Interact
Interact opens its intranet to outside AI assistants and uses Claude to attack its own platform.
A side-by-side editorial comparison of Double and Novelcrafter — release velocity, themes, recent moves, and the top alternatives to consider.
Double turns a recorded Chrome session into an agent that repeats the task.
Double is an accounting-practice platform built around the Ask Double assistant. Autoclose, an October 29 add-on at $500 a month, lets agents run the month-end close, and November 5 extended Ask Double to allocations, bank matching and 1099 prep. The November 12 release lets accountants record a task in the Double Chrome extension and turn it into an agent, adds bank feeds for US Xero clients, per-user caps on AI credits and new permission choices for agent actions.
Novelcrafter keeps the model layer swappable and spends its own effort on the manuscript instead.
Two threads run through this window. The first is model plumbing: default collections refreshed as Claude 4.5 Sonnet, Gemini 3 Pro, and GPT-5.1 arrive, a generic OpenAI-compatible provider so unsupported vendors work anyway, and an opt-in control to prefer or avoid reasoning across Scene Beats and Chats. The second is the writer's own data — Codex entries can be marked case-sensitive so a character named Will stops matching every sentence, and an entry can sit in several custom categories at once. Word export gained bullet and numbered lists. The feed stops in March 2026.
Double is an accounting-practice platform built around the Ask Double assistant. Autoclose, an October 29 add-on at $500 a month, lets agents run the month-end close, and November 5 extended Ask Double to allocations, bank matching and 1099 prep. The November 12 release lets accountants record a task in the Double Chrome extension and turn it into an agent, adds bank feeds for US Xero clients, per-user caps on AI credits and new permission choices for agent actions.
Double is moving from an assistant that answers to agents that do recurring work, and is now letting firms create those agents by showing rather than configuring. Usage caps, permission levels and a web-browsing switch that is off by default show it adding controls as agents get more reach.
Expect more agent templates and recorder support for other client systems, plus wider Xero coverage after the US bank feeds launch.
Two threads run through this window. The first is model plumbing: default collections refreshed as Claude 4.5 Sonnet, Gemini 3 Pro, and GPT-5.1 arrive, a generic OpenAI-compatible provider so unsupported vendors work anyway, and an opt-in control to prefer or avoid reasoning across Scene Beats and Chats. The second is the writer's own data — Codex entries can be marked case-sensitive so a character named Will stops matching every sentence, and an entry can sit in several custom categories at once. Word export gained bullet and numbered lists. The feed stops in March 2026.
The model layer is treated as commodity and kept deliberately replaceable: users can clone collections, revert to previous ones, or point at any OpenAI-compatible endpoint, and the reasoning control is a preference rather than a hardcoded behavior. Novelcrafter's own investment goes into the Codex — the structured record of characters, places, and rules that gets fed to whichever model is in play — and into getting manuscripts out cleanly. That is a defensible split for a tool whose value is the writer's accumulated context rather than the generation itself.
Expect further Codex precision work, since case-sensitivity and multi-category membership are both fixes for the same failure — the wrong entries being pulled into context. What the entries do not show is whether the experimental reasoning support graduates out of the settings flag.
Other Collab products tracked by Sparkpulse, ranked by recent ship velocity. Each card links to a full editorial trajectory and lets you pivot into a head-to-head comparison with either Double or Novelcrafter.
Interact opens its intranet to outside AI assistants and uses Claude to attack its own platform.
Nextcloud's November patches lean on preview speed and sharing fixes across three branches.
Mattermost v12.1 puts bots and burn-after-reading messages under the same access rules.
Asana lets Division admins run their own custom roles, on top Enterprise plans only.
SiYuan 3.8.11 alphas add freeform mind maps and plugin snapshots right after 3.8.10.
Hive turns reporting into a planning tool: shared inputs, grouped values, per-person drill-downs.
See all Double alternatives → · See all Novelcrafter alternatives →
Latest ship moves from both products, interleaved chronologically. ⚡ = editorial spark.
They serve adjacent needs but don't currently overlap on shipped themes. Double is currently shipping more aggressively (velocity 8.8 vs 0.0), with 3 editorial sparks in the last 30 days against 0. See the at-a-glance table above for a side-by-side breakdown of velocity, recent sparks, and editorial themes.
Sparkpulse doesn't pick a winner — we score release velocity, not feature parity. Double is currently shipping more aggressively (velocity 8.8 vs 0.0), with 3 editorial sparks in the last 30 days against 0. For your specific use case, the alternatives sections above list other Collab products to evaluate alongside.
Top Double alternatives in Collab are ranked by recent ship velocity. Browse the "Double alternatives" section above for the current picks, or visit /alternatives/double for the full list with editorial commentary on each.
Top Novelcrafter alternatives in Collab are ranked by recent ship velocity. Browse the "Novelcrafter alternatives" section above for the current picks, or visit /alternatives/novelcrafter for the full list with editorial commentary on each.