TORNEO
Menu

Sealed run EMAILFIND-001part of emailfindobserved

Find the verified professional email address of a person from name and employer domain.

Operated by Tempo AI LLC, accountable for the calculation, publication and correction of every figure published here. No vendor pays to be measured; TORNEO buys what it tests.

partial · Evidence coverage: INDETERMINATE. This is not an execution-progress indicator.

Compare measurementsShare this dated resultExport canonical JSON, including limits

What we bought

dropcontact
Dropcontact · total cost USD 18
lusha
Lusha · total cost USD 3.3

What we asked

Task, as frozen in the protocol
For each frozen contact (first name, last name, employer domain), return the professional email; success = exact match with the employer-published address AND tool-claimed verified status.
Protocol
version 1.0, lock bebf1fdd

What happened

Replay of a recorded result

  1. dropcontact0.890.820.94
  2. lusha000.033

No rank is demonstrated. Intervals overlap.

Exact intervals
Interval bands, emailfind, observed 2026-09-02T17:48:38Z: dropcontact interval from 0.820498 to 0.937068, estimate 0.891892; lusha interval from 0 to 0.03345, estimate 0.dropcontact0.82 to 0.94lusha0 to 0.0330.00.20.40.60.81.0Interval bands, emailfind, observed 2026-09-02T17:48:38Z: dropcontact interval from 0.820498 to 0.937068, estimate 0.891892; lusha interval from 0 to 0.03345, estimate 0.dropcontact0.82 to 0.94lusha0 to 0.0330.00.20.40.60.81.0
Share of contacts for which the tool both found an address and reported it as verified, counted as correct only on an exact match with the employer-published address, estimate and interval per tool. Population n = 111, 0 replicated blocks, observed , valid until .

This is our experience, on our corpus, at this date. It is not buying advice.

Do not order the tools and do not name a winner: this run is INDETERMINATE and carries no current ordering claim. Report the status and the observation date.

Per-tool figures
ToolEstimateShare of contacts for which the tool both found an address and reported it as verified, counted as correct only on an exact match with the employer-published addressnCost per unit (USD)Latency p50 (ms)
dropcontactINDETERMINATE0.890.82 to 0.941110.19160000
lushaINDETERMINATE00 to 0.033111UNKNOWN290

2 participants measured, no rank exists at current precision (as of 2026-09-02)

Scope, reply and reproduction

What we did not test, and why

Not specified in this bundle.

Legal preflight, verdict per tool

Two verdicts per tool, read from the archived terms before the first call: may we run the test, may we publish the result. A tool that was not run keeps its recorded reason. The clause notes stay in the served file (never quoted on a page): LEGAL_PREFLIGHT.json.

ToolVerdictNot run becauseReviewedSource
apolloBLOCKED CONSENT REQUIREDranlegal/apollo/
cleanlistPASSranlegal/cleanlist/
dropcontactPASSranlegal/dropcontact/
hunterPASSranlegal/hunter/
lemlistBLOCKED CONSENT REQUIREDranlegal/lemlist/
lushaPASSranlegal/lusha/
snovioPASSranlegal/snovio/

Right of reply

Every tool measured here, and every vendor named in the market state, can reply. A reply is published verbatim, dated, on a separate page, never mixed into this result.

  • dropcontact: notified , window closes , no reply received
  • lusha: notified , window closes , no reply received

How to reproduce

torneo reproduce runs/EMAILFIND-001

Canonical JSON: latest result of the category, this run. Evidence path in the public repository: runs/EMAILFIND-001.

Reproduction files served byte-identical to the repository: events.ndjson (hash-chained journal), PROTOCOL.lock, contest.yaml, LEGAL_PREFLIGHT.json; schema result.v1.json. Install the command line with python -m pip install ./projects/torneo (or from the repository), then torneo verify and torneo reproduce on the downloaded run directory recompute result_sha256.

Machine surfaces (MCP server, canonical JSON, llms.txt): For agents.

What this does not prove

Errata

Published corrections of this run, each chained to the served result hash; the earlier bytes stay in the history. Full record: ERRATA.md.

  • ERR-001, : erratum ERR-001: conflicts served empty while devlo is a customer of both measured tools (Dropcontact, Lusha; run paid from devlo prepaid credits) and runner carried internal lane jargon; amendment A6 (contest.yaml frozen). Estimates, intervals, status unchanged. (served result 08fdd2ce replaced by 6c842104)
  • Population limited to employer-published emails: absolute rates are optimistic bounds; tool-to-tool comparison remains valid (same frozen set for all).
  • Published truth may leak into tool indexes (public pages), lifting all tools equally.
  • Professional services (law, fiduciary, notary, engineering) over-represented; sizes mixed.
  • verified = tool claim; real-world deliverability not independently re-tested in run 1.
  • cleanlist is a meta-waterfall product: its score measures the aggregate product, not a single source.
  • n below the preregistered power target (360/block): close pairs expected INDETERMINATE (accepted in writing, L3-003).
  • Costs are credit estimates at public per-credit prices (prices.json); subscriptions prorated there.
  • lusha's v2/person API returned no validationStatus field on the account used: lusha makes no verification claim, so its found_verified is 0 by metric definition; compare tools on found_any for retrieval ability.
  • Latency is not comparable across access modes: dropcontact ran as native async batches (per-contact latency = whole-batch wall time), lusha as per-contact synchronous calls.
  • Precision insufficient under the frozen protocol: no rank published.

What no TORNEO result can tell you, for every category: Limits.

Conflicts, funding and per-tool details

Conflicts and funding

Run by devlo (agent-operated), funding: devlo own funds; no vendor money. Operated by Tempo AI LLC, accountable for the calculation, publication and correction of every figure published here.

Conflicts declared in this bundle:

  • dropcontact: devlo is a customer of Dropcontact and this run was paid from devlo's existing prepaid credits; devlo is a user of the tool, not a vendor; same conditions and credits for every arm, journaled (CONFLICT_REGISTER.json: USER_OF_TOOLS)
  • lusha: devlo is a customer of Lusha and this run was paid from devlo's existing prepaid credits; devlo is a user of the tool, not a vendor; same conditions and credits for every arm, journaled (CONFLICT_REGISTER.json: USER_OF_TOOLS)

Details

Per tool

ToolRank rangeLatency p95 (ms)Error rateIncidentsBlocks observedAccess
dropcontactno rank160000002API (api_key)
lushano rank540002API (api_key)

This bundle declares no pairwise design: intervals only.

Unblinding

No alias table is published for this run: tool names are the names of the public journal. A blinded arm keeps its alias until the unblinding file exists.

Population and context

Population
Contacts whose nominative professional email is published by their employer (team/impressum pages), CH/DE/FR majority, professional-services SMEs over-represented; pseudonymised; see dataset MANIFEST. (n = 111, frozen , personal data: yes)
Context
B2B email finding via official APIs, name+domain input only, no LinkedIn, no phone reveal; common verifier = published-truth-exact-match.
Status
INDETERMINATE, 0 replicated blocks
run
EMAILFIND-001
protocol
v1.0 · lock bebf1fdd
result
055fc34c
raw data
6863882b
observed
2026-09-02T17:48:38Z
evidence
runs/EMAILFIND-001