxiv.org, nature.com)
Exclude DomainsNoComma-separated domains to filter out
Start Crawl DateNoISO 8601 lower bound for when Exa first crawled the page
End Crawl DateNoISO 8601 upper bound for crawl date
Start Published DateNoISO 8601 lower bound for when the page was published
End Published DateNoISO 8601 upper bound for publish date
Return Page TextNoWhen enabled, each result includes the page text. Adds per-result cost (see below)
Max CharactersNoCap on returned text length per result (active when Return Page Text is on)

Pricing

Exa charges per search and adds an extra per-result fee when page text is requested. Approximate rates:

ComponentApprox. CostWhen Charged
Search call~$0.005 per queryEvery /search request
Result with page text~$0.001 per resultOnly when Return Page Text is on

A typical call with Return Page Text off costs about half a cent. With page text on and Result Count at 10, expect roughly 1.5 cents per call. Confirm current rates on the Exa pricing page before committing to high-volume usage. Exa offers a free monthly allotment for evaluation; paid plans bill on usage above that.

Gotchas

  • Exa is stateless. ExecAssist's multi-turn search flow re-issues a fresh /search call on each turn rather than continuing a session, so per-call cost multiplies with MaxTurnsPerSession.
  • Use Autoprompt has no effect on the keyword search type. Disable it explicitly if you want the agent's exact query passed through verbatim on neural runs.
  • Return Page Text adds latency as well as cost - Exa fetches and trims each page server-side before responding. Leave it off for fast title/snippet lookups; turn it on only when the agent needs to reason over full content.
  • Start/End Crawl Date and Start/End Published Date filter different signals. Crawl date is when Exa indexed the page; published date is when the source claims the page was authored. They can diverge by months for older content.
  • Exa does not return an LLM-synthesized answer. The tool wraps results into a Markdown digest client-side, but agents that need cited prose should prefer Perplexity or You.com Research.
  • The Exa /search endpoint covers the text content option used here. Other Exa endpoints (/findSimilar, /contents) are out of scope for this provider type.

Getting Your Exa API Key

  1. Sign up at exa.ai and verify your email
  2. Open the Exa dashboard and navigate to API Keys
  3. Create a new key and copy it
  4. Paste the key into the API Key field in ExecAssist

Brave

Brave Search is a privacy-focused web and news index. Pick this provider when agents need fast factual lookups with broad coverage and a low per-call price, and when the answer should come from raw web results rather than an AI-synthesized summary. For research-style cited answers, prefer Perplexity or You.com Research instead.

Configuration Fields

FieldRequiredDescription
API KeyYesYour Brave Search API subscription token, sent as X-Subscription-Token on every request
EndpointYesweb or news - selects the Brave Search index queried
Result CountNoNumber of results to return (1-20, default 10)
CountryNoISO 3166-1 alpha-2 country code (e.g., US)
Search LanguageNoTwo-letter language code for results (e.g., en)
UI LanguageNoBCP 47 language tag for localized result strings (e.g., en-US)
SafesearchNooff, moderate, or strict (default moderate)
FreshnessNoRecency filter: pd (past day), pw (past week), pm (past month), py (past year), or a YYYY-MM-DDtoYYYY-MM-DD range
Extra SnippetsNoReturn additional excerpt strings per result (Pro tier and above)
Goggles IDNoA custom Goggle URL or ID that re-ranks results against a community ranking profile

Pricing Tiers

TierApprox. CostRate LimitNotes
Free$01 query/sec, 2,000 queries/monthNon-commercial use only; good for evaluation
Data for Search Base~$3 per 1,000 queries ($0.003/call)20 queries/secStandard web/news results
Data for Search Pro~$5 per 1,000 queries ($0.005/call)50 queries/secAdds extra snippets, summarizer access, Goggles
Data for AI Pro~$9 per 1,000 queries ($0.009/call)HighIncludes data rights for LLM grounding and RAG pipelines

Pricing changes occasionally; confirm current rates on the Brave Search API pricing page before committing to a tier.

Gotchas

  • The free tier prohibits commercial use. Move to a paid tier before pointing production agents at it.
  • Extra Snippets and the Brave summarizer require the Pro tier or higher; the field is accepted on Base but ignored.
  • The web and news endpoints are mutually exclusive on a single provider entry. Configure two providers if agents need both.
  • Brave's index is global, but result quality varies by region. Set Country and Search Language when answers should reflect a specific market.
  • Each subscription token is bound to one tier. Rotating from Free to Base or Pro requires generating a new token in the dashboard.

Getting Your Brave API Key

  1. Sign up at brave.com/search/api and verify your email
  2. Open the API dashboard and pick a subscription tier
  3. Generate a subscription token under API Keys
  4. Copy the token and paste it into the API Key field in ExecAssist

Managing Providers

Viewing Providers

The Specialized Search list shows all configured providers with their type, connection status, and the date they were added.

Editing a Provider

  1. Click on the provider name in the list
  2. Update settings as needed
  3. Click Test Connection to verify the updated credentials
  4. Click Save

Deleting a Provider

  1. Remove any agent tools that reference this provider first
  2. Click the delete icon next to the provider
  3. Confirm deletion

Deleting a provider removes its associated search tool from all agents that use it.

Troubleshooting

Connection Test Fails

SymptomLikely CauseSolution
401 UnauthorizedInvalid API keyRe-copy the key from your provider dashboard
403 ForbiddenSubscription limitVerify your plan includes API access
TimeoutNetwork or rate limitRetry; check provider status page

Search Returns No Results

  • Verify the query is supported by the selected provider
  • Check that domain filters are not too restrictive
  • For You.com Research, try a lower effort tier to confirm basic connectivity

Livecrawl Not Returning Page Content

  • Confirm livecrawl is set to always or fallback (not off)
  • Check that the crawl timeout is sufficient (some pages load slowly)
  • Some pages block crawlers; this is expected behavior

FAQ

Can I add both You.com Research and You.com Search with the same API key? Yes. Create separate providers for each type - they share the same API key but have different configuration options and produce different tool behaviors.

Which You.com tier should I start with? Start with standard. It balances cost, speed, and answer quality for most research tasks. Move to deep or exhaustive only when agents need comprehensive coverage.

Does livecrawl affect my You.com API rate limits? Livecrawl is billed separately by You.com per page crawled and does not count against your search query limits. Check your You.com plan for crawl pricing.