When agents start reading your work chats, what happens to the enterprise knowledge base?
Conversation is context, and context is knowledge. Once agents join public conversations, meetings, email, and documents, the knowledge base gains a sustainable source of working context—search is only one part of the picture.
- Conversation is context, and context is knowledge.
Anthropic recently published a conversation with Slack's chief product officer, Jaime DeLanghe, about a persistent problem in enterprise knowledge management. Companies generate enormous amounts of chat, meetings, and documents every day, yet the moment someone needs specific context, teams still have to explain everything from the beginning.
DeLanghe joined Slack in 2017, initially leading search and machine learning. Her mandate was to turn workplace conversations into reusable institutional knowledge. After years of research, Slack reached a sobering conclusion: conversations don't automatically become knowledge just because they're saved. Even as messages pile up, people still repeat meetings, re-explain decisions, and hunt for the reasoning behind past choices.
Agents are reviving this long-unfulfilled promise. The shift happens when an Agent enters the work site: it reads public daily conversations, connects meetings, emails, calendars, and documents, reconstructs why a decision was made and what conditions changed afterward, then moves on to the next task.
This workflow has a clean division of labor. Public communication provides the raw material, the Agent restores context, and humans handle judgment and course correction. The enterprise knowledge base is evolving from a repository of saved results into something embedded in daily workflow.
Conversation is context, and context is knowledge
Tap each practice to see which knowledge gap it addresses.
Key moveKeep non-sensitive daily discussion and decisions in shared team spaces.
What the agent gainsSees the discussion that shaped a decision, plus the final file.
What the team losesLess repeated explanation; genuinely sensitive content still gets deliberately isolated.
Key moveAsk both why the decision was made and what changed afterward.
What the agent gainsGets the rationale, dissenting views, trade-offs, and later new conditions.
What the team losesFewer outdated decisions treated as current answers.
Key moveConnect chat, meetings, email, calendar, and documents.
What the agent gainsSees a continuous timeline of one topic across tools.
What the team losesLess context re-explained when people or tools change.
Key moveGive the agent clear goals, responsibilities, tools, permissions, and delivery standards.
What the agent gainsKnows what it owns and when it must hand back to a human.
What the team losesFewer chat windows that answer everything but answer for nothing.
Key moveAgents draft, summarize, monitor, and prep; humans review, prioritize, decide, and correct.
What the agent gainsActs on the human's judgment and returns results to the shared space.
What the team losesHumans stop doing all the groundwork; agents stop making final calls.
There's already enough material; what teams lack is context they don't have to re-explain
Enterprise knowledge bases have traditionally grown by collecting documents, proposals, slide decks, and meeting notes. With AI, these formal artifacts can be produced faster and in greater volume than ever.
But more archivable material doesn't equal more usable knowledge. A flawless document nobody reads doesn't gain value from better formatting. A summary that accurately records a pointless meeting doesn't make that meeting necessary. AI can lower the cost of producing work artifacts, but it can't automate the genuinely hard parts of knowledge work: spotting problems, changing assumptions, resolving disagreements, and getting a group of people to understand why they should do something next.
If teams still need to reconvene and re-explain whenever they need background, the knowledge base has only accumulated more files—it hasn't closed the knowledge gap. Once Agents read workplace conversations, the metric changes too. The old question was "how much have we stored?" The new question is "can we recover the full story of how things came to be?"
What do conversations capture that documents don't?
Knowledge management has always favored formal outputs. Documents are stable, tidy, and easy to archive. Chat, by contrast, felt like exhaust from the work process—messy, redundant, and not worth preserving.
DeLanghe thinks that hierarchy is backwards. A product brief looks substantial, but it usually preserves only the conclusion at a single moment in time. What actually changed the direction may have happened outside it: an engineer pushing back on an unrealistic timeline, a client call overturning an assumption, an argument that redefined the problem, or someone killing bad ideas before they ever made it into the document.
Documents are receipts left behind after understanding has formed. Conversations preserve how that understanding actually took shape: who raised objections, what evidence shifted, what the team abandoned, and where trust was built or broken. They contain contradictions, timestamps, and organizational intent. They're harder to organize than the final product—and much closer to the real texture of knowledge work.
Formal documents still matter. Contracts, specifications, stable facts, and final decisions need clear records. But the basic unit of the knowledge base has expanded from a single file to a time-ordered arc of context: the conclusion, its rationale, the objections, the trade-offs, and the conditions that shifted later. Agents can now bring that formative process—previously shut out of documents—back into current judgment.
Agents must recover conclusions, reasons, and changes
If an Agent only pulls "the final decision" out of chat logs, it's still doing something close to keyword search—just with more fluent answers.