ai-coding-tools-comparelisted

Produce a side-by-side comparison of AI coding tools — GitHub Copilot vs Cursor vs Windsurf vs Cody vs Tabnine vs JetBrains AI vs Amazon Q Developer vs emerging entrants — against the org's enterprise rubric. Rubric axes — auth (SSO/SAML/SCIM), data flow (residency, content exclusion, training-data policy), IP indemnity, on-prem / single-tenant options, admin telemetry, FedRAMP/SOC2/ISO certifications, model routing transparency, audit log access. Use when the user asks to compare AI coding tools (Copilot vs Cursor vs Windsurf vs Cody vs others) against the org's enterprise rubric, or asks "should we switch to X?" — during periodic re-evaluation, vendor selection for a specific use case, or before responding to leadership. For an in-depth single-tool study (not a comparison) use copilot-deep-dive.
themarmack/research-bot · ★ 0 · AI & Automation · score 68

Install: claude install-skill themarmack/research-bot

# ai-coding-tools-compare The "should we be using X instead of Copilot?" answer with structure. Most comparisons in the wild are vendor-marketing pageant scoring; this one applies the org's actual procurement / TPRM / compliance rubric. ## When to use - Periodic re-evaluation cadence (currently annual; revisit if regulator activity, vendor change, or material capability gap forces it). - Vendor selection for a specific use case (e.g., agentic refactoring of legacy COBOL — does Cursor's UX matter more than Copilot's posture there?). - Leadership question: "I saw a demo of Cursor — should we switch?" - Annual Copilot TPRM-file review needs a comparative posture summary. ## When NOT to use - Specific Copilot questions → `copilot-faq-answerer`. - Frontier-model comparison (which model is best) → `frontier-model-watch`. - Tool selection for non-coding AI (chatbot platforms, knowledge management) → out of scope. ## Enterprise rubric (the comparison axes) | Axis | What we check | |------|---------------| | **Auth** | SSO via SAML, SCIM provisioning, EMU support, IP allow-list | | **Data residency** | US / EU regions available + enforced at tenant level | | **Training-data policy** | Do customer prompts train models? Default + contractual options | | **Content exclusion** | Org-level + repo-level + path-level patterns | | **IP indemnity** | Scope of indemnity + conditions (e.g., filter requirement) | | **On-prem / single-tenant** | Available for regulated buyers? At what tier?