All systems operational
SOC 2 Type II · Trust center →
Journal

Field notes from the post-ticket era.

Essays, benchmarks, engineering deep-dives. Written by the team building Quellra — for the teams using it.

Essay · 12 min · Jia Lin

Why "agentic" is not a feature.

The market keeps confusing chat-with-tools for autonomous agents. They are not the same. Here's the architecture difference, in 2,400 words.

Read article →
Benchmark · 8 min · Quellra Labs

The Quellra Support Benchmark, Q2 2026.

Side-by-side accuracy of leading agents on 14 production support tasks. We publish the data. Everyone else doesn't.

Read report →
Engineering · 18 min · Sam Veranis

Building a verifier model that refuses to lie.

How we shipped an independent verifier that catches 94% of the failure modes our planner misses — without slowing the loop.

Read article →
Customer · 6 min · Plinth

From $14 cost-per-resolve to $0.04.

Daniel Reyes (CFO) on how Plinth restructured the support P&L around outcomes, not headcount.

Read story →
Essay · 9 min · Ana Stathis

The end of the ticket as the unit of work.

Tickets exist because humans can't watch the product. Agents can. What replaces the inbox?

Read article →
Engineering · 14 min · Ron Park

Designing idempotent tool-use.

How we make sure an agent calling Stripe twice doesn't refund a customer twice. Patterns, primitives, and pitfalls.

Read article →
Essay · 7 min · Maya Okonkwo

Support is the most mis-measured function in SaaS.

CSAT is a vanity metric. Time-to-resolution is closer. The real number lives somewhere else.

Read article →
Product · 5 min · Quellra

Workflow Builder, in plain English.

A walkthrough of the natural-language workflow compiler, with the messy prompts that taught it taste.

Read article →
Field report · 11 min · Maxx Lin

Six lessons from forty design-partner kickoffs.

What growth-stage support teams actually want from AI. (Hint: not better autocomplete.)

Read article →