Platform
Solutions
Resources
Pricing
Blog
About
Careers
Sign in
Book a demo
Engineering notes, research and playbooks from the team building Synth.
All
Engineering
Research
Product
Guides
Company
Search posts
⌘K
Sep 16, 2026
Language models are good at conversation and bad at policy. Here is how we split the two, and what it did to our error rate.
By Tomasz Wrona
Sep 9, 2026
Reviewing fifty tickets a week felt rigorous. Scoring all of them showed us how much the sample was hiding.
Aug 28, 2026
People notice a pause on the phone at around a second. This is the latency budget we work to, stage by stage.
Aug 19, 2026
The plan we run with every new customer, week by week, including what we check before real traffic arrives.
Aug 7, 2026
Most quality rubrics are written for people who already know what good looks like. Here is how to write one for a model.
Jul 29, 2026
One model per agent is simple and expensive. One model per step is cheaper, faster and easier to change. Here is how routing works.
Jul 15, 2026
An agent that never hands over is either doing very easy work or doing hard work badly. How we design the moment it passes to a person.
Jul 2, 2026
Synthetic test cases miss the strange things customers actually say. A step-by-step guide to turning your history into tests.
Jun 18, 2026
When a winter storm grounded two hundred flights, an airline's agent handled the morning. What we saw from the inside.
Load More
Create a free website with Framer, the website builder loved by startups, designers and agencies.