Research

Find what already works, read the source, then promote only what the evidence supports.

The arrows show the route from discovery to a tested reusable method.

Scroll sideways to see the full diagram →

Diagram source

flowchart TD
    L["landscape.md<br/>find existing tools"] --> R["references/<br/>read + cite sources"]
    R --> P["process-profiles.yaml<br/>encode scoped rules"]
    P --> C["../src/cadagent/<br/>apply the rule"]
    C --> T["../tests/<br/>worked examples + defects"]
    T --> S["../skills/<br/>when to use it"]
    classDef here fill:#fffdf5,stroke:#173d3c,color:#173d3c
    classDef near fill:#eef1e4,stroke:#6f8a80,color:#173d3c
    class L,R,P here
    class C,T,S near

Scroll sideways to see the full diagram →

Diagram source

flowchart TD
    L["landscape.md<br/>find existing tools"] --> R["references/<br/>read + cite sources"]
    R --> P["process-profiles.yaml<br/>encode scoped rules"]
    P --> C["../src/cadagent/<br/>apply the rule"]
    C --> T["../tests/<br/>worked examples + defects"]
    T --> S["../skills/<br/>when to use it"]
    classDef here fill:#fffdf5,stroke:#173d3c,color:#173d3c
    classDef near fill:#eef1e4,stroke:#6f8a80,color:#173d3c
    class L,R,P here
    class C,T,S near

Evidence	Files and use
Reference registry	Core sources, shards, evidence ladder and promotion procedure; one id space, not one confidence level
Tools to adopt or wrap	Landscape and data, agent toolkits, upstream registry
Process rules	Profiles and limits, rule data; unread rules cannot drive checks
Compliant mechanisms	Survey → snap-fit method
Simulation	Tools, FEA/process survey → toolkit
Sheet metal	Survey, guides, joining, parts data
Review practice	Design workflows and data → pitfall checks
Supply chain	Dated report, machine report, accepted findings; regenerate rather than hand-edit reports
Benchmarks	Gate timing script; timings describe its selected cases and environment

cad-agent rules <feature> serves scoped rule cards; cad-agent choose joining --load N starts a joining decision. Profiles and card limits explain the inputs, source confidence and gaps; the cards are generated from the rule data, not copied into this map.

python -m cadagent.review.references --check checks registry consistency and citation/evidence rules. It does not verify every source claim or prove a physical result. The existing evaluation paths and limits distinguish deterministic regression checks from the planned model-comparison framework.

Home · Guides · Skills · Lessons