Resources
Guides and practical notes on adding AI assistants to software products.
Choosing a platform
Embedded AI assistants for SaaS: a buyer’s guide
The layers of an embedded assistant, the product categories, and the questions to ask before choosing one.
GuideCode-grounded AI assistants: a buyer’s guide
How code indexing, source refreshes, documentation drafting and claim verification differ.
GuideCopilotKit and Vercel AI SDK alternatives: what you still build
A layer-by-layer comparison of assistant-ui, CopilotKit, ChatKit, the AI SDK and Teaflask.
Comparison
Building the experience
Grounding and execution
Codebase grounding for AI assistants: the Provenance engine
From repository evidence to released documentation, executable checks and reviewed corrections.
ExplainerDurable execution for AI agents: pause and resume after approval
What happens when a turn waits for a person, a browser closes or a runtime restarts.
Explainer