Evidence tier Source Confirmed · 4 captures on record
What the publisher says
As described on AWS Marketplace.
Provenance turns your data into answers. Connect your Parquet data in S3, ask questions in natural language, and get structured analytical reports - automatically. Under the hood, Provenance decomposes every question into an execution plan using a deterministic capability graph with 32 analytical operations and 15 composable motifs. A BFS planner validates the plan against your actual schema before execution begins - no hallucinated columns, no failed queries. The DAG executor runs each step, and a reporter generates interactive tables, charts, and narratives from the results. Key capabilities: - Natural language to structured analytics: top 5 stores by revenue last quarter becomes a validated execution plan in milliseconds - Schema-aware: discovers your columns, entities, and relationships automatically from Parquet metadata - Multi-scope analysis: compare entities, compute ratios, rank within groups, detect trends - all from a single question - Deterministic audit trail: every answer traces back through the exact operations that produced it - Secure multi-tenancy: each customers data is isolated via cross-account IAM roles with confused-deputy prevention - Customer-managed or provider-managed storage: you choose where artifacts and context data live - Conversation memory: follow-up questions build on prior results with full context Built on AWS with Bedrock for AI, ECS Fargate for compute, S3 for storage, and DynamoDB for tenant management. No GPUs required. Scales to thousands of concurrent tenants. Provenance is domain-agnostic - it works with any tabular data. Energy, retail, logistics, finance - if your data is in Parquet, Provenance can analyze it.
Highlights
Highlighted by the publisher on AWS Marketplace.
Ask questions in plain English, get structured reports with tables, charts, and narratives - no SQL, no dashboard building, no data engineering required
Deterministic execution engine with 32 analytical capabilities and schema-aware planning - every answer is validated against your actual data before execution, eliminating hallucinations
Secure cross-account architecture with per-tenant isolation, customer-managed storage options, and full audit trail from question to answer
Agent build and provenance
See the full provenance
The layer-by-layer build, the evidence behind each claim, the risk basis and the cross-marketplace links are open to any account. Some rows are disclosed, some the source leaves Unknown; a free account shows you which.
Plans and pricing as listed
9 listed- Units
- Units
- Units
- Units
- Units
- Units
- Units
- Units
- Units
Refund terms
As stated by the publisher on AWS Marketplace.
Provenance offers a full refund within the first 14 days of any new contract. After 14 days, unused portions of annual contracts are eligible for a prorated refund. Monthly contracts are non-refundable after the billing period begins. Contact support@provenance.squidbot.io to request.
Sources
Linked repositories
Unknown means this listing does not publish a repository. It is not a statement that the code is closed, and a linked repository is not a claim that the publisher wrote it: the registry computes that relationship privately and does not publish it.
Evidence risk is the share of the build you cannot see before you deploy, not a security rating. Sign in to see the layer-by-layer basis for this band.

