/guided-research

What it does

An orchestration layer over deep research that decides when the expensive version is worth running — architectural decisions, new problem domains with established best practice, unfamiliar APIs you have already failed against twice — then organizes what comes back so it is reusable rather than read once.

When to reach for it

Before choosing a library, framework, or structural approach. Agents systematically under-research at exactly these moments: two shallow web searches at a decision point is the signal.

It's working if

• ·It sometimes concludes the question does not need the expensive version, and stops there.
• ·You open the write-up again a month later instead of re-running the research.
• ·You can name what you rejected and why, not just what you chose.