Our own product, not a client project
How we built CIP on Microsoft Azure.
CIP shows how we design, build and test an AI platform. Here is what we set out to do, what we built and what our testing shows so far.
Challenge
Reviewing long business documents takes skilled time, and results can vary between reviewers. A summary alone is not enough for important work: people need the evidence, a clear review step and a record of the decision.
Solution
We built a cloud-native, multi-tenant platform on Azure that moves each document through a governed workflow.
A clear workflow
Each job moves through stages from submission, classification and analysis to human review, decision, report and notification.
AI with evidence
Document Intelligence reads the document. Azure OpenAI and rule-based checks find risks, facts and recommendations, with quotes from the source.
People decide
A reviewer approves or rejects the analysis, and the decision is recorded. Users have separate roles.
Built to run
Services scale down when idle and wake when work arrives. Reports are produced as PDF, Word, PowerPoint and JSON.
Outcome
These are our own tests on a fictional two-page IT services contract, checked against an answer key with eight expected risks. They are not customer results.
| Test | Expected risks found | Workflow |
|---|---|---|
| 2 October 2026 | 8 of 8 | Upload to approved report in 2 min 40 s, including human review |
| 15 October 2026 | 7 of 8 | Every stage completed, with services starting from idle, and reports in four formats |
What we learned
Test more than one run
Results varied between the two tests on the same contract, so we measure consistency, not just a single good result.
Check the evidence
We test whether important risks were found, quotes match the source and severity is right.
Keep improving
We have since made further changes, including work on consistency, and are testing them.
Want a platform like this?
Tell us your use case, and we can design and build a platform around your business.
Start a conversation