Athlete Intelligence Agent

Give it an athlete's name — get back a rich, source-cited profile. The Athlete Intelligence Agent is an autonomous AI agent, not a fixed scraper. Powered by Claude, it decides for itself which sources to consult: it resolves the athlete's identity and sport, then pulls career stats, market value, achievements, social reach, and recent news from free sports APIs, the open web, and specialised Apify scrapers — cross-checking sources and attaching a confidence score and citation to every field.

You can steer it with plain English ("focus on transfer rumours", "I'm evaluating social reach for a sponsorship deal"), or just give it a name and let it figure out the rest. Run it on the Apify platform for API access, scheduling, integrations (Make, Zapier, Slack, Google Drive), proxy rotation, and run monitoring.

Why not just ask an AI chatbot? A chatbot gives you unsourced prose from memory and can't reach the data that actually matters — follower counts behind anti-bot walls, Transfermarkt market values, or clean structured stats. This Actor pairs the same reasoning with proxy-backed scrapers and structured sports APIs, then returns it as a schema-stable, batchable, source-cited dataset you can pull via API or run on a schedule.

What does Athlete Intelligence Agent do?

• Resolves identity first — uses Wikidata + Wikipedia to pin down the exact athlete (handling same-name ambiguity), their sport, nationality, date of birth, and official social handles.
• Gathers sport-specific stats from free official/structured sources: ESPN (NBA/WNBA, NFL, NHL, MLB and US college), the MLB Stats API (baseball), and the Ergast/Jolpica F1 API (Formula 1).
• Adds depth where free data falls short — Transfermarkt for football market value & transfers, Google News for recent coverage and sentiment, and Instagram / X / TikTok / YouTube for follower counts and influence (opt-in).
• Falls back to open-web search (Apify RAG Web Browser for search, Web Fetch for reading a specific page) for any sport or fact the structured sources miss — so niche athletes still get a profile.
• Synthesises one structured profile with per-field provenance, an overall confidence score, and a completeness percentage.

Why use Athlete Intelligence Agent?

No single database covers every athlete and every sport. Analysts, journalists, scouts, and marketers normally stitch together Wikipedia, ESPN, Transfermarkt, and social platforms by hand. This agent does that work autonomously and shows its sources, so you can trust (or challenge) every value.

Typical buyers:

• Sports journalists & media — instant, sourced player backgrounders and comparisons.
• Scouts, agents & clubs — career trajectory, market value, and availability at a glance.
• Sponsorship & brand-marketing agencies — social reach, engagement, and influence scoring for athlete-brand fit.
• Fantasy & sports-betting products — enriched player context and recent news/injury signals.
• Fan apps & media platforms — ready-made athlete profiles to drive engagement.

How to use Athlete Intelligence Agent

1. Open the Actor and enter an athlete name (e.g. Carlos Alcaraz).
2. (Optional) Add instructions to emphasise what you care about, and a sport hint if the name is ambiguous.
3. (Optional) Pick a depth: quick (free only), standard (recommended), or deep (adds social media).
4. Click Start. When the run finishes, open the Output tab to see the profile, or pull it via the API/integrations.

Input

Field	Type	Description
operation	enum	profile (default) for the full AI-built profile, or a single lookup: identity, stats, market, news, social, search, crawl.
athleteName	string	The athlete to research.
instructions	string	Free-text steer for emphasis / source priority.
sportHint	string	Disambiguates same-name athletes (e.g. tennis).
depth	enum	quick / standard / deep. Default standard.
enableSocial	boolean	Scrape social media follower counts. Leave unset to follow the depth preset (ON for deep).
costCapUsd	number	Soft ceiling on combined LLM + scraper spend per run.
maxIterations	integer	Hard ceiling on agent reasoning steps (≤ 20).
model	enum	Claude model. Default claude-opus-4-8.
query	string	For the news and search lookups. Defaults to the athlete name.
url	string	For the crawl lookup.
platform / handle	string	For the social lookup.
maxResults	integer	For the news and search lookups.
anthropicApiKey	string (secret)	Optional. Leave empty — no AI account needed (see Pricing).

{
  "athleteName": "Kylian Mbappé",
  "instructions": "Focus on market value, recent transfers, and social reach.",
  "depth": "standard"
}

Output

Single lookups (operation other than profile) write one raw source envelope:

{ "ok": true, "source": "Wikidata", "layer": 0, "url": "https://www.wikidata.org/wiki/Q85518537",
  "fetchedAt": "2026-09-14T17:41:02Z",
  "data": { "canonicalName": "Carlos Alcaraz", "sport": "tennis", "nationality": "Spain" } }

Full profiles write one dataset item per athlete. Download as JSON, CSV, Excel, or HTML. Simplified example:

{
  "identity": { "canonicalName": "Kylian Mbappé", "sport": "association football", "nationality": "France", "dateOfBirth": "1998-12-20" },
  "team": { "currentTeam": "Real Madrid", "league": "La Liga" },
  "statistics": { "career": { "goals": 320, "appearances": 420 } },
  "market": { "estimatedValueUsd": 180000000, "valueAsOf": "2026-06" },
  "social": { "profiles": [{ "platform": "instagram", "followers": 122000000, "verified": true }], "totalReach": 150000000, "influenceScore": 98 },
  "news": { "overallSentiment": "positive", "recentHeadlines": [{ "title": "...", "source": "...", "sentiment": "positive" }] },
  "meta": { "overallConfidence": 88, "completenessPct": 83, "sources": [{ "field": "market.estimatedValueUsd", "source": "Transfermarkt", "confidence": 80, "url": "..." }] }
}

Data fields

Group	Contents
identity	name, Wikidata QID, DOB, age, nationality, birthplace, sport, status
physical	height, weight, dominant hand/foot, position(s), playing style
team	current team, league, shirt number, contract end, coach
careerHistory	chronological stints: team, dates, appearances, transfer fee/type
statistics	sport-specific career totals + season breakdown
achievements	titles, individual awards, records, international caps/goals
market	estimated value (USD), value timeline, salary estimate
social	per-platform handles, followers, verification, total reach, influence score
news	recent headlines with source, date, sentiment, topic
endorsements	known sponsors & categories (confidence-tagged)
meta	per-field sources + confidence, overall confidence, completeness, tokens, cost

The full raw evidence trail (every source call the agent made) is saved to the run's key-value store under evidence for auditing.

Pricing & cost

This Actor uses pay-per-event pricing. You are charged for what you ask for:

You run	You're charged
A full profile	profile-emitted, once — at 1x for quick, 2x for standard, 3x for deep
A single lookup (operation other than profile)	tool-call, once
Any run	the standard Apify start event

Deeper research calls more paid sources, which is why it costs proportionally more.

Everything runs on your Apify account, so there is a second layer: the platform usage of this Actor and of every sub-Actor it calls. Measured on real runs:

Run	Total platform cost
quick, Haiku, a tennis player	~$0.20
deep, Opus, a footballer	~$0.49
deep, Sonnet, a footballer	~$0.56

On a deep footballer the two big line items are the LLM ($0.21) and Transfermarkt ($0.20); Transfermarkt varies significantly run to run. Single lookups are far cheaper — typically under $0.01, except market, which pays Transfermarkt.

No AI account needed. By default the Actor reaches Claude through Apify's first-party apify/openrouter proxy, billed to your Apify account in credits with everything else. Supply anthropicApiKey only if you'd rather the LLM cost went to your own Anthropic account.

The costCapUsd input is a soft ceiling on combined LLM + sub-Actor spend during one profile: when reached, the agent stops gathering and emits what it has.

Tips

• Cheaper runs: choose depth: quick, lower costCapUsd, or model: claude-haiku-4-5. For one specific fact, use a single lookup (operation) instead of a full profile — it skips the AI entirely.
• Ambiguous names: set sportHint (e.g. two athletes named "Chris Wood" — add "soccer").
• Sponsorship analysis: set depth: deep (or enableSocial: true) for follower counts and influence scoring.
• No AI account required: leave anthropicApiKey empty and Claude is reached via Apify's apify/openrouter proxy, billed in Apify credits. Set the key only to move that cost to your own Anthropic account.
• Running with a scoped API token? Apify doesn't support restricted-access scoped tokens against Standby Actors, and the LLM proxy is one. If the run fails to reach it, use a normal token or supply your own anthropicApiKey. Single lookups (operation other than profile) are unaffected.

FAQ, disclaimers & support

• Which sports are supported? Basketball (NBA/WNBA), NFL, NHL, MLB and US college have first-class structured stats via ESPN; baseball also via the MLB Stats API; Formula 1 via Ergast/Jolpica. Football/soccer, tennis and everything else are covered by Wikidata identity plus open-web search and, for footballers, Transfermarkt market data — expect a good profile, but not a full season-by-season stat line.
• Why is some data missing or marked low-confidence? Public sources disagree and have gaps. The agent reports honest completeness/confidence rather than inventing data; conflicts are noted in meta.
• Legality: This Actor aggregates publicly available information and attributes its sources. You are responsible for using the output in compliance with the source sites' Terms of Service and applicable data-protection laws. Inferred endorsements are flagged as low confidence.
• Feedback / bugs: please open an issue from the Actor's Issues tab.

Use it as a tool server (Standby)

The Actor also runs in Apify Standby mode as an HTTP tool server. Every tool endpoint runs with no AI key at all — point your own agent at them and let it do the reasoning:

Endpoint	Returns
GET /identity?name=	Wikidata identity: QID, DOB, nationality, sport, social handles, same-name candidates
GET /stats?name=&sport=	Career stats (ESPN / MLB Stats API / Ergast-Jolpica F1)
GET /market?name=	Transfermarkt market value & transfers (football). Priced separately — Transfermarkt is the one expensive source.
GET /news?query=	Recent news
GET /social?platform=&handle=	Follower count & verification
GET /search?query=	Web search as Markdown
GET /crawl?url=	Read one page (via Apify Web Fetch)
GET /profile?athleteName=	The full agent-built profile

Browse and try them on the Actor's Standby tab, or reach them from any AI agent through Apify's MCP server.

Note for operators: configure the profile-emitted, tool-call and market-lookup pay-per-event meters in the Apify Console before publishing. Keep the synthetic apify-actor-start event, and delete the synthetic apify-default-dataset-item event — it would double-charge alongside profile-emitted.