Software Factory Intensive - Two-Day Practical Workshop for Software Engineers [AI Tinkerers - Seattle]
Cities (231) ▾

Software Factory Intensive - Two-Day Practical Workshop for Software Engineers

Apr
21
Tuesday
April 21st, 2026 • from 8AM (PDT)
Apr
22
Wednesday
April 22nd, 2026 • until 6PM (PDT)
Address Info
Available on RSVP acceptance

Event Ended

This event has already taken place.

Attendees 108+ registered
We’d love to have you join our attendees, who include engineering leaders and founders from Microsoft, Adobe, and Epic Games specializing in AI/ML, Python, and AWS, with some holding patents in network optimization and machine learning.

(Banner) A promotional banner for an event titled 'Software Factory Intensive' taking place in Seattle, organized by AI Tinkerers and hosted by Actual AI. Text: Sign up for the Software Factory Intensive April 21st – 22nd Seattle, WA In-person Event by AI TINKERERS | Hosted by Actual AI Modern, clean, and minimal with high-contrast typography. | Colors: #000000, #FFFFFF, #4ADE80, #60A5FA Note: The image is a digital graphic designed to promote an event, featuring a clear headline, event details in stylized containers, and organizational logos.

Build an AI-powered open-source Software Factory

Join AI Tinkerers and Actual AI for a hands-on, project-based workshop where you’ll learn how to build an AI-powered software factory, a pipeline of AI agents that can plan, architect, design, code, review, and deploy software around the clock.

This is not a lecture. You’ll bring your own project (or start a new one) and leave with a working system that can generate and improve production-ready software with minimal manual effort.

Speakers

(Banner) A promotional graphic on a black background introducing six male instructors with their circular portraits, names, titles, and company affiliations. Text: //SPEAKERS Meet the instructors John Kennedy Founder Actual AI Chris Sells AI Engineer GasCity David Miura Founding AI Engineer Actual AI Kevin S Lin AI Engineer OpenAI Klaus Bravenboer Founder Hack Humanity Caleb John AI Engineer PSL Modern, minimal, and clean with a dark mode aesthetic. | Colors: #000000, #FFFFFF, #2ECC71 Note: The image is a structured graphic design intended to introduce a group of people for an event or course, featuring headlines, portraits, and descriptive text in a layout typical of a website section or promotional slide.

Schedule

(Other) A digital graphic displaying a detailed two-day schedule for a 'Software Factory' workshop, organized into 'Day 1' and 'Day 2' columns. Text: SCHEDULE DAY 1 BREAKFAST 8:00 – 9:00 Coffee and light breakfast · Registration & check-in INTRODUCTION 9:00 – 9:30 The Future of Software Factories ORIENTATION 9:30 – 10:30 Factory Roadmap for Your Project WORKSHOP 10:30 – 11:30 Optimize the Individual AI Workflow LAB 11:30 – 12:30 Build a Structured Development Loop LUNCH 12:30 – 1:30 dietary needs accommodated WORKSHOP 1:30 – 2:15 Design the 6-Agent Software Factory LAB 2:15 – 3:30 Deploy Planner + Architect Agents BREAK 3:30 – 3:45 Help desk available LAB 3:45 – 5:00 Deploy Designer + Coder Agents WRAP-UP 5:00 – 5:30 Factory Checkpoint & Day 2 Preview DAY 2 BREAKFAST 8:00 – 9:00 Coffee and light breakfast · Help desk open INTRODUCTION 9:00 – 9:30 From AI Assistants to Autonomous Delivery Teams WORKSHOP 9:30 – 10:15 Architect Multi-Agent Coordination BREAK 10:15 – 10:30 Help desk available LAB 10:30 – 11:45 Deploy Reviewer + DevOps Agents WORKSHOP 11:45 – 12:30 Create Continuous Improvement Loops LUNCH 12:30 – 1:30 dietary needs accommodated CAPSTONE LAB 1:30 – 3:00 Run the Software Factory End-to-End BREAK 3:00 – 3:15 Help desk available TROUBLESHOOTING 3:15 – 4:15 Facilitator-led factory troubleshooting CLOSING 4:15 – 4:45 From Workshop to Real Operating Model Note: The image is a structured digital graphic or infographic representing an event itinerary, which is distinct from a photo, logo, or banner.

What You’ll Learn

Over two days, you’ll go from individual AI-assisted coding to orchestrating a full software factory:
  • Optimize your personal AI workflow for speed and accuracy
  • Deploy specialized agents for planning, coding, reviewing, and DevOps
  • Implement guardrails to ensure consistency and maintainability
  • Automate feedback loops to continuously improve your system

What You’ll Build

By the end of the workshop, you’ll have:
  • A working software factory tied to your codebase
  • A set of metadata repositories including architecture rules and context files to guide code generation
  • A workflow where agents can take a feature request → ship production code
  • A repeatable process for scaling development with AI

Workshop Plan

(Banner) A dark-themed infographic titled 'Build Your Agent Factory' outlining a four-step development pipeline for AI agents. Text: //WORKSHOP PLAN Build Your Agent Factory DEVELOPMENT PIPELINE STEP 01 Start a Project What do you want to build? Define your idea, goal, or problem. Your vision in plain language — what you want to build and why it matters. STEP 02 Project Manifest idea -> structured intent AI transforms your idea into a Project Manifest — goals, scope, constraints, roles, and success criteria. The living document that drives every factory decision. STEP 03 Software Factory Spec Project-specific SDLC blueprint Generated from your manifest, specific to your project. Maps the full SDLC: workflow stages, agent roles, coding standards, quality gates, and deployment rules. STEP 04 Building your Agent Factory CORE BUILD PHASE Agent Storage Metadata that operates the factory Test Cases Unit, integration & E2E test templates Perf Specs Performance benchmarks & SLAs Security Model Access controls, trust boundaries, guardrails Pricing Model Token budgets & API cost thresholds Agent Operation The structural blueprint for ongoing agent operation // ARCHITECT Rules for operation Set and update architectural rules // PLAN Work breakdown Create work packages for agents based on high level goals // DESIGN UX systems Create and update design systems. Deploy storybook demos. // VALIDATE Test Cases Validate acceptance criteria and build tests // BUILD Code Generate code using artifacts and continual test output // REVIEW Code Review Automated review — style, security, and spec compliance // DEPLOY Release Gate Quality gate — all checks must pass before shipping // IMPROVE Feedback Loop Runtime data feeds back into the spec and memory Modern, minimal, dark-mode UI design. | Colors: #000000, #22C55E, #818CF8, #FFFFFF Note: The image is a structured digital graphic designed for a presentation or educational purpose, featuring a clear layout, headlines, and instructional text.

Who This Is For

This workshop is designed for:
  • Software engineers exploring AI-native development
  • Tech leads and architects designing scalable systems
  • Engineering teams looking to increase velocity with AI
  • Builders who want to go beyond prompting and into process + systems

Format
  • 2-day, in-person workshop
  • Project-based: build a software factory custom to your own software project
  • Guided sessions + hands-on implementation
  • Direct support from experienced builders

Prerequisites
  • 5+ years of professional software development experience
  • A laptop with 16GB+ RAM capable of running Claude Desktop and a local dev environment
  • A Claude Code subscription (Max preferred)
  • A new software project concept you bring as the first deliverable for your Software Factory

Outcome

You won’t just learn about AI-assisted development-you’ll leave with a system that can build, review, and evolve software continuously.

Tickets
  • Regular Admission - $750
  • Group Tickets (for teams 5+) - $600

Once you register, you can use this link to pay for the training. Once you have paid, we will accept your registration:
Stripe Payment Link

Secure your spot and start building the future of software development.

Sponsors

(Banner) A dark banner section acknowledging a lunch sponsor, featuring the text 'SPONSORS' and 'LUNCH SPONSOR' above a logo for 'PSL'. Text: SPONSORS LUNCH SPONSOR PSL Minimalist and modern. | Colors: #000000, #B9C43E, #CCCCCC Note: The image functions as a promotional or informational section of a digital layout, specifically designed to recognize a sponsor.

FAQ

What will I build?

A production-ready software factory: a pipeline that takes a structured issue as input and executes planning, design, architecture, test generation, code generation, review, and deployment. The system is designed to run continuously and can be triggered programmatically.

What is a software factory (in this context)?

A software factory is a composition of specialized agents, each responsible for a stage in the development lifecycle. Agents communicate via structured artifacts (manifests, specs, tests, code) and operate under shared constraints defined in your factory configuration.

How is the system configured?

You’ll define your system via two generated artifacts: a Project Manifest (describes the product, domain, constraints, and goals) and a Factory Manifest (defines agent behavior, interfaces, and outputs). These are used to generate agent-specific configuration files that control execution across the pipeline.

What parts of the system do I control vs plug in?

You will customize six core agents: Planning, Design, Architecture, Testing, Code Review, and Deployment. For code generation, you can plug in your preferred coding agent (e.g., your existing LLM-based coding tool). This keeps the system flexible and allows you to swap in best-in-class generation models as they evolve.

How is the workshop structured?

Two days split into Workshops (live, guided sessions where an instructor presents from stage and everyone builds in parallel at the same pace) and Labs (hands-on sessions where you work at your own pace with facilitators available to unblock you). You’ll be working directly on your own project throughout.

How does this work for a solo developer vs a team?

The same system applies. For a solo developer, the factory acts as a force multiplier. For teams, it standardizes workflows, enforces architectural consistency, and reduces coordination overhead.

What frameworks or tooling are used?

The workshop is structured around Gas City (successor to Gas Town), along with supporting tooling for agent configuration, context management, and pipeline orchestration. The system is designed to be extensible and not tied to a single vendor.

Do I need to prepare anything beforehand?

Yes. Seven days before the workshop, you’ll receive a structured input form about your project. This is used to generate your initial manifests, so you start with a system already aligned to your codebase and requirements.

What does “continuous improvement” mean in this system?

The factory captures outputs (code quality, test results, review feedback, deployment outcomes) and feeds them back into the system to update prompts, constraints, and agent behavior over time.

How does the open source factory we build compare to tools like Gstack, Aider, OpenDevin, SWE-agent, Devika, OpenClaw, Continue.dev, Gstack, GasTown, Gas City, CrewAI, LangGraph, MetaGPT, etc?

Most of these tools solve a single layer of the problem:

  • Coding harnesses (Aider, SWE-agent, Devika, OpenDevin) focus on the edit → run → fix loop
  • Execution runtimes (Open Interpreter, OpenClaw, TinyClaw) focus on tool use and environment control
  • IDE interfaces (Continue.dev) focus on developer interaction
  • Starters / stacks (Gstack) provide opinionated project scaffolding
  • Orchestrators / multi-agent frameworks (GasTown, Gas City, AutoGen, CrewAI, LangGraph, MetaGPT) coordinate agents and workflows

The factory you build in this workshop sits one level above all of these.

It is a system that composes them:

  • You define the architecture of the pipeline (planning → design → architecture → test → code → review → deploy)
  • You encode behavior in manifests and context files (e.g. soul.md)
  • You plug in any coding harness or model you want
  • You run it as a continuous, end-to-end system, not a single agent loop

Contact Organizers

Questions? We're here to help.

Events Gallery FAQ Sponsor