Document extraction and reconciliation for Capital Markets
Extracts the fields you need from a document pack and shows you where the documents disagree.
- Category
- Agent Tools
- Registry category
- Operations & ProductivityWorkflow & Productivity
- Vendor
- Flowx AI
- Location
- Not disclosed
- Reviews
- This marketplace has no ratings
- Listed on
- Google Cloud Marketplace
- Pricing
- 1 plan listed
Each fact carries one Provenance score: the average of its Disclosure and Evidence scores, the same rule the page uses for the overall score. Click any score to see the math behind it.
Vendor Provenance
Who actually operates this agent.
Build Provenance
What the agent is built on.
Reach Provenance
How the agent is distributed and adopted.
Data Provenance
What the vendor discloses about data handling.
Compliance Provenance
What standards the vendor meets, and who verified them.
What the publisher says
Institutional onboarding arrives as a pack of unlabelled documents that are supposed to describe the same people and the same company — and frequently do not. Reading them is slow; noticing that two of them disagree is slower, and easy to miss.
This agent reads the whole pack. You supply a JSON Schema describing the fields you need, and it extracts each one with the verbatim quote and page that support it. It then resolves which claims refer to the same person or company — matching name orderings, initials and legal-entity suffixes — and compares every field across every document that mentions it.
Each field comes back marked agreed, single-source, conflicting or missing. Where documents disagree, all readings are returned side by side and none is chosen. Where only one document supports a value, that is stated rather than presented as established. Where a required field appears nowhere in the pack, that absence is proven by an exhaustive pass, not inferred from a search that returned nothing.
Show the rest of the publisher’s description (2 more lines)
This is deliberately more than retrieval. Two addresses differing by a single digit are near-identical to a search index and are exactly the finding that matters. The same name written three ways is three different strings and one person. Both cases are resolved here, deterministically — the language model reads documents and writes the summary, but is never asked whether two values match.
The agent stops before verified. No outcome asserts that a fact is confirmed. It gives a reviewer the evidence, the disagreements and the gaps, and leaves the judgement where it belongs.
Plans and pricing
1 plan listed
Linked repositories
Unknown
Unknown means this listing does not publish a repository. It is not a statement that the code is closed.
Publisher resources
Sources
- Marketplace listingGoogle Cloud Marketplace (opens in a new tab)
- Company recordVendor website company data, matched on flowx.ai
Reading the score
Disclosure · how many sources corroborate it
Evidence · what kind of evidence backs it
The SettleTop steps above are possible but not automated yet, so today they sit open and a perfect 10 is out of reach. Open information like firmographics and reach has fewer steps to climb, so it sits a little higher for the same visible evidence.
Information shown here reflects the best available information at the time of assessment and may be incomplete, outdated, or subject to change. It should be independently verified before being relied upon for any decision. SettleTop is not liable for any errors, omissions, or decisions made in reliance on this information.
Have information about this agent?
Send it to us for consideration
Spot something missing, wrong, or out of date? Share what you know. Every note reaches our team. It does not change the passport by itself: we review it first.