Enrico Ros
Official sources for big-AGI, the open AI workspace whose fixed application document names Enrico Ros as author. The README credits Enrico Ros × Token Fabrics; current team size and controlling ownership remain unknown. Both original native Beam and standard Fuse cases completed once and failed with the recorded cached Qwen model; four of twelve conditions passed and eight failed.
The fixed application document names Enrico Ros as author, and the MIT license carries Enrico Ros copyright. The README describes big-AGI as independent and non-VC-funded and credits Enrico Ros × Token Fabrics. Its Token Fabrics LLC publisher field is an upstream self-description; this page does not independently establish corporate registration, current employee count or controlling ownership. The profile covers the complete main snapshot 80d366a88cc8 with package version 2.1.1, distinct from the separately observed v2.1.0 release. A solo creator or small-shop owner can provide confirmed facts, write a Custom Persona, compare Beam drafts and review a standard Fuse answer. In this snapshot standard Fuse uses its own synthesis prompt and excludes the original Persona system message, so indispensable facts also belong in the actual user request. The frozen pilot uses two same-model rays and one standard Fuse for each fictional repair-workshop case, with native LocalAI transport, omitted max_tokens, Context Override 8192 and approximate token counting. Both original cases completed once on 2026-10-03 and failed: primary passed three of six conditions and boundary passed one of six, with zero unverified conditions and five of six failure conditions triggered. Primary omitted Script and its spoken-copy section, did not preserve the one-shirt-per-attendee rule, and used Owner Review rather than the exact Owner review heading. Boundary omitted the workshop name and correction body, adopted contradictory twelve-attendee, leather-bag and guarantee fields, produced eighteen bullets rather than two and asserted booking/email completion. These were model-written claims; no real booking or email occurred. Six actual generation forwards and zero quality reruns were recorded. Native histories were recovered by read-only CUA IndexedDB observation and byte checks; The single native Download JSON attempt remained pending and no saved file was confirmed. The modern saving implementation waits for a system save picker; that inferred cause was not directly observed. The AIX capture retained canceled net::ERR_ABORTED events alongside complete provider stop/DONE streams and exact accepted first Fuse, without claiming an error-free browser. Results cover only this model, original prompts and fixed application configuration. Same-model alternatives cannot establish a cross-model accuracy benefit.
big-AGI is an open-source AI workspace for people who want control over their writing prompts and model choice. A solo creator or small-shop owner can supply confirmed facts, write a Custom Persona, compare separate Beam drafts and use a standard Fuse to combine them into material for human review. The official README credits Enrico Ros × Token Fabrics and describes an independent, non-VC-funded project; the fixed application document names Enrico Ros as author and Token Fabrics LLC as publisher. These are upstream public descriptions, not an independent company-registry or ownership audit. Current team size and controlling ownership remain unknown. This profile covers the complete main snapshot 80d366a88cc8 (package 2.1.1), not a v2.1.1 release. The two original cases used a fictional repair-workshop script and a conflicting sponsor note, each through two rays of the same cached Qwen model followed by one standard Fuse. Standard Fuse creates its own system prompt and omits the original Custom Persona system message, so the complete confirmed facts are also supplied in the user request. Both original native cases completed once on 2026-10-03 with Qwen2.5-Coder-1.5B-Instruct Q4_K_M and failed. Four of twelve conditions passed, eight failed and none remained unverified. The first fused workshop draft missed the required Script section, one-shirt-per-attendee rule and exact Owner review heading. The sponsor correction adopted conflicting capacity, item and guarantee claims and asserted booking/email completion. These results cover this recorded application, prompts and model configuration only; they do not measure overall product quality or establish a benefit from same-model Beam alternatives.