> For the complete documentation index, see [llms.txt](https://www.conserver.io/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://www.conserver.io/thinking-in-vcon/the-keynote.md). # The Keynote {% embed url="" %} Thinking in vCon — the keynote, in one sitting. 17:55. ### The argument Documents have files. Images have files. Spreadsheets have files. Conversations never got one. A call lives as a recording in one vendor's storage, a transcript in a second system, a summary in a third, and a few notes typed into a CRM by whoever happened to be on the line. Nothing binds those pieces together and nothing certifies that they belong to each other. The talk argues that this is not a small gap in tooling. It is the reason conversations are hard to govern, hard to audit, and hard to move between systems. Every integration re-derives what the conversation was, and every re-derivation is another chance for the record to drift from what actually happened. vCon closes that gap by giving a conversation what every other kind of content already has: a defined container. Parties, dialog, recordings, transcripts, analysis, and rights sit together in one signed object that can be handed from system to system without losing its meaning or its provenance. ### Why the gap matters now AI raises the stakes. Models are trained on conversations, agents act on them, and analytics pipelines make decisions from them. When the underlying record has no fixed shape and carries no permissions of its own, basic questions have no reliable answer: who agreed to what, which transcript a summary came from, whether a recording has been altered since it was captured. A conversation with a standard format is a conversation you can reason about. Consent becomes checkable rather than assumed. Provenance becomes verifiable rather than asserted. And the conversation becomes portable — something the parties to it can actually hold, instead of a byproduct locked inside whatever platform happened to capture it. ### What the talk covers * Why documents, images, and spreadsheets all got file formats while conversations never did * What a conversation actually contains once you write it down honestly: parties, dialog, recordings, transcripts, analysis, and rights * How signing and provenance turn a scattered pile of artifacts into a record a recipient can check * What changes for governance, compliance, portability, and AI once the container is standard ### Watch and share * [Thinking in vCon — full talk on YouTube](https://www.youtube.com/watch?v=YDh0phRx0bM) * [Thinking in vCon playlist on YouTube](https://www.youtube.com/playlist?list=PLaxNQ-GrpFLc) * [conserver channel on YouTube](https://www.youtube.com/@conserverio) ### Go deeper * [Privacy](/thinking-in-vcon/thinking-in-vcon-privacy.md) * [The Conversational Graph](/thinking-in-vcon/the-conversational-graph.md) * [Why Conversations Need a File](/vcons/why-vcons.md) * [A vCon Primer](/vcons/a-vcon-primer.md) --- # Agent Instructions This documentation is published with GitBook. GitBook is the documentation platform designed so that both humans and AI agents can read, navigate, and reason over technical content effectively. Learn more at gitbook.com. ## Querying This Documentation If you need additional information that is not directly available in this page, you can query the documentation dynamically by asking a question. Perform an HTTP GET request on the current page URL with the `ask` query parameter, and the optional `goal` query parameter: ``` GET https://www.conserver.io/thinking-in-vcon/the-keynote.md?ask=&goal= ``` `ask` is the immediate question: it should be specific, self-contained, and written in natural language. `goal` is optional and describes the broader end goal you are ultimately trying to accomplish on behalf of the user. GitBook uses it to tailor the answer towards what is most useful for that goal. The response will contain a direct answer to the question and relevant excerpts and sources from the documentation. Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.