Accounts payable spends its days retyping invoices and guessing which account each line belongs to. This reads the invoice and proposes the coding for you.
sonnet1 weekLlamaParseOpenAIGoogle SheetsQuickBooks API
Claude
84ROI
86Scale
$2.8k93Saved
ROI for
README.md
Why this subagent
Accounts payable spends its days retyping invoices and guessing which account each line belongs to. This reads the invoice and proposes the coding for you.
It parses line items with LlamaParse, structures the header fields, and suggests a GL code per line for your team to confirm. Nothing posts until a human approves the review row.
How it runs
Used at step 01 to kick off the pipeline.
Write
Used at step 01 to kick off the pipeline.
WebFetch
Used at step 01 to kick off the pipeline.
WebSearch
Used at step 01 to kick off the pipeline.
Identify the vendor, invoice number, dates, and amount due into a fixed structure.
pending
Suggest a general ledger code per line based on the vendor and item description.
pending
Write the coded result to a review sheet and hold it for AP approval before posting.
pending
Sample output
json
// Sample output
// (generated when the pipeline finishes)
Extract invoice fields and suggest a GL code per line item; return JSON and never post without the approved flag.
Unlock the rest
The full agent definition, install snippet, and starter task are gated for community members.
Members get the full `.md` agent file, the npm / pnpm install one-liners, a starter prompt that we've tuned against real runs, and the open-source repo when this automation ships there. One email, magic link, done.