Work5 shipped · 3 in progress
Case studies.
Applied AI, business-systems, and workflow case studies from systems I owned end to end. Counts and claims are traced to code; anything the source could not reproduce is labeled as self-reported on the page itself.
CoHost AI Studio AI automation Nothing publishes until it clears the gate. 
Throughline Revenue systems backbone One connector interface, every system in sync. Manifest CRM data pipeline Every record accounted for on the way into one identity layer. 
Meter Billing automation Intermedia usage, billed straight into ConnectWise. 
EnrichCRM Applied AI enrichment CSV in, enriched contacts out, at a fraction of the cost. 
Synapse Client intelligence system Where scattered business data becomes client intelligence. 
Foreman AI tooling Keeps your AI coding sessions alive and restarts the ones that hang. 
Tether Internal tools Run your dev ops from your phone. Live demos.
You can open these right now without a login. Each one runs on a real server-side backend — live DNS, data import, deterministic analysis — against a synthetic sample or your own input. The fleet operations layer pings all 7 backends from your browser and shows the CI and drift checks that keep the proof honest.
RevOps Software Factory Featured Real multi-agent backend Applied AI · RevOps Multi-agent review for synthetic revenue data. A coordinator dispatches specialist agents (dedup, attribution, stage-logic, enrichment) over a synthetic HubSpot batch, fuses their findings, and returns one approval-biased verdict with a live token-cost ledger. Risk-scaled compute, model tiering, and a cache + budget guard make the live backend safe and cheap. (Synthetic data, not a live CRM.) 
Q2See Featured Real import backend Revenue systems Inspect a quote-to-cash flow record by record. Import your own quote-to-cash export and the backend parses it server-side into one quote→contract→invoice→renewal flow, flagging the broken handoff before revenue leaks. (A point-in-time export, not a live CRM connection.) 
Apexlint Featured Real linter backend AI ops-code review Deterministic review for Apex, Flow, and n8n changes. Deterministic lint of agent-generated Apex / Flow / n8n before it hits production — SOQL-in-loop, missing bulkification, no error handling. 
Tracewell Featured Real analysis backend AI observability Inspect a failed agent run step by step. Reads a failed agent run down to the token — tool-call timeline, cost per node, the prompt regression that caused it. 
Funnelguard Real linter backend RevOps / lifecycle Check funnel configuration before attribution drifts. Catches the broken UTM, the orphaned form, the lifecycle-stage contradiction before they corrupt the funnel. 
Forager Real import backend AI-native proof Turn resolved Slack threads into a queryable knowledge base. Upload a real Slack export and the backend harvests resolved threads into a queryable, confidence-scored knowledge base server-side. (MCP panel shows the tool contract — a simulation, not a live MCP server.) 
Inboxward Live DNS backend GTM / RevOps Check sending domains and see where deliverability risk is building. Runs live SPF / DKIM / DMARC inspection on any domain you enter, then layers synthetic-fleet blacklist and inbox-placement scenarios with auto-prioritized remediation.