Floki's AI email agents improve themselves — safely. Every loop is contained, every action logged, and every increase in autonomy is a decision only you can make.
Builds a private model of your voice and habits from your edits and actions — per mailbox, never shared across boxes. 14 edits absorbed this week.
82% approve-unchangedRuns each of your workflows as mail arrives — trigger, AI steps, actions. This morning it filed 6 emails and drafted 2 replies, all within the trust dial you set.
214 handled / wkWatches outcomes and proposes new workflows or trust changes. Proposals only — you approve every one, and a dismissed idea stays dismissed.
2 proposals waitingOne continuous cycle: learning feeds execution, execution’s log feeds improvement — and approved proposals, plus your edits, flow back into learning. Proposals land in Suggestions; nothing enacts itself.