Ninety days to first revenue and a funnel that compounds.
The 90-day job is not launching a business — it's building the three assets that unlock 2027: a paying client + case study, a live funnel, and a metering skeleton.
01 /
Month 1 — Package & polish
july
Weeks 1–4
Goal: a sellable offer and an install experience that doesn't leak users.
Write the productized offer — "orchestration setup + 3 custom workflows, $500–$2K fixed" — and put it on the landing page with a booking link.avenue 1 · the only near-term cash
Add the Claude Code one-liner install to the README top (claude mcp add … npx).2026 install norm — competitors all meet it
Turn on GitHub Sponsors + FUNDING.yml; open a Polar account.avenue 5 · free trust signal
Submit to directories: Anthropic Connectors, Smithery, Glama, PulseMCP, mcp.so — freemium posture.avenue 4 · pure distribution
02 /
Month 2 — Funnel & first client
august
Weeks 5–8
Goal: one paying engagement, one Pro-tier gate live.
Land 1–2 service clients — direct outreach to teams adopting MCP; the offer is already public.avenue 1 · $1K–5K
Build the usage-analytics dashboard (real token capture, per-provider spend) and gate it as the Polar Pro tier.avenue 2 · the credibly-wanted gate; also a product differentiator
Publish 2 free pieces on the jury/council protocols and zero-cost local jurors.avenue 6 · top-of-funnel for everything
Add a CLA note to CONTRIBUTING to keep sole copyright → dual-license optionality.avenue 9 · preserve the AGPL moat
03 /
Month 3 — Skeleton & proof
september
Weeks 9–13
Goal: the metering loop works end-to-end; the case study is public.
Publish the client case study on the landing page.converts the next client at higher price
Stand up the hosted-tier skeleton: thin managed deploy, holds keys, meters margin over OpenRouter, billed via the same Polar sub. No public launch — steps and platform pick on the Cloud & Hosting tab.avenue 3 · proves the 2027 margin loop · no AWS needed
Wire the budget cap into live calls (cost-monitor exists, unwired) and expose spend in usage_stats.trust feature BYOK users need before they'll ever hand you keys
Review the funnel numbers and decide Q4: double down on services vs. push hosted beta.decision gate, not a guess