← back
Beyond Conversation: Why Documents Transform Natural Language into Code - Filip Kozera
Takeaway
Move from chat to documents-as-specs to repeatable background agents triggered by emails/meetings — human role becomes Tinder-style swipe-approve.
Summary
- Filip Kozera (Wordware CEO) argues chat is fundamentally broken for serious work: context pollution, concurrency-of-one, no version control, no logical nesting, no reusability, model laziness as context grows.
- Documents are humanity's oldest spec format (PRDs trace to ~Noah's-Ark era); they force clarity and structured iteration in a way chat never can.
- Background agents (Manus, Deep Research) let work happen async; triggered by emails/Slack/meetings (e.g., post-investor-meeting CRM update); future agents will manage other humans (filing Jira tickets).
- Calls for richer communication protocols beyond MCP — MCP lacks constraint specs, authority levels, and approval-required flags for human-in-the-loop.
- Predicts coding is the leading edge: IC engineers who can also manage interns/agents extract leverage; pure ICs with high taste bar often refuse AI tools.
documentsbackground-agentsworkflow
Original description
Natural language is quickly becoming our most powerful programming abstraction, perfectly suited to capture the inherent fuzziness and complexity of real-world problems. But despite the power of AI chatbots, endlessly brainstorming in conversational interfaces rarely leads to clarity or reliable results. This session explores how structured, document-based natural language is uniquely positioned as the ultimate interface for humans to precisely describe complex systems. We'll discuss why conversational interfaces often fail at forcing clarity, and how shifting to a document-driven model ensures that humans articulate their intent clearly and rigorously. Attendees will learn: Why natural language (not code) is the most intuitive way to describe complex systems How documents inherently force clarity, rigor, and structured thinking compared to chatbots Real-world examples of document-based programming for building reliable, deployable AI systems Practical insights into transitioning from conversational brainstorming to structured document-driven workflows