Knowledge Management

The biggest hurdle for AI is not the user's skill level, but the agent's access to necessary context and data. The ability to connect to and process information from diverse, non-standard sources (like government paperwork or internal documents) is the key differentiator.

AI's greatest impact is seen when individual power users build automated processes (e.g., creating a 'chat site' for a financial model) that can then be adopted by the entire team, moving beyond personal productivity gains.

AI is enabling the creation of new 'AI-native artifacts' (like interactive sites) that allow non-technical users to express complex needs that traditional formats (PDFs, spreadsheets) cannot support, filling a gap in knowledge work.

As agents become more powerful, the user experience must evolve to support fluid, bidirectional interaction—allowing users to interrupt, interject, or guide the agent's run in real-time, rather than just relying on a single question-response cycle.

Current single-player AI chats force users into a 'context task' workflow (e.g., copying code from GitHub to Claude, then pasting it to Slack). Multiplayer agents allow co-workers to interact with the same agent session simultaneously, eliminating this friction.

1. **Refuse to Copy and Paste:** Agents must live directly next to the work surface (e.g., in Notion or GitHub) rather than within a separate chat window. The agent must access all tools available to the human team. 2. **Work with the Door Open:** Collaboration requires open learning, where best practices and insights are shared publicly, accelerating collective knowledge gain (analogous to Shopify's 'River' system). 3. **Continuously Improve:** Learning from successful prompts or complex iterations should be automatically codified as a skill for the agent. 4. **People are not Routers; Agents are:** Humans must focus on high-value activities, while agents handle routing and answering repetitive project update questions. 5. **Nothing Starts from Scratch:** The entire agent session that generated an artifact (document, PR) must persist in the cloud to ensure continuity for team members.

AI agents must reside entirely in the cloud and be managed by a robust boundary. This is crucial because local/laptop agents are insecure, cannot be preserved long-term, and prevent team access. Furthermore, strict governance (a 'black box' record) is required to track what data an agent accesses and which users interact with it.

The development loop involves Brainstorming $\rightarrow$ Planning $\rightarrow$ Working $\rightarrow$ Reviewing $\rightarrow$ Polishing $\rightarrow$ Compounding. The human must be 'brain-on' at both the start (defining the problem) and the end (raising the bar/taste).

Allocate 50% of time to building the feature and 50% to teaching the system what it did wrong or how it can learn. This knowledge extraction is crucial for long-term efficiency.

Storing solutions and learnings within a repository (compounding) makes future interactions more token-efficient because the AI does not need to perform deep research or correction passes; the solution is already embedded.

The goal of Compound Engineering is that each shipped feature makes the next one easier, counteracting the typical accumulation of complexity in software development.

Code churn is high (861%), leading to increased bottlenecks at the review stage. Currently, over 30% of changes merge without any review, and even when AI reviews are used, human involvement often reduces to skimming rather than deep reading.

Code review's most critical function is not just catching bugs (semantic accuracy), but facilitating knowledge sharing, mentorship, and architectural alignment. This 'alignment' aspect must survive the shift to automated development.

Instead of reviewing code diffs, the review surface should become a verification of 'intent' and 'evidence.' This is achieved by capturing user decisions from development sessions, converting them into acceptance criteria, and generating a test plan that runs against a live preview.

The core issue is not a style problem but one of authorship; AI tools accelerate passes but cannot decide if the work genuinely reflects the author's intent or thought process (12:39).

AI slop doesn't eliminate the work; it merely pushes the burden downstream, requiring human readers to spend time checking and correcting unvetted content (4:35).

Authorship must be treated as a process—a commitment to refining the work until it is clear and true enough to communicate, rather than just an output (8:50).

Agents' small discoveries and incidents often remain trapped within a single session (e.g., closed PRs or chat history), leading to the evaporation of corrections and preventing knowledge from becoming reusable.

Teams need more than just a wiki; they require a 'knowledge factory' that catches mistakes, interruptions, and turns them into validated guidance. This knowledge must be constantly evolving (live, die) rather than static.

Giving agents a unique identity with signed commits and access rules solves the problem of attribution masking. It establishes a clear actor boundary, preventing agents from operating under human permissions.

The 'Diary' serves as the central home for all discoveries and decision-making ('what the F moment'). It allows work/decisions to be linked to specific entries, providing reasoning beyond just diffs and commit messages.

The process involves capturing an incident (Entry) $ ightarrow$ grouping related Entries into a 'Pack' $ ightarrow$ rendering the Pack into usable markdown/context for the agent. This ensures lessons are traceable back to the original failure.

To ensure quality, two types of evaluation are necessary: checking if the Pack is 'true to the entries' (fidelity) and running a task that reproduces the original incident using the knowledge pack to measure improvement (usefulness).