Prospeo
Emails and mobiles, with a searchable database behind them.
Prospeo is a contact enrichment tool, and one of the 53 tools hyreflow connects to Claude, ChatGPT and other AI assistants. Through hyreflow, an AI agent can run 7 actions, all of which look something up. Paid Prospeo actions cost 0.1 to 3.4 credits per result or per request, from your hyreflow credit balance, so you need no Prospeo account, though you can connect your own key.
Prospeo finds and verifies contact details for people you name, and searches its own database of 200 million contacts when you do not have a list yet. Both run in bulk.
Prospeo can start a list or finish one. In the default hyreflow waterfall it is among the first enrichers tried.
What can you ask Claude or ChatGPT to do with Prospeo?
With hyreflow connected, you ask for the outcome in plain language and the assistant runs Prospeo for you. For example:
- “Take this job brief url and build a first longlist using Prospeo and AI Ark”
- “Find verified emails for these 50, then check deliverability with Enrichley”
- “Search operations managers at logistics firms in the Midlands and file them in Recruiterflow”
- “Get a mobile for this candidate profile before I call”
Which tools work well with Prospeo?
In a hyreflow run, Prospeo is most often paired with AI Ark, Enrichley, FullEnrich and Recruiterflow.
- AI Ark
run both databases and merge, the coverage rarely overlaps completely
- Enrichley
clear the addresses before outreach
- FullEnrich
the waterfall for whatever Prospeo could not find
- Recruiterflow
file the longlist against the role it was built for
Which Prospeo actions can an AI agent run through hyreflow?
Through hyreflow, an AI agent can run 7 Prospeo actions, all of which look something up. Paid Prospeo actions cost 0.1 to 3.4 credits per result or per request, from your hyreflow credit balance, so you need no Prospeo account, though you can connect your own key.
| Prospeo action | What it does | Cost through hyreflow |
|---|---|---|
| Bulk enrich company | Looks something up | 0.4 credits per result |
| Bulk enrich person | Looks something up | up to 3.4 credits per result |
| Enrich company | Looks something up | 0.4 credits per result |
| Enrich person | Looks something up | up to 3.4 credits per result |
| Search company | Looks something up | 0.4 credits per request |
| Search person | Looks something up | 0.4 credits per request |
| Search suggestions | Looks something up | 0.1 credits per request |
One credit is priced on the pricing page. The full price list for every tool is in the pricing tables.
Which hyreflow skills use Prospeo?
75 hyreflow skills call Prospeo as part of the run. A skill is a whole pipeline your agent already knows, end to end.
Build Boolean and X-ray search strings from a job spec
use whenyou have a spec and want search strings you can paste into LinkedIn, Google or your ATS, without hand-typing forty title variants
Find candidates who have said publicly that they are open to work
use whena role has to be filled fast and you want to start with the people who have raised a hand, without the open-to-work filter in LinkedIn Recruiter
Find more candidates like the best person you ever placed
use whenyou can point at one person and say more like this, faster than you can write the brief that describes them
Find the candidate one level below who is ready to step up
use wheneveryone who already holds the title is out of budget or not moving, and the realistic hire is someone one level below
Map a whole talent pool, including the half that is not looking
use whenthe role is hard, the obvious search is exhausted, and you need to prove to a client that you have covered the market
Run one candidate search across every people database at once
use whenone database keeps handing you the same names and you suspect the rest of the market is sitting in the others
How does an AI agent know how to use Prospeo?
hyreflow ships a written playbook for Prospeo, and the agent loads it before the first call. Auth, rate limits, what each call costs, which actions need your approval, and the mistakes worth avoiding. It is the difference between an agent that knows the tool and one that guesses at it.
Read the Prospeo docs →Show the raw playbookwritten for the agent
HOW in lib/prospeo.py. Docs cached at reference/docs/prospeo/raw/.
Auth & config
- Base URL:
https://api.prospeo.io· Auth: headerX-KEY(envPROSPEO_API_KEY; never hardcode). All endpoints POST + JSON; consume credits on a found result.
Operations (ALL CONFIRMED from prospeo.io/api-docs, 2026-06-01)
Live: enrich_person (/enrich-person — data{first_name,last_name,full_name,linkedin_url,email,company_name,company_website,company_linkedin_url,person_id} + only_verified_email/enrich_mobile/only_verified_mobile), bulk_enrich_person (≤50), enrich_company, bulk_enrich_company (≤50), search_person (200M+ contacts, 30+ filters), search_company (30M+), search_suggestions, account_information (your own Prospeo account; needs your own Prospeo key). Endpoint index: reference/docs/prospeo/raw/endpoints.md.
⚠️ Deprecation
email_finder, domain_search, mobile_finder, social_url_enrichment, email_verifier, linkedin_email_finder are deprecated (sunset 2026-03-01) — kept as thin wrappers but migrate to enrich_person/search_person. enrich_person(enrich_mobile=True) = 3.4 credits (vs 0.4 for email).
Handoff
Enrichment layer: shortlist → Prospeo for emails/phones → validate → ATS/sequencer.
Member of the email_enrichment, people_search, phone_enrichment, and linkedin_profile waterfalls.
Field notes (production experience)
Field-shape note: these are vendor-native operational notes. The client returns the raw vendor JSON and uses the method names in this file — read field shapes accordingly (no normalized-wrapper /
result.data.prefix).
- Flow:
search_person/search_companyto build lists ->enrich_person/enrich_companyfor detail. - Search cost:
search_personandsearch_companybill 0.4 credits per request - one charge per page of up to 25 results. Person results are a masked preview (no email/mobile). Person search supports job-title boolean operators, department, seniority, industry, headcount, technology, location. - Mobile reveal is expensive:
enrich_mobile: truecosts 3.4 credits (vs 0.4 for email-only) when a mobile is actually revealed — afree_enrichmentresponse bills 0 and a mobile-tier call that reveals no mobile settles at the 0.4 base rate - only request it when phone outreach is explicitly needed. - Do NOT use Prospeo for job-change detection/filters - the live job-change filter has schema drift; use FullEnrich for job-change workflows.
Callable surface — lib/prospeo.py
Import: from lib.prospeo import Prospeo → instantiate Prospeo() (reads key from env). Base: https://api.prospeo.io. Generic passthrough: request(method, path, *, params, json).
account_information(payload: dict | None = None) -> dict— POST /account-information — usage/renewal/credits on your own Prospeo account (needs your own Prospeo key).bulk_enrich_company(payload: dict) -> dict— POST /bulk-enrich-company — up to 50 companies per call.bulk_enrich_person(payload: dict) -> dict— POST /bulk-enrich-person — up to 50 people per call.domain_search(payload: dict) -> dict— DEPRECATED → search_person/search_company. POST /domain-search.email_finder(payload: dict) -> dict— DEPRECATED → enrich_person. POST /email-finder (legacy work-email finder).email_verifier(payload: dict) -> dict— DEPRECATED. POST /email-verifier — verify an email address.enrich_company(payload: dict) -> dict— POST /enrich-company — company data enrichment.enrich_person(data: dict, *, only_verified_email: bool | None = None, enrich_mobile: bool | None = None, only_verified_mobile: bool | None = None) -> dict— POST /enrich-person — enrich one person (replaces email-finder/mobile-finder/social).linkedin_email_finder(payload: dict) -> dict— DEPRECATED → enrich_person. POST /linkedin-email-finder.mobile_finder(payload: dict) -> dict— DEPRECATED → enrich_person(enrich_mobile=True). POST /mobile-finder.search_company(payload: dict) -> dict— POST /search-company — query 30M+ companies.search_person(payload: dict) -> dict— POST /search-person — query 200M+ contacts with 30+ filters.search_suggestions(payload: dict) -> dict— POST /search-suggestions — canonical filter-value autocomplete before a search.social_url_enrichment(payload: dict) -> dict— DEPRECATED → enrich_person(data={'linkedin_url': ...}). POST /social-url-enrichment.
Questions about Prospeo and hyreflow
Can I use Prospeo inside Claude or ChatGPT?
Yes. hyreflow is a connector for Claude, ChatGPT and other AI assistants. Once hyreflow is connected, you ask for the outcome in plain language and the assistant calls Prospeo for you. hyreflow exposes 7 Prospeo actions this way.
Do I need my own Prospeo account to use it with hyreflow?
No. hyreflow holds the Prospeo account and bills each action from your hyreflow credits. If you already pay for Prospeo, you can connect your own key instead, and hyreflow then charges no credits for those calls.
What does Prospeo cost through hyreflow?
Paid Prospeo actions cost 0.1 to 3.4 credits per result or per request, from your hyreflow credit balance, so you need no Prospeo account, though you can connect your own key. hyreflow can show the cost of a paid action before it runs.
How do I connect Prospeo to an AI agent over MCP?
Add the hyreflow MCP server to your assistant and sign in. hyreflow calls the Prospeo API directly and exposes its actions as tools the assistant can run, so there is no separate Prospeo server to install.
Put Prospeo to work from one prompt
Connect hyreflow to Claude or ChatGPT and ask for the outcome. It reads the playbook above before it makes a single call.