Skip to content

Workflows Overview

TL;DR: Sam runs five distinct workflow types simultaneously in a single agent, leading to context collision, memory pressure, and scheduling conflicts. Each workflow is complex enough to be its own specialized agent.

Sam's Five Core Workflows

                    [John / Slack]

                    [Sam — Single Agent]

         ┌───────────────┼───────────────────┐
         │               │                   │
  ┌──────▼─────┐  ┌──────▼──────┐  ┌────────▼────────┐
  │   Funnel   │  │  Creative   │  │ Braze / Prospect │
  │ Monitoring │  │  Pipeline   │  │   Operations     │
  └──────┬─────┘  └──────┬──────┘  └────────┬────────┘
         │               │                   │
  ┌──────▼─────┐  ┌──────▼──────┐
  │  GitHub    │  │  Reporting  │
  │ Monitoring │  │  Cadence    │
  └────────────┘  └─────────────┘
WorkflowFrequencyIntegrationsOutput
Funnel Monitoring3×/dayPostHogsam-chat updates, DM on shifts
Creative PipelineAd hocHiggsfield, Shotstack, Google DriveCreative briefs, scripts, hooks
Braze OperationsWeekly audits + ad hocBrazeAudit reports, gap analyses
GitHub MonitoringEvery 30min (cron) + 3×/day (heartbeat)GitHub APIfunnel-changes.md, alerts
Reporting Cadence3×/day heartbeatPostHog, Looker, BrazeSlack channel posts

The Overload Problem

All five workflows run inside the same agent context. Problems this causes:

Context Collision:

  • A creative brief request arrives mid-heartbeat
  • The agent finishes the heartbeat task but now has partial funnel data + partial creative context
  • Memory from one task bleeds into the next

Schedule Conflict:

  • GitHub monitoring runs via cron (30min) AND heartbeat (3×/day)
  • Heartbeat combines funnel check + GitHub check + Slack monitoring + test tracking
  • At the 3×/day windows, the agent is trying to do 4 things simultaneously

Memory Pressure:

  • Long creative sessions (micro-bucket maps, creative briefs) use large chunks of context
  • Subsequent heartbeat sessions start with less available context
  • MEMORY.md (419 lines) must be loaded every main session

Error Propagation:

  • Loop incident (March 17): heartbeat near auto-compaction, context trimmed, tasks repeated ~100 times
  • Cron timeout: GitHub check hitting 90s limit consistently
  • Format bug: tool_call XML leaking into John's Slack messages

What Proper Decomposition Looks Like

Each workflow maps to a dedicated agent:

WorkflowBecomesWhy Separate
Funnel MonitoringFunnel AgentNeeds deep Sanity + PostHog access, no creative context
Creative PipelineCreative AgentGPU-heavy tasks, different model needs, separate approval flow
Braze OperationsProspect AgentEmail/SMS domain knowledge, not shared with analytics
GitHub MonitoringFunnel Agent (or cron-only)Code monitoring belongs with funnel changes
ReportingData AgentDedicated to aggregating and reporting metrics

Navigate to each workflow for detailed analysis:

FuturHealth Internal — Confidential