Budget Pacer
Reallocates daily budgets across your portfolios using fitted saturation curves. Operates within velocity caps and budget locks you set.
Runs on mathAllocate budget, set targets, and optimise autonomously across Google, Microsoft and Meta. Powered by a powerful statistical engine that understands marginal ROAS and platform nuances. Every decision explained in plain English, every push traceable. Control everything via MCP with your LLM of choice, if you like.
New · GA4, Shopify and HubSpot revenue routingLink Google, Microsoft and Meta Ads in one OAuth flow. ROASt pulls campaigns, budgets, and conversion actions automatically — no CSVs, no API keys, no manual setup. Connect GA4, Shopify, Hubspot and ROASt will automatically attribute your conversion goals to your campaigns.
ROASt scans every account on connect and auto-fixes broken conversion setups. Anything it can’t fix gets flagged for review with a one-click resolve.
The Strategic Mix Allocator fits Hill response curves per platform. Given a total budget, what is the optimal spend distribution? These efficiency curves power the live daily allocator.
Marginal-ROAS scoring redistributes campaign budgets every night within portfolios to maximise performance against your chosen goals, whether those are platform defaults or direct from your CRM/Shopify.
Approved changes flow back to Google, Microsoft and Meta via their APIs daily, or even intra-day for fast-moving campaigns. No copy-paste, no spreadsheet exports, no manual edits, no worries.
Each push is observed against actual outcomes. The engine’s confidence in your portfolios compound with every cycle.
Nine specialists working on your account in the background. Three Optimisers act on it, three Watchers alert you to changes, two Analysts make sense of the data — plus a Generalist you can talk to in plain English. Powered by Claude where it helps. Deterministic math and statistics everywhere else. Take things to the next level with full read/write MCP integration.
Some teammates act on your account. Some watch for changes. Some explain the numbers. Flume is your generalist assistant that can do everything else. Just ask for performance/pacing reports, find out what needs attention today or even just ask how to get started.
Reallocates daily budgets across your portfolios using fitted saturation curves. Operates within velocity caps and budget locks you set.
Runs on mathScans search terms weekly. Proposes negative keywords and keyword pauses. Close-rate aware when HubSpot or Shopify is connected.
Runs on math + ClaudeSpots fatigued ads across Google RSA, PMax, and Meta. Sibling-count guards so a campaign never loses its last working asset.
Runs on math + ClaudeFlags portfolios drifting off their monthly spend pace. 15% off-pace triggers a daily digest.
Runs on mathSpots when a competitor enters or leaves your auction. Writes notes the team can use later to explain ROAS shifts.
Runs on mathSurfaces tracking gaps, broken UTMs, and revenue divergence between platforms.
Runs on mathRe-fits saturation curves nightly. Grades the engine’s predictions against actuals.
Runs on mathWrites your weekly brief and daily mini-brief — narrates what each agent did this week, in plain English.
Runs on ClaudeFlume is your every-day assistant. Ask it to generate beautiful reports, to take action on your portfolios, or what you should focus on today. Includes full MCP integration for unlimited interaction.
Runs on Claude + MCPUpload your landing pages, brand briefs, dated promos, and client notes. When an anomaly lands, ROASt cross-references the drop against everything it knows — events, platform changes, creative refreshes, URL shifts — and writes a one-paragraph narrative to explain it.
The narrative points at the exact document and date — no guessing which change caused the dip.
Every Monday at 7am client-local: KPIs, what changed, what to act on. One page, ready to forward.
Connect Claude, ChatGPT, Gemini, or any MCP client to ROASt’s read/write tools to take your understanding to the next level.
The engine is pure math and modelling, no LLM involvement - which is how it should be. Platform adaptors are trained on platform behaviour and apply nuance and safeguarding to campaign scoring.
The widest auction surface, with the most learning-phase quirks. Search, Performance Max, and Shopping each get their own ceiling.
Native learning stages, dwell windows, and creative cycles — respected in their own language, not papered over.
Smaller auction volume means more caution, more compounding, and a harder watch on budget that isn’t spending.