RSS
Subscribe to the writing
New posts reach your reader the day they go up, and you do not need an email address or an account. Paste this URL into any feed reader:
https://www.saumyajain.info/feed.xmlWhat you get
- In the feed
- All 51 posts, newest first, not just the latest few.
- Last published
- · Idempotency Is a Scaling Problem, Not a Correctness Footnote.
- Each entry
- Title, a paragraph on what the post argues, the date, its tags, and a permalink to the full piece.
- Format
- Plain RSS 2.0. Any reader that accepts a URL accepts this one.
New to feed readers? One checks this URL on your behalf and gathers what is new into a single list. NetNewsWire on Apple platforms, or Feedly, Inoreader and Reeder across web and mobile, all subscribe from a pasted URL. Browsers dropped built-in feed reading years ago, which is why the raw file above looks the way it does.
Latest in the feed
·11 min read
Idempotency Is a Scaling Problem, Not a Correctness Footnote
Double charges, phantom inventory, ghost orders: all the same bug. The operation was safe to run once and your infrastructure ran it twice.
Backend / Architecture / Distributed Systems / E-commerce / PostgreSQL / Node.js
·13 min read
You Cannot Prompt Away a Hallucination
My system prompt said every number must come from a tool. With that rule in place, an eval run still flagged 14 of 38 answers. A rule in a prompt is a request. A check in code is a control.
AI / LLM / Testing / Reliability / Architecture
·14 min read
A Pause Is Not the End of an Answer
Voice agents end your turn when you go quiet. In an interview, quiet is where the answer gets built. Let the person end the turn, then engineer the silence that follows.
AI / LLM / Voice / WebSockets / Streaming / Architecture
·12 min read
Rate Limits Are an Architecture Problem
Rate limits are a throughput constraint, and the fix is a queue, a concurrency cap, and a degradation path. A longer backoff only resubmits work the provider has already refused.
LLM / AI / Architecture / Backend / Rate Limiting / Node.js
·11 min read
Observability for a Small Team
You do not need a vendor to know your system is broken. Structured logs, a request ID, and three dashboards get a small team further than most observability platforms.
Observability / Backend / Node.js / DevOps / Architecture
·11 min read
Building an Agent Loop That Knows When to Stop
Starting an agent loop is the easy part. The hard part is making it stop before it has burned forty dollars retrying a step that will never work.
Agents / LLM / AI / Architecture / Backend
·11 min read
A Pipeline Where No Node Is Allowed to Raise
An exception at stage nine throws away the model calls you already bought. Make every node declare what it returns when it cannot do its job, and make that answer a value rather than a log line.
AI / LLM / Reliability / Architecture / Backend
·11 min read
Every Model Call Should Have an Owner
The invoice says one number. Your pipeline has fourteen stages, and one of them is most of the bill. Attribution is what turns model spend from a surprise into a design decision.
LLM / AI / Cost / Architecture / Backend / PostgreSQL