Prescription intake and processing
Kohepets turns incoming prescriptions into records ready for pharmacy review.
An intake agent reads uploaded prescriptions, extracts the details and checks them against customer and product records. Customers are notified immediately of issues they need to resolve, reducing delays before pharmacy review.
Built with Anthropic Claude
The impact
84%
less manual intake work
Prescription intake and processing
Case study facts
- Industry
- Pet retail & pharmacy
- Team
- Operations
- Systems connected
- 3
- Time to live
- 2 weeks
- Engagement
- AI implementation
The impact
Results for the team
- less manual intake work
- 84%
- less manual intake work
- The agent extracts prescription details and checks record matches, reducing the intake work the pharmacy team enters by hand.
- returned to the team each week
- 32 hrs
- returned to the team each week
- Repetitive prescription intake takes fewer staff hours each week, freeing time for pharmacy review and exceptions.
- of prescription fields prepared for review
- 92%
- of prescription fields prepared for review
- Prescription fields are extracted and checked against customer and product records before being presented for pharmacy review.
Situation
Every prescription started with manual entry.
Kohepets receives uploaded pet prescriptions. The pharmacy team had to read each document, find the matching customer and product, and enter the prescription details by hand before reviewing it.
Challenge
Unclear details need attention, not guesswork.
Different document formats, unclear writing and missing details made intake repetitive and difficult to standardize. The agent needed to prepare reliable records without guessing, keeping the original prescription and any uncertainty visible to the reviewer.
Customers also needed immediate feedback on issues they could resolve, rather than waiting for the team to discover them later.
What we built
From incoming prescription to prepared record.
We built an intake agent that reads uploaded prescriptions and extracts the relevant fields into a structured record. It checks customer and product matches, identifies missing or unclear information and immediately notifies customers of submission issues, with clear guidance on what needs correcting or resubmitting.
It also flags exceptions for the pharmacy team. Reviewers see the prepared fields beside the source document, make any corrections and approve the record for the existing prescription process.
- Receive the prescription
Receive the uploaded prescription and retain the original document for review.
- Extract the details
Read the customer, pet, prescribed product, quantity and directions, preserving uncertainty where the source is unclear.
- Match existing records
Check extracted details against customer and catalog records, surfacing uncertain matches.
- Notify customers immediately
Flag missing information, unreadable text or conflicting details as soon as they are detected, and tell customers what they need to correct or resubmit.
- Prepare pharmacy review
Present the structured record alongside the original prescription so the team can check and correct it.
- Save the reviewed record
Carry approved details into the existing prescription process with the review history retained.
Evals and guardrails
Extract accurately. Escalate uncertainty.
Extraction evals
Compare extracted prescription details with reviewer-checked examples. Test blurry scans, missing fields and conflicting customer information.
Matching evals
Measure correct and missed customer and product matches. Test unclear cases and check extracted details against the original prescription.
Guardrails
Check required fields, prevent duplicate notifications and send uncertain details to pharmacy review. The agent cannot authorize dispensing.
Results
Earlier corrections. Fewer delays before review.
The agent extracts prescription details and checks record matches, reducing the intake work the pharmacy team enters by hand. Repetitive prescription intake takes fewer staff hours each week, freeing time for pharmacy review and exceptions.
Prescription fields are extracted and checked against customer and product records before being presented for pharmacy review.
- less manual intake work
- 84%less manual intake work
- returned to the team each week
- 32 hrsreturned to the team each week
- of prescription fields prepared for review
- 92%of prescription fields prepared for review
From Kohepets
“We have worked with Revensi for many years. In that time they have made vast improvements to how our business runs, and they are great people to work with. We highly recommend them.”
Build Capacity To Grow. Own Your Intelligence.
Bring the workflow slowing your sales, orders or delivery. We'll map the bottleneck and show you what the AI system could look like.