C.R.E.S.S. Principles for Context Engineering

Psst. If your boss won’t invest in training you in Specification By Example (BDD, ATDD), I’m running out-of-hours workshops on May 12 and 16 specifically for self-funding learners. £99 + UK VAT. After more than 3 years of research and experimentation, I feel like I have a good handle on what properties of LLM contexts tend to produce the best results in code generation and modification. You’ll have read about them on my site if you follow this blog. That was the easy part. The hard part is coming up with a catchy mnemonic to help me remember them. Introducing C.R.E.S.S. principles for context engineering. The most effective input contexts – measured by successful coding task completion in the fewest passes – are: CurrentThey contain up-to-date information (e.g. not an architecture summary that was generated multiple changes ago)RefutableThey contain some way of knowing with high confidence when the output doesn’t satisfy the intent (e.g. an acceptance test)EmpiricalThey use…