Loop Desk is an always-on business workspace that takes incoming signal (email, forms, feeds, notes) and turns it into briefs, watch items, and next actions.

Does Loop Desk send emails on my behalf?

Loop Desk can draft responses, but nothing sends until you approve and explicitly trigger it. The approval boundary is fundamental.

What signal sources does Loop Desk support?

Email, RSS/Atom feeds, form submissions, manual notes, and webhooks. The desk treats all sources equally in its processing loop.

rev 204 — Loop Desk changelog

rev 2042026-07-15Accelerating

Ships per-tier default daily cost caps — the flat-fee promise turned on by default — and closes the last two named rev-201 radar templates (independent specialty fishing / outdoor outfitters + independent stationery / pen shops, cluster reaches 77 verticals), then fixes the two gaps the cost-cap seeding + templates work left open. Connecting thread: rev 204 makes the rev-20 daily cost cap load-bearing on the strongest positioning axis Loop Desk has — 'you literally cannot overspend' — by seeding a plan-tier default at workspace creation instead of leaving it null (no cap). (a) Every workspace now seeds a plan-tier default daily cost cap via defaultCostCapCentsForTier (free $0.50 / pro $5 / team $20) so a brand-new desk has a hard spend ceiling from cycle 1 even if the operator never opens the integrations panel — fully overridable + removable via the rev-20 UI, and the integrations panel gains a 'Use plan default' one-tap re-apply affordance. The PLAN_LIMITS.{tier}.defaultDailyCostCapUsdCents figures are the single source of truth: the pricing module (src/lib/pricing-plans.ts) projects the same dollar figures via defaultDailyCostCapUsd so the /pricing caps block, the landing pricing block, and the /api/v1/pricing endpoint never drift from the seeded cap. (b) Two more onboarding templates close the rev-201 named radar wave: independent specialty fishing / outdoor outfitters (named-license + named-permit currency on every guided trip + charter, named-guide / named-charter continuity with a named-backup on every multi-day booking, seasonal inventory turn with the named-buyer ordering window per season, safety-incident hygiene with a same-day named-report + named-equipment quarantine on the water) and independent stationery / pen shops (named-supplier continuity on every allocation-limited pen + ink + paper line, collectibles authentication on every vintage + limited-edition intake, named-nib-service continuity on every service intake, gifting-peak inventory cadence). Two new OnboardingTemplateKey enum values (fishing_outfitter in hospitality-food, stationery_pen_shop in retail-ecommerce). The templates cluster is now 77 named verticals deep. (c) FIX — the rev-204 cost-cap seeding silently broke the rev-165 activation checklist 'Set a guardrail' step: because every workspace now ships with a cost cap set, the completion check (which keyed off 'a cost cap is set') auto-completed on cycle 1 and the nudge never surfaced. Rev 204 rekeys it off a cap that has been TUNED away from the seeded plan default (or Slack quiet hours / non-UTC timezone) so the step still nudges active engagement, and reframes the copy to 'Review your guardrails' — acknowledging the desk is already protected and inviting the operator to make the cap their own. (d) FIX — the rev-204 templates work added the two new verticals to the enum, TEMPLATE_LAUNCH, TEMPLATE_CATEGORY_BY_KEY, and the template data but forgot the TEMPLATE_KEYWORD_HINT entries, so both new verticals rendered without the per-vertical tagline chip every other vertical has had since rev 195; rev 204 adds both. (e) DESIGN — the today-panel Spend stat now surfaces the seeded cap as a reassuring brand-teal '🛡 $X/day cap · protected' chip at zero spend (the flat-fee promise visible from cycle 1) instead of the clinical '0% of $X cap', reverting to the percent-of-cap fact once spend starts. Plus the landing pricing sub-copy names the default-on hard cap as the 'No surprises' proof point ('every plan ships with a hard daily cost cap turned on by default, so your desk literally cannot overspend — even under a flat fee'). PRD + ROADMAP + CLAUDE.md updated (rev 204)

Per-tier default daily cost cap — the flat-fee guardrail, on by default from cycle 1The rev-20 daily cost cap was operator-configured per workspace and started null (no cap) — the strongest flat-fee positioning primitive Loop Desk has was off by default, so a fresh desk had no hard spend ceiling until the operator explicitly opened the integrations panel and set one. Rev 204 closes that: new PLAN_LIMITS.{tier}.defaultDailyCostCapUsdCents (free 50c / pro 500c / team 2000c) + a defaultCostCapCentsForTier(tier) helper seed a plan-tier default at workspace creation (both the Credentials-register and Google-OAuth ensureWorkspaceForUser paths). A brand-new desk literally cannot overspend on day one even if the operator never touches the cost-cap UI — the strongest possible flat-fee positioning signal against per-cycle-credits (Notion Custom Agents) and outcome-based (HubSpot Breeze) competitors. Fully operator-overridable + removable via the rev-20 integrations panel, which gains a 'Use plan default' one-tap re-apply affordance + a hint line naming the operator's plan-tier default. Existing workspaces are untouched — the seed fires only at creation, so a long-running desk that explicitly removed its cap stays uncapped. The pricing module (src/lib/pricing-plans.ts) projects the same figures via defaultDailyCostCapUsd + the caps.costCap display string so the /pricing caps block, the landing pricing block, and the rev-203 /api/v1/pricing endpoint never drift from the seeded cap — the concrete answer to the rev-202/203 'Higher daily cost cap' (Pro) / 'Highest daily cost cap' (Team) claim. The OpenAPI 3.1 spec types the defaultDailyCostCapUsd field on the /pricing response. Strategic significance: closes the pricing ↔ cost-guardrail loop the rev-202 /pricing page hinted at, and makes the flat-fee guarantee a structural default rather than an operator opt-in.
Two more onboarding templates — independent specialty fishing / outdoor outfitters + independent stationery / pen shops (cluster reaches 77 verticals)Closes the last two named rev-201 radar candidates. Independent specialty fishing / outdoor outfitters (owner-led specialty fishing shops + fly-fishing outfitters + outdoor guide services — 4 high-importance memory entries: named-license + named-permit currency on every guided trip + charter with a sub-policy on named-federal / named-tribal water, named-guide / named-charter continuity with a named-backup + named-warm-handoff on every confirmed multi-day booking, seasonal inventory turn with the named-buyer ordering window per season + an end-of-season liquidation markdown cadence, safety-incident hygiene with a same-day named-report + named-equipment quarantine on the water + a 3-in-90-days pattern threshold on any named-equipment line + 1 sample mid-season named-guide license-lapse signal). Independent stationery / pen shops (owner-led fine-stationery shops + fountain-pen retailers + writing-instrument specialists — 4 high-importance memory entries: named-supplier continuity on every allocation-limited pen + ink + paper line with a named-customer-waitlist on allocation-limited flagship releases, collectibles authentication on every vintage + limited-edition intake with a named-confidence threshold, named-nib-service continuity with a named-nibmeister-of-record + named-turnaround + condition photograph at intake, gifting-peak inventory cadence with the named-buyer ordering window per gifting peak + reserved named-engraving capacity + 1 sample pre-peak allocation-vs-waitlist signal). Two new OnboardingTemplateKey enum values (fishing_outfitter in hospitality-food, stationery_pen_shop in retail-ecommerce) extend the rev-19 enum without migration. The templates cluster is now 77 named verticals deep. The rev-172 listing endpoint count copy + OpenAPI 3.1 spec both read seventy-seven in lockstep. Strategic significance: closes the rev-201 named radar wave at two more underserved owner-led segments where named-relationship discipline (named-guides + named-charters on the outfitter side, allocation-limited named-suppliers + named-nibmeisters on the pen-shop side) is the load-bearing differentiator against generic chain operators.
FIX — activation 'Set a guardrail' step no longer auto-completes on the seeded default capThe rev-204 cost-cap seeding silently regressed the rev-165 activation checklist. The 'Set a guardrail' step's completion check was Boolean(dailyCostCapUsdCents || slackQuietHoursStart != null || timezone !== 'UTC') — but because rev 204 seeds a cost cap on every workspace at creation, dailyCostCapUsdCents is now always truthy, so the step auto-completed on cycle 1 and the nudge never surfaced for a single operator. That defeats the rev-165 intent: nudge new operators toward reviewing the desk's defensive / operator-respect controls explicitly rather than bumping into them. Rev 204 rekeys the check off a cost cap that DIFFERS from the plan default (defaultCostCapCentsForTier(planTier)) so the step completes only when the operator has actively tuned a guardrail — the tuned cap, Slack quiet hours, or a non-UTC timezone — not the inherited seeded value. The step copy is reframed to 'Review your guardrails' with an honest lede: 'Your desk already ships with a default daily cost cap, so it can't overspend on day one — that's the flat-fee promise, on by default. Make it yours.' Strategic significance: preserves the day-1 trust-signal nudge while acknowledging the rev-204 default. A genuine bug the unshipped cost-cap-seeding code introduced, caught and closed in the same rev it ships.
FIX + DESIGN — missing template keyword hints + flat-fee 'protected' chip on the today panel + landing top-line proof pointThree cleanups closing gaps the rev-204 primitives left open. (1) FIX: the rev-204 templates added fishing_outfitter + stationery_pen_shop to the enum + TEMPLATE_LAUNCH + TEMPLATE_CATEGORY_BY_KEY + the template data but forgot the TEMPLATE_KEYWORD_HINT entries — so both verticals rendered on /templates + /templates/[key] + the per-category archive without the per-vertical 'this is what this industry actually cares about' tagline chip every other vertical has carried since rev 195. Rev 204 adds both hints matching the templates' actual four-pillar seed content. (2) DESIGN: the today-panel Spend stat surfaced a set-but-zero-spend cap as the clinical '0% of $X cap'. Rev 204 makes it a reassuring brand-teal '🛡 $X/day cap · protected' chip at zero spend (with a cursor:help tooltip explaining the hard flat-fee ceiling) — the flat-fee promise made visible from cycle 1 — reverting to the percent-of-cap fact once spend starts. New .ld-today-cap-shield CSS in the rev-22+ design language with a tactile hover lift. (3) MARKETING: the landing pricing sub-copy now names the default-on hard cap as the 'No surprises' headline's concrete proof point — 'every plan ships with a hard daily cost cap turned on by default, so your desk literally cannot overspend — even under a flat fee' — surfacing the rev-204 thesis at the landing top-line where prospects evaluate against per-cycle-credit competitors. Strategic significance: the cumulative rev-by-rev visual-hierarchy discipline (every rev 22+ carries at least one piece of polish) reaches the today-panel Spend stat + landing pricing sub-copy, and the flat-fee differentiator is now visible across the landing page, the /pricing page, and the operator's daily dashboard glance.