5 items
AI reconciliation assistant: record page steps, read elements/screenshots, run LLM actions, and sync Feishu/Lark reports. ReconPilot helps operations, finance, and reconciliation teams turn repetitive browser review work into guided AI-assisted workflows. Many reconciliation tasks still happen inside real web systems: checking bills, comparing order fields, reviewing table rows, reading exception messages, capturing screenshots, clicking audit actions, and writing the final report somewhere else. ReconPilot is built for that exact pattern. It lets you record the page elements that matter, describe each review step in plain language, ask your configured LLM to analyze the evidence, and then save the outcome as a clean report. Why install ReconPilot? 1.Save each page-specific workflow as its own task. 2.Run multi-step review processes in a predictable order. Record Read, Click, and Input selectors instead of relying on fragile manual instructions. 3.Send structured page evidence, tables, images, attachments, and Read screenshots to your selected model. 4.Keep sensitive browser actions under control with optional human confirmation. 5.Automatically continue steps once a workflow is trusted. 6.Create a fresh Feishu or Lark document report for each completed run. 7.Use common cloud model providers, local OpenAI-compatible services, or your own custom gateway through llm-hub based settings. 8.Schedule routine checks with Chrome alarms when Chrome is open and the target system is already logged in.
Jun 22, 2026
rating_count is the Chrome Web Store ratings count, not a written-review count.
Media assets
Screenshots and videos on the listing.
Has promo video
Whether the listing includes at least one video.
Languages
Declared language locales.
Developer website
Listing exposes a developer website URL.
Contact email
Listing exposes a contact email.
Keyword in name
Case-insensitive substring match in the name.
Keyword in description
Case-insensitive substring match in the description.
Keyword occurrences in description
Count of case-insensitive occurrences in the description.
Category user-count percentile
Share of same-category extensions with fewer users (null if unknown).
These are transparent listing completeness / keyword signals, not a prediction of Chrome Web Store search ranking.