Automated API HTML parsing for Salesforce CRM intelligence
Automated API HTML parsing for Salesforce CRM intelligence converts each HTML page attached to a record into searchable passages, so the assistant answers from the file rather than from fields someone typed.
How does automated API HTML parsing feed Salesforce CRM intelligence?
Automated API HTML parsing for Salesforce CRM intelligence converts each attached HTML page into passages when the file is saved, so the assistant can cite the file instead of guessing from record fields.
Where the HTML page sits in Salesforce
Salesforce keeps the file on the lead, account, or opportunity as a ContentVersion or a classic Attachment. The typed fields on that record are already searchable. The HTML page is not, until automated API HTML parsing copies its words into passages keyed to the same record. CRM intelligence that only reads the fields is intelligence about what a person typed, not about what the file says.
What an HTML file actually yields
HTML is markup around words. The parser walks the text and puts a break between block elements, so two paragraphs do not glue into one token. It does not fetch remote entities: network access and XXE are off. Scripts are not the passage. A saved page attached to a record can be indexed without turning the converter into a browser.
The API call that feeds Salesforce
An Apex trigger, a record-triggered Flow, or a Platform Event can POST those bytes when the file is saved. The response is JSONL, one passage per line, with the record id in metadata for the retrieval store beside Salesforce. Asking a model to reread the HTML page inside chat for every question never builds that index. Automated API HTML parsing runs when the file is saved, once, and later questions retrieve.
What the answer is allowed to cite
After a clean parse, an answer should cite the passage and the HTML page it came from. A file that yields no text is a skip, named as a skip, not a blank passage that crowds real hits. The parsers are Remade with Rust crates, and RAG Converter is part of MATA. The longer note on this format is RAG for HTML.