Your AI teammate that gets answers, follows up, and keeps people and AI agents moving together
Stage
Startup
Startup
Founded
Not given
Not given
Based in
US
Not given
Pricing model
Paid
Freemium
Pricing
Free 100M tokens for new users. $0.04 per 1M tokens for input tokens.
10 free tasks (no credit card required), then $29/month for 20 tasks (founding price for first 50 teams, held for first 12 months if subscribed by December 31, 2026, then $59/month). Extra tasks $6 each when enabled. The people Emily contacts never pay.
Key features
384K token context window
Multimodal input support
100K tokens processed in less than a second
Structured output for direct code use
Subquadratic Sparse Attention algorithm for efficient compute
$0.04 per 1M tokens pricing
Customer content not used for model training
Data retention limited to 60 days
Works via email, Slack, and Discord without setup or inbox access
Reaches people across companies without requiring them to install anything
Remembers decisions and catches contradictions when plans change
Respects privacy and context by default
Coordinates work between people and AI agents on the same team
Provides each team member private follow-through from shared messages
Automatically follows up and waits through out-of-office periods
Bundles decisions and updates to minimize interruptions
Lets team members answer questions from collective memory without interrupting busy people
What makes it different
First long-context decision model purpose-built for enterprise work
Frontier-level decision-making performance at 5-10x lower cost than frontier LLMs
Tied for #1 on Artificial Analysis Decision Index
Processes entire codebase or data room in single context window
Speeds agent reasoning from minutes to seconds
No setup required; just CC Emily on emails or add her to Slack/Discord
Works transparently as a teammate with her own name, not as an anonymous automation
Coordinates people and AI agents across company boundaries without requiring installations
Keeps context separate by channel, conversation and privacy level automatically
Remembers what was decided and catches contradictions to prevent miscommunication
Subquadratic
Meetless