Running imza as a service, AI Code Tools

imza Agency Implementation, Delivering AI-Assisted Code Projects

Learn how to integrate imza's Plan-Build-Review loop into your agency workflow to deliver custom code projects faster while keeping clients in control of scope. This course covers setting up the terminal agent, configuring MCP integrations for GitHub and Linear, structuring client handoffs through diff reviews, and packaging AI-assisted development as a productized service with predictable timelines.

Open the decision record for imza

What does running imza for clients commit you to?

Published figures for this service. Blank fields are not published.

Monthly tool cost
Not published, imza is open-source with no vendor plan price; the agency must budget engineering labor and model-endpoint usage separately.
Time to first value
Not published
Payback
Not modeled, client price, labor cost, model-endpoint usage, overhead, and expected volume are not supplied.
Guided implementation
8 hours

Is imza worth running as a client service?

The evidence supports a small-footprint, open-source terminal agent with an explicit Plan-Build-Review loop, sandboxed Lua execution, and MCP integrations, suited to agencies with in-house engineering. What remains unknown is the client fee, labor cost, and model-endpoint usage needed to model ROI.

An agency-fit judgement for reselling this service. It is separate from the tool description on the decision record.

Before you start

What has to be in place before the first client engagement.

Tools and subscriptions

  • imza native binary (open-source, no vendor fee)
  • OpenAI-compatible or Anthropic model endpoint (local, API, or subscription)
  • Client repository checked out locally for the agent to explore and edit
  • MCP server credentials for GitHub, Linear, Slack, Notion, Stripe, Figma, or Sentry as needed
  • Project instruction files defining guidelines and skills for AI review

People and inputs

  • Developer workstation capable of running the ~20 MB native binary with fast startup
  • Engineer familiar with terminal workflows and diff review
  • Written review-gate policy covering workspace-mutating actions and permission gating
  • Access to a sandboxed Lua execution environment for batching multi-step operations

Included with the course

7 working documents for delivering this service.

  • imza Project Setup Checklist for Agencieschecklist
  • Client Handoff Template: Plan Review and Diff Approvaltemplate
  • MCP Integration SOP: GitHub, Linear, and Slack Connectorssop
  • Scope Control Worksheet: Plan Editing Before Build Executionworksheet
  • Sandboxed Lua Batching Guide for Multi-Step Operationsguide
  • Productized Service Pricing Model: AI-Assisted Development Retainerstemplate
  • CI Automation Runbook: Headless Plan and Build Turnssop

Listed by name. These documents are not yet published as individual downloads.