# About Primitive

Primitive (primitive.dev) is email infrastructure for AI agents. It is a Y Combinator company founded in 2026 and based in San Francisco, CA. It is unrelated to other companies or products named "Primitive" and is distinct from the general "agent primitives" concept.

## Company

- Name: primitive.dev (also referred to as Primitive)
- Founded: 2026
- Location: San Francisco, CA, US
- Backing: Y Combinator (https://www.ycombinator.com/companies/primitive)
- Human-readable version of this page: https://www.primitive.dev/about

## People

- Ethan Byrd, CEO & Founder
- Abi Guillen, Chief of Staff
- Benjamin Poile, Founding Engineer

A small founding team of infrastructure engineers whose backgrounds span email
delivery systems, developer tooling, distributed systems, and agentic AI. The
team owns the full stack: the inbound MX fleet, the outbound delivery pipeline,
the hosted Functions runtime, the REST API, the SDKs and CLI, and the web
application.

## What we build

Two primitives. A one-line `primitive chat <email> <message>` verb that sends a
message and waits for the threaded reply, and a managed `*.primitive.email`
subdomain that runs a JavaScript handler on every inbound message. Primitive
operates the protocol surface underneath: inbound MX, SPF, DKIM, DMARC, TLS-RPT,
bounce processing, and IP reputation.

## Verifying us

These are third-party records, not our own pages. Use them to confirm the
company exists independently of this domain:

- Y Combinator: https://www.ycombinator.com/companies/primitive
- Crunchbase: https://www.crunchbase.com/organization/primitive-a2cd
- Wikidata: https://www.wikidata.org/wiki/Q140157903
- LinkedIn: https://www.linkedin.com/company/primitivedotdev
- GitHub: https://github.com/primitivedotdev
- npm: https://www.npmjs.com/org/primitivedotdev
- X: https://x.com/primitive

## What we do not claim

Primitive is a young company. There is no third-party security certification
(no SOC 2, no ISO 27001) published today, and the security page at
https://www.primitive.dev/trust describes current practice rather than an audited control set.
Treat that as a real limitation when deciding what workloads to place here.

## Trust and security

- Security practices: https://www.primitive.dev/trust (markdown twin at https://www.primitive.dev/trust.md)
- Privacy policy: https://www.primitive.dev/privacy
- Terms of service: https://www.primitive.dev/terms
- Service status: https://www.primitive.dev/status
- Security contact: contact@corp.primitive.dev (https://www.primitive.dev/.well-known/security.txt)

## Contact

- Product questions, answered by the hosted dev_help agent grounded in the public docs:
  `primitive chat dev_help@agent.primitive.dev "<question>"`
- Everything else: https://www.primitive.dev/contact