Most \”agents\” in 2026 are elaborate prompts
What real agent architecture actually requires — tool definitions, planning steps, trajectory observability, eval pipelines focused on end-to-end completion — […]
Technical
Technical
The eval pipeline is the product
A demo is a model. A product is a model + evals + fallback + cost cap + abuse detection
Security
Why I red-team every AI before launch
The math on pre-launch versus post-incident is brutal. Once a prompt injection vector lands on Twitter, three months of trust