Ephemerals

Ephemerals turns every Git branch into a disposable, agent-ready cloud machine, which lets agencies bill per developer seat at $10 per user per month plus metered compute instead of vague project fees. Because each environment auto-reaps on merge and secrets vanish with it, agencies can promise clients isolated, secure parallel AI development without local resource fights or credential leaks, a differentiator that manual setups cannot match.

Ephemerals lets agencies resell disposable cloud dev environments per Git branch, each running Claude Code. The margin model hinges on the $10/seat/month fee plus metered compute at $0.18 per 2 vCPU/4 GB hour, with heavier add-ons at $1.44 per 16 vCPU/32 GB hour. An agency can charge clients a flat retainer, say $2,500 for a 20-hour setup, then a per-developer monthly fee that covers seat costs and a buffer for compute. Since Ephemerals does not proxy Claude API tokens, the agency must separately bill for agent usage, which can erode margins if not tracked. The model works best when clients run parallel agent-assisted tasks across branches, maximizing the value of isolated environments. Agencies should monitor compute per branch to set retainer tiers that keep margins above 30%.

AI code tools compress the cost of producing a first working version, but they do not compress the cost of owning it. The Scaffold Versus Steward Split separates two jobs agencies have historically billed as one: scaffolding (generating a full-stack app, wiring auth and payments, standing up a prototype) and stewardship (architecture decisions, review, and keeping consumer code in sync when contracts change). Scaffolding is where the speed advantage lives. Stewardship is where retainer value and liability live. Verdent illustrates the first half, turning a plain-English description into a working product with authentication, payments, and an admin dashboard. Ripple illustrates the second, detecting a breaking API change and opening pull requests across every affected repository. Agencies that price both halves at the same rate give away the margin on scaffolding and undercharge for stewardship. Split the two in your statements of work, and staff them differently.

The Agent Output Liability Line is the boundary between code an agency can ship under its own name and code that still needs a human signature. Agentic tools now generate full-stack applications from prompts and auto-fix breaking API changes across repositories, which moves the liability question from 'did we write it' to 'who reviewed it.' Agencies that blur this line absorb client risk without pricing it. A practical test: if an agent opens a pull request at 2am and no human reads the diff before merge, that code sits above the line and belongs in a maintenance retainer, not a fixed-scope build. Tools like Agent Monitor and Agent Desk exist specifically to make that review boundary visible by surfacing per-file risk levels and session histories. The framework matters because delivery speed without a defined liability line converts margin into unpaid warranty work.

Adopt Ephemerals only if your agency can manage separate Claude billing per client and your parallel branch workload justifies the per-second compute costs.

Set a hard blast-radius limit per agent run, then require a named human reviewer before any change merges into a client branch.

IF your agency runs parallel agent-assisted development across multiple client repos and needs isolated, disposable environments per Git branch, THEN Ephemerals at $10 per user per month plus $0.18 per 2 vCPU / 4 GB hour is a cost-effective fit. IF you require white-labeling or unified billing for Claude API usage, THEN skip because client-facing surfaces show Ephemerals branding and you must manage Claude subscriptions separately.

A structured sprint to onboard a client onto Ephemerals, configuring per-branch cloud environments with Claude Code, and establishing a repeatable delivery workflow for parallel agent-assisted development.