An example workflow
A logistics platform
Delivery notes and invoices arrive as phone photos and scans. An evaluation could run a labelled sample through right-sized models and compare field accuracy, latency and total cost with the current provider.
Your extraction pipeline, tested on your own documents.
Turning scans, invoices and forms into structured data is mostly extraction and classification. Test right-sized models on your labelled documents before you switch.
Prefer email? hello@azitalabs.com, subject “Workload evaluation: Data extraction”
Messy documents, strict fields.
You turn a large volume of scanned documents, invoices and KYC forms into structured data. Every table has to parse and every field has to match your labels, and each step runs on a frontier model whether it needs one or not. Your customers' contracts decide where documents may be processed, and model changes arrive on someone else's schedule.
- What you bring
- A labelled sample of your documents: scans, invoices or forms, with the fields you extract.
- What comes back
- Structured fields and tables with accuracy, latency and total cost for each step, checked against your labels.
What an evaluation could look like.
An example workflow
A fintech startup
KYC forms and bank statements must be parsed accurately and kept in the country. An evaluation could run a labelled sample where the firm's rules allow and compare extraction accuracy and total cost.
An example workflow
An accounting software provider
Customers upload ledgers and receipts in every format. An evaluation could profile the table extraction step, test smaller models on the team's labels, and set the total cost of each route side by side.
Your evals decide.
Your evals are the bar
Every step is judged against your labelled documents. A step that does not pass stays where it is.
Checked against your labels
Every field and table is scored against your labelled documents, so accuracy is measured on your formats, not a public benchmark.
Quality and total cost, compared
Each parsing and classification step's total cost compared with what you pay today, before you switch.
Where it runs, and what is agreed.
Capacity from the Azita fleet
Run your workload on capacity from Azita’s installations. Scope the workload and data requirements.
Discuss your workload on the fleetAn installation in your building
Scope the room and workload together. Azita designs, installs and commissions the deployment.
Discuss an installation in your buildingWhere the work runs, which models are used, who has access and how long anything is kept are agreed in your proposal before any work starts. The Trust page sets out custody and residency by side.
Compare quality and total cost on your own workload.
Agree a representative job and the acceptance criteria. Compare the output, turnaround, data requirements and total cost before deciding.
- Share one workflowOne extraction pipeline in production, with its eval set and last month's usage.
- Agree the pass criteriaField accuracy against your labels, the latency your pipeline needs and where documents may be processed.
- Compare on both stacksPass rates, latency, data requirements and total cost, side by side. Cut over step by step, or not at all.
Available to evaluate on your own workload.
On the Azita fleet, or on an installation in your building.
Arrange a workload evaluation
We'll review what you need to run and contact you to discuss the right setup.
Proposal based on your workload and deployment.
There is no price list. Your proposal states what is being quoted, the commitment and what is included. Human review, software licences and integration are listed wherever they apply.
Add what you pay for today. It travels with your enquiry as a note, so the comparison starts from the same work.
Prefer to read first? How pricing works
Straight answers.
Will our extraction evals still pass?
Your eval suite decides. We map each step to the smallest model that meets your pass criteria and run the suite on both stacks side by side. A step that does not pass stays where it is.
How does an evaluation work?
Send one extraction pipeline with its eval set and last month's usage. We agree the pass criteria, run the suite on both stacks, and set out pass rates, latency and total cost for each step.
What changes in our pipeline?
Your evals run in CI, and you cut over step by step behind your own flags. Any step that does not pass on the new stack stays with your current provider.
Where do our sensitive documents go?
On the Azita fleet, or on an installation in your own building. Where your documents are processed, who has access and how long anything is kept are agreed in your proposal before any work starts.
How is it priced?
Proposal based on your workload and deployment. It states what is being quoted, the commitment and what is included, and lists human review, software licences and integration wherever they apply. There is no price list.
What are the contract terms?
Term, what is included, exit and data handling at the end are set out in your agreement before you sign.
Related
Engineering and product
Agents, support, extraction and product features, tested on your own evals.
The page for every kind of work in this group, and how an evaluation works.
Read
Also for
IT services company
Coding assistance and code review for delivery teams whose client contracts restrict where code goes. Evaluate on your own repositories first.
Read
Also for
Fintech product
KYC extraction, statement parsing and fraud checks on right-sized models, tested on your evals. Compare accuracy, latency and total cost first.
Read
Start with your own workload.
Share one pipeline
A production workflow and its eval set. We agree the pass criteria, then compare output, latency and total cost on the same input.
Arrange a workload evaluation