The Amy blog

Working smarter,
in plain English.

Practical ideas on putting AI to work — no jargon, just things you can use this week.

Featured

Welcome to the Amy blog

Announcements

A new home for what we ship, what we learn, and how we think about agents that work for your business.

HN
Henry Ng
Apr 30 · 1 min read
Amy Engineering

Inside Amy's credit system

How we ship a credit-based ledger that survives partial failures, refunds, and webhook re-deliveries — without losing a single cent.

HNApr 22 · 3 min read
Product

Why we moved to credit pricing

Seat licenses force teams to over-buy. Per-call pricing punishes experimentation. Credits are the only model that fits how agents actually get used.

HNApr 15 · 2 min read
Research

Notes on prompt caching at agent scale

What we measured running Amy with aggressive prompt caching: where it pays off, where it backfires, and the rule of thumb we use now.

MPApr 8 · 2 min read
Amy Engineering

How we sandbox untrusted browser tools

Running an agent's browser actions next to production data is a footgun. Here's the isolation model we landed on.

ATApr 7 · 1 min read
Amy Engineering

Observability for long-running agent runs

Traces work great until your span outlives your trace exporter. Notes from instrumenting eight-hour agent jobs.

ATMar 31 · 1 min read
Amy Engineering

Designing the Amy job scheduler

Cron-style triggers, idempotent dispatch, and the surprising amount of work that lives between 'fire' and 'run'.

ATMar 24 · 1 min read
Amy Engineering

Postgres advisory locks for at-most-once delivery

We replaced a Redis-based mutex with a single Postgres advisory lock and removed an entire class of races.

ATMar 17 · 1 min read
Amy Engineering

Rate-limiting per-user API keys without a queue

Token buckets in Postgres, no Redis, and a hot-key strategy that doesn't pretend hot keys won't exist.

ATMar 10 · 1 min read

One useful idea, every week.

Short, practical, no spam. Join business owners getting their time back.