Open SystemDecoder on a larger screen to build systems, run simulations, and inject chaos.
What's waiting for you on desktop
Live Simulations
Watch latency spike, queues fill, and nodes fail in real time. Every slider change is instant.
Visual Architecture Canvas
Drag nodes, draw edges, and build any distributed system topology from scratch.
Chaos Engineering
Kill servers, introduce packet loss, throttle CPUs — and watch your system react.
Real-time Insights
Throughput, p99 latency, error rates — all charted live as your simulation runs.
40+
Concepts
<1s
Feedback
∞
Replays
"The best way to understand a distributed system
is to break it."
Capacity Planning
1 of 5
The 10-minute estimate that can save you $50,000/month.
4,050
Avg RPS
sustained load
12,150
Peak RPS
3× spike (events)
17
Servers
needed (w/ headroom)
11 PB
3-yr data
with 3× replication
In 2008, Twitter went down under the load of election night traffic. They had 20,000 requests/second — their servers expected 5,000. Nobody had done the math. Capacity planning is doing that math *before* the crash, not after.
Before you build
Choose the right database, server count, and storage tier from day one. Emergency migrations under live load are 10× harder and cause outages.
Before you scale
Know exactly which component breaks next. Pre-provision it — before your users discover it first. Reactive scaling is always too slow.
Before you overspend
A 10-minute estimate prevents $50,000/month in over-provisioned cloud resources. Most teams skip this and pay silently for years.
In every interview
Every staff/senior system design interview requires back-of-envelope calculations. It is the single most testable skill — and the one most candidates skip.
You don't need exact answers. You need answers within 2× of reality — with your assumptions written down so your whole team argues about the right things, not the wrong ones.
Try it in the Library