Find the work your AI stack should remember.

Paste approved assistant logs, Codex or ChatGPT session JSONL, tool traces, or session exports. Workflow Miner finds repeated prompts, tool chains, failures, and manual handoffs, then turns the evidence into candidates and starter artifacts for reusable prompts, skills, automations, and connectors.

Your logs stay in this browser.

Analysis and redaction run locally. The shared site shell may load fonts and configured analytics; Workflow Miner does not upload or persist raw logs.

Workflow analysis No source loaded

Import a text, log, JSON, or JSONL file. The file is read locally.

Add approved activity

Plain text, JSON, JSONL, assistant messages, Codex session exports, and common tool-call records are supported.

Fixture kit Load or download a known-good sample before testing your own export.
Not checked
0 lines · 0 B Kept in memory only

Set privacy filters

Common tokens, credentials, authorization headers, and secret URL parameters are redacted automatically. Add one custom pattern per line for customer-specific data.

Entire matching events are removed before analysis.
Matches become [REDACTED] everywhere.
Built-in secret redaction active

Mine reusable work

Find candidates only when the source contains supporting evidence.

Your findings will appear here

Load the demo to see how repeated work becomes specific, evidence-backed recommendations.

From trace noise to a build decision.

01Normalize

Messages, sessions, tool calls, and errors become one local event stream.

02Find evidence

Repeated intent, action sequences, failure markers, and handoffs are counted.

03Recommend

Each candidate explains what to build and which evidence supports it.

04Prioritize and build

Use the backlog to pick the first implementation slice, then export the report or starter files.