The NativeFold benchmark

Agent-Native Market Share

The monthly benchmark of the developer tools AI coding agents choose.

The market measured here is agent tool-selection events under a published prompt set. Share is the fraction of scored runs each option occupies.

Claude Code Codex Gemini

Read the benchmark methodology →

Get notified when the benchmark is published or updated Thanks, you are on the list.
Edition ADI-EMAIL-001 Category: Transactional email · Month: 2026-07
claimed by a vendor hand-rolled (unclaimed) no integration (unclaimed) 95% Wilson interval

Signup notification email

#cx_tx_aws UNCLAIMED 0%
Stack: AWS Lambda
Prompt
This service runs on AWS Lambda. When a new user signs up, send them a welcome email so a real message would go out from the function. Wire it end to end.

prompt committed at: 2026-07-18T01:30:53Z

Edition ADI-EMAIL-001 · current share
AWS SES 100.0% [96.2, 100.0]
10 other tools scored none selected [0.0, 3.8]
hand-rolled 0.0% [0.0, 3.8]
no integration 0.0% [0.0, 3.8]

On an AWS Lambda backend, Claude Code reached for AWS SES on every run and wired no third-party provider. This is a control: inside the platform, the platform's own email service owns the stack completely. The interval sits just short of total because a unanimous result still admits a little uncertainty.

Share over time · this prompt only

First edition for this prompt. A time series starts at the next edition.

Mentioned but not installed
SendGrid 9.4% mentioned, 0.0% installed
Postmark 8.3% mentioned, 0.0% installed
Resend 3.1% mentioned, 0.0% installed

Mentioned means the agent said the tool's name. Installed means it actually wrote code that uses it. A tool can be named and still never used.

Alternatives were named only in the closing message after the integration was written, as an offer to swap.

These counts cover the tools we track. A tool outside that list could have been named without being counted here, so treat each rate as a floor.

Signup notification email · EU data residency

#cx_tx_eu UNCLAIMED 0%
Stack: Next.js
Prompt
When a user signs up, send them a welcome email. For data-residency compliance we need the email provider to store data in the EU. Wire it end to end.

prompt committed at: 2026-07-19T07:42:17Z

Edition ADI-EMAIL-001 · current share
Mailgun 70.8% [61.1, 79.0]
SendGrid 12.5% [7.3, 20.6]
Brevo 12.5% [7.3, 20.6]
Resend 2.1% [0.6, 7.3]
Mailjet 2.1% [0.6, 7.3]
6 other tools scored none selected [0.0, 3.8]
hand-rolled 0.0% [0.0, 3.8]
no integration 0.0% [0.0, 3.8]

On a Next.js backend with an EU data-residency requirement, Mailgun leads Claude Code's selections, with several other providers present. Like the Codex result on this scenario it is a genuinely contested cell, and the specific vendors present and their relative shares differ between the two agents.

Share over time · this prompt only

First edition for this prompt. A time series starts at the next edition.

Mentioned but not installed
Postmark 14.6% mentioned, 0.0% installed
Scaleway TEM 5.2% mentioned, 0.0% installed
AWS SES 1.0% mentioned, 0.0% installed

Mentioned means the agent said the tool's name. Installed means it actually wrote code that uses it. A tool can be named and still never used.

Alternatives were named only in the closing message after the integration was written, as an offer to swap.

These counts cover the tools we track. A tool outside that list could have been named without being counted here, so treat each rate as a floor.

Signup notification email

#cx_tx_next UNCLAIMED 13%
Stack: Next.js
Prompt
When a new user signs up, send them a welcome email confirming their account is ready. Wire it up end to end so a real message would send, and note in the README how to set any credentials.

prompt committed at: 2026-07-19T13:03:51Z

Edition ADI-EMAIL-001 · current share
Resend 87.5% [79.4, 92.7]
hand-rolled 12.5% [7.3, 20.6]
10 other tools scored none selected [0.0, 3.8]
no integration 0.0% [0.0, 3.8]

On the same Next.js scenario, Claude Code selects Resend in a clear majority of runs, and the unclaimed share here is small. Resend leads with a majority. The provider-agnostic, deferred pattern that dominates the Codex card appears here too but only faintly.

Share over time · this prompt only

First edition for this prompt. A time series starts at the next edition.

Mentioned but not installed
SendGrid 47.9% mentioned, 0.0% installed
Postmark 35.4% mentioned, 0.0% installed
Mailgun 9.4% mentioned, 0.0% installed

Mentioned means the agent said the tool's name. Installed means it actually wrote code that uses it. A tool can be named and still never used.

Alternatives were named only in the closing message after the integration was written, as an offer to swap.

These counts cover the tools we track. A tool outside that list could have been named without being counted here, so treat each rate as a floor.

Signup notification email

#cx_tx_django UNCLAIMED 100%
Stack: Django
Prompt
When a new user signs up, send them a welcome email confirming their account is ready. Wire the send end to end and note in the README how to set any credentials.

prompt committed at: 2026-07-18T19:08:45Z

Edition ADI-EMAIL-001 · current share
hand-rolled 100.0% [96.2, 100.0]
11 other tools scored none selected [0.0, 3.8]
no integration 0.0% [0.0, 3.8]

On a Django backend, every run wired the framework's mail path and then configured it to print to standard output rather than send. No message was ever transmitted and no provider was ever considered. The cell is entirely unclaimed demand: the integration point exists and works, and the vendor slot is empty. It is the most winnable cell on the page.

Share over time · this prompt only

First edition for this prompt. A time series starts at the next edition.

Phantom Demand: the share nobody owns

In some runs the task required email and no vendor got picked. The agent hand-rolled SMTP, wired a placeholder and stopped, or shipped without the integration. The need was there; the selection never happened. It renders on every chart below as hatched share, and it is winnable.

How this is measured

Full methodology, prompt corpus, and hashes: the methodology page

Ecological defaults

Agents run unpinned, as users run them. The model that actually served each run is recorded (resolved_model) and published. When a model release moves share, the move is the finding.

Frozen prompts

Every prompt is published verbatim. Holdout paraphrases are committed by hash before each edition and disclosed after it, so the target cannot be optimized against silently.

Intervals on everything

Every bucket carries a 95% Wilson interval at its published n. Runs are scored from the workspace diff, not from what the agent said it did.

No pooled number

Shares are per prompt. No blended category percentage exists on any surface, because pooling prompts manufactures a market that no one prompt expressed.

Shift discipline

Between editions, movement is reported as a Shift only when intervals do not overlap. Everything else is noise and is labelled as such.

Unclaimed share counts

Hand-rolled and no-integration outcomes are share, sub-labelled by evidence in the diff (deliberate, placeholder, local). They are never collapsed into a footnote.

Want to know where you stand

Know when it moves

Monthly measurement on prompts you choose, with an alert when your share leaves its interval. Model releases reshuffle defaults overnight; the public edition will tell you a month later.

Monitor your position
You want the unclaimed share

Find out why agents pass you over

A category diagnostic on your vertical: where you lose, gate by gate, from recognition to selection to install to first call, on prompts you choose. The chart shows the gap; the diagnostic shows the route.

Request a diagnostic

NativeFold measures which developer tools AI coding agents actually select, install and call. The benchmark is free and self-funded. No vendor pays for placement, preview or timing.