We Let Our Financial Planners Write the Agents — Matthew Ragone, Range
Financial planners can build AI agents without writing code by capturing institutional judgment. The process involves five steps: Pick, Teach, Pack, Test, and Ship.
Read articleTopic
Knowledge Management
All digests tagged Knowledge Management
Suggested route
Topic journey
Move from earlier context through the available material to the newest signals. This route is a reading aid, not a difficulty ranking.
Start here
Edouard Maleix - How AI-First Dev Teams Build Collective Intelligence — One Attributed Mistake at Learn how to build collective intelligence by turning agent mistakes into reusable, attributable knowledge. The process involves Identity $\rightarrow$ Diary $\rightarrow$ Knowledge Pack.Build context
AI Slop Is Costing You Hours. Here's How To Stop Sending It. AI slop is costing hours of human effort because LLMs converge on predictable patterns. True quality requires focusing on authorship as a process, not just an output. How to Kill the Code Review — Ankit Jain, Aviator Code review must evolve beyond checking code diffs. The focus needs to shift from semantic accuracy (bugs) to preserving alignment, mentorship, and architectural intent by capturing session decisions. The Era of Compound Engineering — Kieran Klaassen, Every/Cora Compound Engineering suggests that efficiency comes from spending half your time building a feature and half teaching the system what it got wrong. This process compounds knowledge, making future development easier.Recent signals
We Let Our Financial Planners Write the Agents — Matthew Ragone, Range Financial planners can build AI agents without writing code by capturing institutional judgment. The process involves five steps: Pick, Teach, Pack, Test, and Ship. How OpenAI Puts ChatGPT to Work | DevDay 2026 Discover how OpenAI's teams use ChatGPT as an agentic teammate to automate complex workflows, from monitoring social feeds to scaling competitive research. Learn about Spaces and Dots. Grep or Embeddings? Agentic Search Over Company Documents — George He, LlamaIndex For enterprise data, simple file traversal fails. We need an agentic 'harness' that combines hybrid search, metadata filtering, and specialized parsing (LlamaParse) to ground answers from massive, multimodal corporate documents.
How OpenAI Puts ChatGPT to Work | DevDay 2026
Discover how OpenAI's teams use ChatGPT as an agentic teammate to automate complex workflows, from monitoring social feeds to scaling competitive research. Learn about Spaces and Dots.
Read article
Grep or Embeddings? Agentic Search Over Company Documents — George He, LlamaIndex
For enterprise data, simple file traversal fails. We need an agentic 'harness' that combines hybrid search, metadata filtering, and specialized parsing (LlamaParse) to ground answers from massive, multimodal corporate documents.
Read article
Stop Fine-Tuning to Fix Retrieval Problems — Anant Srivastava
The key architectural decision in enterprise AI is determining if knowledge belongs in the prompt (behavior), memory (facts), or weights (reflexes). This is not a ladder, but three distinct tools.
Read article
Your Coding Agent Deletes Its Memory After 30 Days
AI agents lose memory when sessions end. Learn how to build persistent knowledge repositories, implement a 'diary' for decision rationale, and use 'Super Agents' to extract maximum value from AI development.
Read article
AI News & Strategy Daily | Nate B Jones
Does Your Computer Belong To Codex? I Went To OpenAI To Ask.
AI adoption is less about aptitude and more about access to context. Learn how agents are moving beyond APIs to perform complex, multi-step tasks across diverse systems, fundamentally changing the definition of work.
Read article
Multiplayer AI Manifesto
The Multiplayer AI Manifesto outlines five principles for collaborative agent work: agents must live next to the work, learning must be open, and sessions must persist in the cloud. This shifts AI from single-user chats to true co-working.
Read article
The Era of Compound Engineering — Kieran Klaassen, Every/Cora
Compound Engineering suggests that efficiency comes from spending half your time building a feature and half teaching the system what it got wrong. This process compounds knowledge, making future development easier.
Read article
How to Kill the Code Review — Ankit Jain, Aviator
Code review must evolve beyond checking code diffs. The focus needs to shift from semantic accuracy (bugs) to preserving alignment, mentorship, and architectural intent by capturing session decisions.
Read article
AI News & Strategy Daily | Nate B Jones
AI Slop Is Costing You Hours. Here's How To Stop Sending It.
AI slop is costing hours of human effort because LLMs converge on predictable patterns. True quality requires focusing on authorship as a process, not just an output.
Read article
Edouard Maleix - How AI-First Dev Teams Build Collective Intelligence — One Attributed Mistake at
Learn how to build collective intelligence by turning agent mistakes into reusable, attributable knowledge. The process involves Identity $\rightarrow$ Diary $\rightarrow$ Knowledge Pack.
Read article