Enterprise AI · AWS
Writer
Writer operates as a multi-tenant SaaS platform primarily hosted on AWS, with options for customers to deploy Writer’s self-hosted LLM on-premises or in their own cloud/VPC for stricter data residency and control.[9][16] The core stack combines enterprise-grade proprietary LLMs, a knowledge graph over customer data sources, and agent orchestration tooling (AI HQ / Agent Builder) exposed via web UI and APIs.[10][16][19]
Foundation proximity: Native (own / self-hosted weights)
Foundational models & how they consume them
PrimaryPalmyra (Writer enterprise-grade LLM family, including task- and industry-specific variants)· Writer (self-hosted on AWS and customer VPC/on‑prem options) · Native (own / self-hosted weights)
SecondarySelf-hosted LLM (Writer-branded, deployable in customer cloud or on‑prem)· Writer / customer-managed infrastructure · Native (own / self-hosted weights)
Cloud & datastore
AWSPostgreSQLvectorCompliance
SOC 2 (inferred)GDPR (inferred)Others that build on proprietary / self-built models
Abnormal SecurityAbridgeAdobeAI21 LabsAleph AlphaAmbienceExplore
FAQ
Does Writer use a foundational AI model?
Writer uses Palmyra (Writer enterprise-grade LLM family, including task- and industry-specific variants), Self-hosted LLM (Writer-branded, deployable in customer cloud or on‑prem) (Native (own / self-hosted weights)).
What cloud does Writer run on?
Writer runs on AWS.
What database does Writer use?
Writer uses PostgreSQL, vector.
How close does Writer run to the foundational model?
Writer is Native (own / self-hosted weights) — close to the metal, so cheaper tokens and more control over outputs.
Sources
writer.com ↗Also on the map
← Full orbit map (260 companies) · Score your own stack →
Architecture inferred from public sources · confidence medium · verify before betting on a detail.