Deterministic conversion across CSV, JSON (array of objects), and Markdown pipe tables. RFC 4180 CSV parsing with quoted fields, embedded delimiters and newlines, optional strict type coercion, and SHA-256 digests over both input and output. First node of the client-side conversions chain with Policy Mandate and W3C VC export. Zero network.
Copy this paragraph into Claude, OpenClaw, or any MCP-aware agent to run this exact tool, with this sample, and verify the artifact.
Run the AINumbers MCP tool `convert_tabular_data`. Task: Convert a table between CSV, JSON (array of objects), and Markdown pipe tables.
Call it with arguments: {"policy_parameters":{"data":"name,qty\napple,3\npear,5","source_format":"csv","target_format":"json","options":{"has_header":true,"coerce_types":true}}}
Verify before trusting: call `verify_execution_hash` on mcp.ainumbers.co (https://mcp.ainumbers.co/mcp) with the parameter `claimed_hash` set to the returned `execution_hash`, passing the full artifact the run returned (the object containing `policy_parameters` + `output_payload` + `execution_hash`; equivalently `policy_parameters` + `output_payload` with `claimed_hash`), not the bare hash string.
Return the ledger link https://ledger.ainumbers.co/ so a human can re-verify without contacting us.
PII rule: All inputs are processed locally in your browser. No data is transmitted. Do not enter real personal data — use synthetic or anonymised inputs only.
Open the tool with the sample prefilled: https://ainumbers.co/chaingraph/art-190-tabular-data-converter.html#p=v1.H4sIAAAAAAAA_wGDAHz_eyJkYXRhIjoibmFtZSxxdHlcbmFwcGxlLDNcbnBlYXIsNSIsInNvdXJjZV9mb3JtYXQiOiJjc3YiLCJ0YXJnZXRfZm9ybWF0IjoianNvbiIsIm9wdGlvbnMiOnsiaGFzX2hlYWRlciI6dHJ1ZSwiY29lcmNlX3R5cGVzIjp0cnVlfX3a_8a6gwAAAA