A note on this post. This is an engineering retrospective, first published in August 2025. The visual agent-workflow builder described below was a prototype from that period — it is not part of the ProvenMap product today, and nothing here describes a feature you can use. We are keeping the post up because the type-safety and composition problems it works through are still interesting, and the lessons shaped what we did build. For what the product actually does now, start here.
A visual orchestration tool that generated type-safe agentic workflows — and what building it taught us.
We wanted to democratize AI workflow creation for software architects, business teams and other stakeholders, in the context of providing architectural understanding and automating the more mundane tasks around it. The premise was that users should be able to compose agents that understood their specific domain — either generated automatically as they worked, or assembled visually when they needed something bespoke.
"The challenge? Different teams need different ways of extracting architectural understanding. Some might want to monitor discussion channels and diagrammatically depict the outcome. Others research markets and adapt architecture to respond. Or assess technical debt."
The prototype generated agents on the fly as a workspace was set up, hydrating it with purpose-built agents based on context. Where automatic generation could not resolve something, the builder let you step in and edit the flow directly, then evaluate it — in the most type-safe way we could manage.
On deploy, the visual workflow compiled into a LangGraph graph executed on our Node.js backend. The builder validated input/output types for each node, inferred schemas when integrating dynamic APIs, and handled MCP-compatible tool integration.
The technical layer underneath this is described in detail in the companion post on type-safe LangGraph workflows.
These were the workflows we designed for. They are illustrative of the prototype's intent, not capabilities of the current product.
Agents that parsed team conversations, extracted decisions, and drew the evolution of architectural thinking — including spotting when a new decision contradicted an earlier one.
Agents that monitored industry patterns and technology adoption, then suggested architectural responses.
Agents that analysed codebases, tracked dependency health, and prioritised debt reduction by its actual drag on delivery.
Visual composition is seductive, and the type-safety work behind it was genuinely valuable — that layer survives in the product today. But the builder asked users to think about how to assemble an agent before they had any answer to the simpler question: what is actually in my system, and what will this change break?
That turned out to be the more valuable problem, and it is the one ProvenMap solves now. The workflow builder was the right engineering, aimed one step too far ahead of where teams actually are.
Get the latest insights on architectural intelligence and platform updates.
Madhuri Ganta is a frontend developer at ProvenMap, building user interfaces with React and Next.js. She also works on cloud infrastructure using AWS CDK.
3 min read
Code preserves what was built. It does not preserve why. AI coding agents make this gap worse, not better - they read the artifact and not the input. The fix is not better diagrams or longer system prompts. It is keeping the reasoning alive next to the code it explains.
6 min read
Sequoia Capital identifies a $10 trillion services automation opportunity, but calls this the "steam engine moment"—the foundational AI technology exists, but we're still decades from systematic deployment. Early agent-first implementations show 40-85% efficiency gains, yet success requires architectural expertise concentrated among technical specialists. The companies that democratize this knowledge—making agent system design as accessible as ChatGPT—will become the Westinghouse of the cognitive revolution.
8 min read
How we built type safety, human-AI collaboration, and visual workflow authoring by putting an explicit input/output resolution layer on top of LangGraph's state annotations — and the patterns that made composable, type-safe workflows possible.