# Find experts to interview on any topic. From their papers and podcast appearances An expert search finds people through their recent work, not their self-description. With Agentik, your AI finds authors of recent, well-cited work with OpenAlex, people who spoke on podcasts through Exa, their X profiles through the X API and their emails with Icypeas. - For: Journalists, podcasters, consultants and event organisers - Providers: 4 (OpenAlex, Exa, X and Icypeas), 4 tools - Example (2 OpenAlex searches, one podcast transcript search, 10 X profiles, 10 emails found): at most $1.49, computed from the live catalog - Updated: 2026-10-10 ## Each provider does one part No single provider covers this job. Through Agentik your AI calls each one for its part, from one connection and one prepaid balance. - **OpenAlex** (1 tool, free): Authors of recent, well-cited papers on the topic, with their institutions. - **Exa** (1 tool, at most $1.00): Podcast transcripts searched through Particle for people who spoke on the topic. - **X** (1 tool, at most $0.30): The experts’ X profiles and bios. - **Icypeas** (1 tool, at most $0.19): Their work emails at their institution or company. ## Give this to your agent ```text Use my connected Agentik MCP server for this job: expert finder. Find experts to interview on a topic. First ask me for the topic, the angle and whether I want academics, practitioners or both. Find authors of recent, well-cited work with openalex/search-works. Find people who discussed the topic on podcasts with exa/particle. Read their X profiles with x/users-by-usernames. Find their emails with icypeas/find-emails-batch. Finish with a list (expert, affiliation, recent paper or appearance, why they fit, X, email) and an interview request for each. Before running anything, inspect each tool with inspect_tool, ask me for any input you don’t have instead of inventing it, and tell me the total price. Wait for my go. At the end, tell me what Agentik charged. ``` ## You provide - The topic and angle - Academics, practitioners or both ## What you get: an expert list with contacts and requests - Experts with recent work or appearances - Why each one fits - X profiles and emails - An interview request for each ## How to find experts to interview in Claude or ChatGPT Prices are the most each call can reserve for this example: 2 OpenAlex searches, one podcast transcript search, 10 X profiles, 10 emails found. ### 1. Find recent authors OpenAlex finds authors of recent, well-cited papers on the topic, with their institutions. - [Scholarly works search](/tools/openalex/search-works.md) `openalex/search-works` (OpenAlex, 2 searches): free ### 2. Find people who spoke on podcasts Particle, through Exa, searches podcast transcripts for people who spoke on the topic. - [Particle podcast transcript search](/tools/exa/particle.md) `exa/particle` (Exa, 1 transcript search): at most $1.00 ### 3. Find their profiles and emails The X API returns their profiles, and Icypeas finds their work emails. - [X user profiles by usernames](/tools/x/users-by-usernames.md) `x/users-by-usernames` (X, 10 profiles): at most $0.30 - [Icypeas email finder in batch](/tools/icypeas/find-emails-batch.md) `icypeas/find-emails-batch` (Icypeas, 10 people): at most $0.19 ### 4. Write the requests Your AI writes an interview request for each expert. Example total: at most $1.49. Each call is billed for measured usage; unused reservations are released. ## Ask it your way - Find three experts on urban heat islands I could interview this week. - Who has published the most cited research on this topic recently? - Which practitioners talked about this on podcasts this year? - Write an interview request to each expert. ## Why through Agentik - Research, podcasts, X profiles and emails come from four providers through one connection. - OpenAlex is free; the podcast search is the largest share of the price. ## Good to know - Academic emails are often public on university pages; your AI checks there first when it can. - Particle covers the podcasts it has transcribed. ## When to use something else For vetted experts on demand with scheduling, use an expert network. This playbook finds people through their published work. ## Expert finder: questions ### Are academic emails public? Often, on university pages. Your AI checks there first when it can. ### Does it cover every podcast? Particle covers the podcasts it has transcribed. ### What does the example cost? At most $1.49, reserved before each call and settled at the measured usage. ## Keep going - [Media list](/media-list.md): Journalists who covered your topic in the last months, found from their articles, with their X profiles, verified emails and the story each one wrote. - [Literature review](/literature-review.md): The most cited and most recent papers on a question from OpenAlex and Crossref, research found by meaning with Exa, and background from Wikipedia, in a review with citations. - [Podcast guest pitch](/podcast-guest-pitch.md): Podcasts that discussed your topic in the last year, how often they publish and whether they take guests, with the hosts’ emails and a pitch for each. - [Research tools for your agent](/tools/research.md) - [B2B data and enrichment tools for your agent](/tools/enrichment.md) - [Social tools for your agent](/tools/social.md) [All playbooks](/playbooks.md) · [Connection guides](/docs/clients.md) · [Billing](/docs/billing.md) --- [HTML page](/expert-finder) · [Agent index](/llms.txt)