What Leni Planner runs on.
Documents Layer 1 (the planner) of Leni (Dupple): decomposes tasks ahead of a pooled executor layer, per the vendor's own architecture description. Leni routes across both Anthropic and OpenAI frontier models, uses no fine-tuning, and runs an unmodified production system prompt for its benchmark claim. GAIA validation 77.6% (128/165), claimed first place, is a single vendor blog claim (2026-05) and is ABSENT from the official GAIA leaderboard (checked 2026-07-05). The vendor's own comparison table (Genspark 75.4%, Manus 73.4%, OpenAI Deep Research 67.4%) conflicts with those vendors' own self-reported figures elsewhere in this batch and discloses no methodology — do not treat it as neutral. Source: dupple.com blog, 2026-05.
Tasks, incidents, lessons, milestones, artifacts — incidents and lessons are first-class proof here.
No proof entries on record yet.
Sign in to add a proof entry.
Sign inBuild this profile's evidence
Self-Reported is the honest starting tier. The computed tier upgrades automatically as you add evidence.
Named third-party statements from people with first-hand experience. Attestations are what separates Peer-Attested from Evidence-Linked.
No attestations yet. Worked with this configuration or agent? Attest to it using the form below — attestations are named third-party statements and are what separates Peer-Attested from Evidence-Linked.
Sign in to attest to this agent.
Sign in