Insights for AI builders
Tutorials, product updates, and ideas to help you build and ship AI applications faster.
Subscribe via RSS
Buy the Commodity, Build What's Yours
Buy SaaS for the undifferentiated work—payroll, accounting, the system of record. Build the workflows that are core to how your org actually operates.
Claude Fable 5 vs GPT 5.5: Benchmark Breakdown and Real-World Coding Results
Compare Claude Fable 5 and GPT 5.5 on SWEBench Pro, Frontier Code, and real agentic coding tasks to find the right model for your workflows.
Decentralize the Building. Centralize the Seeing.
The two motions look contradictory: push building to the edges, pull visibility to the center. They only conflict when every tool is a separate island.
Diffusion Language Models Explained: How Google's Diffusion Gemma Works
Diffusion Gemma is Google's first open-weight diffusion language model. Learn how it differs from autoregressive models and when to use it in your workflows.
Your Best Engineers Should Architect Substrates, Not CRUD Apps
When non-engineers build the long tail of internal tools, scarce engineering talent moves up: design the governed substrate, set patterns, review what ships.
Fragmented Tools Make Your Org Illegible to Its Own Leadership
Run on dozens of disconnected tools and leadership can't see across them—can't answer cross-cutting questions, govern, or steer. The org goes blind to itself.
How to Use Claude Fable 5 for Complex Agentic Workflows: Tips and Best Practices
Claude Fable 5 excels at long, complex tasks but burns tokens fast. Learn how to set effort levels, manage costs, and get the most out of this model.
Your Processes Change Faster Than Your Software Can
In most orgs, the business learns faster than its tools can be rebuilt, so understanding outpaces software and the company slows to the speed of its backlog.
The Compliance Case for Letting Everyone Build
Compliance teams treat citizen development as a risk. On a governed substrate it delivers a better audit trail and access control than the status quo.
What Is Analogical Reasoning in AI? Why Bigger Models Don't Always Win
Analogical reasoning is one of the most human-like AI capabilities—and it doesn't scale with model size. Here's what the research shows and why it matters.
What Is Inference-Time Compute? Why OpenAI, Google, and Anthropic Are All Pivoting
Inference-time compute lets AI models think longer at query time instead of relying on bigger base models. Here's why every major lab is making this shift.
The Companies Winning at AI Don't Have the Biggest Budgets
AI returns don't track with spend. The orgs pulling ahead didn't buy the most licenses or GPUs—they shortened the distance between a problem and a working tool.
AI Benchmark Contamination: Why SWEBench Pro Scores Should Come with an Asterisk
SWEBench Pro has contamination problems—models like Claude Opus cheated on 12% of tasks. Learn why DeepSWE is a more reliable benchmark for agentic coding.
How to Build an AI Operating System Using the Four C's Framework
The Four C's—Context, Connections, Capabilities, and Cadence—are the building blocks of a personal AI OS. Learn how to implement each layer with Claude Code.
7 Apps Your HR Team Can Build Without Waiting on IT
Onboarding, PTO, the employee directory—the people-team tools HR keeps faking in spreadsheets. Here are seven your team can build itself, without waiting on IT.
How to Build an AI Second Brain with Claude Fable 5 and Claude Code
Learn how to build a personal AI operating system using Claude Fable 5, the Four C's framework, and Claude Code skills for maximum productivity.
The Build-vs-Buy Decision Just Flipped—and Most Orgs Haven't Noticed
The classic build-vs-buy rule sent everything but core to 'buy' because building was slow and expensive. That input just collapsed—and the rule needs rewriting.
Buying Everyone a Chatbot Is Not an AI Strategy
Handing every employee a chat assistant feels like AI transformation, but it changes nothing structural about how your org operates. Real strategy is about what you can build.
How to Use Claude Artifacts to Build Shareable Web Apps from a Single Prompt
Claude Artifacts turn interactive visuals into standalone web apps with shareable URLs. Learn the brainstorm-first prompt strategy that gets better results.
Claude Code vs OpenAI Codex: Steering vs Dispatching Agents
Claude Code makes steering agents feel natural. Codex makes dispatching feel natural. Learn which approach fits your work and when to use both together.
Claude Fable 5 for Long-Running Agentic Coding: Real-World Results
Claude Fable 5 excels at complex, multi-hour coding tasks. See real benchmarks, Stripe's 50M-line migration case, and when it's worth the 2x cost.
How to Use Claude Fable 5 Dynamic Workflows for Parallel Sub-Agent Execution
Claude Fable 5 paired with dynamic workflows can spawn hundreds of parallel sub-agents. Learn how to use this combination for massive agentic coding tasks.
How to Use Claude Fable 5 Effort Levels: Low, Medium, High, and Max
Claude Fable 5 has five thinking modes. Learn when to use low vs max effort, why overkill hurts performance, and how to match effort to task complexity.
Claude Fable 5 Safety Guardrails: What Gets Blocked, What Doesn't, and Why
Claude Fable 5 has aggressive safety classifiers that block biology, cybersecurity, and LLM dev queries. Here's what triggers them and what doesn't.