Agent-development infrastructure
Flowplane
A workflow engine for AI-assisted software development with isolated execution, durable work tracking, and persistent knowledge.
- Audience
- AI-assisted developers and technical teams
- Role
- Architect and principal builder
The problem
Autonomous development needed stronger boundaries and memory.
Long-running coding work required more than a prompt loop. Teams needed explicit workflows, isolated execution, durable plans, and knowledge that could distinguish decisions, patterns, lessons, and superseded context.
The leadership response
A workflow engine joined orchestration, isolation, and knowledge.
I built a substantial Go system combining an agent runtime, pluggable workflow engine, durable work tracking, SQLite and FTS5 knowledge, Git worktrees, Docker isolation, and a terminal interface. Decisions and lessons could be searched, related, and superseded as the work evolved.
Evidence register
What this case can—and cannot—prove.
Public evidence is classified so a private implementation, deployed system, measured result, and advisory artifact are never presented as equivalents.
- Implemented private system
- A working Go implementation confirms the runtime, workflow, knowledge, isolation, and terminal architecture.
Outcomes and decisions
The result was a change in operating capacity.
These outcomes describe what the implementation made possible. They are not generic product promises.
Created an end-to-end operating surface for AI-assisted development workflows.
Isolated execution from the host environment while preserving work state.
Retained decisions, patterns, learnings, context, and plans for future sessions.
System design and sequence
The architecture followed the operating need.
The system was organized around an operating sequence people could understand, govern, and improve.
Orchestrate
Coordinate work as explicit, durable workflows.
Isolate
Run implementation inside controlled container boundaries.
Track
Keep plans and work state visible through execution.
Learn
Preserve and evolve the knowledge produced by the work.
Method connection
Where this case exercised the operating method.
Not every case uses every movement. These are the parts that materially shaped the work.
- Design
- Decide
- Execute
- Transfer
- Measure
My contribution
I built Flowplane as infrastructure for responsible autonomy.
The architecture reflects a consistent principle in my work: give agents enough structure to move quickly while keeping execution, evidence, and decisions understandable to people.
Return to all projects