The second read on work that matters

Your AI tells you the draft looks great. Lenss tells you where it breaks.

Any plan, proposal or decision you are about to put your name on: a spec, a deck, a budget, a contract, a launch, an email, or the AI conversation you are thinking it through in. Lenss finds what it takes for granted, shows you where in your own words, and, wherever there are numbers, works out the point at which it stops holding.

Same draft, two reviews. Switch presets, flip the toggle, or paste your own in Your draft.

Stakes$9,400 / mo · read path for every catalog pageAdversarial Review · 1/4

Source draft

591 chars

RFC: Redis cluster in front of the catalog database

Platform team · status: proposed

Problem. Catalog reads peak at 18,000 requests per second and our p99 read latency is 420 ms. The SLO is a p99 under 150 ms. Every catalog query against Postgres takes between 380 and 450 ms at peak. Proposal. Put a six-node Redis cluster in front of the catalog read path. A cache hit returns in 4 ms. A miss falls through to Postgres and populates the key. We expect a 90% hit rate based on the 80/20 access pattern we see in logs. Cost. $9,400 per month for the cluster. Two engineers for three weeks. Success. p99 catalog read latency under 150 ms at peak within one sprint of launch.

Adversarial review

pinned · quoted · computed
01

Pinned objective

p99 catalog read latency under 150 ms at 18,000 req/s.

Underneath: The success metric is a tail percentile; the proposal reasons about the average request.

02

Hidden assumption

A 90% hit rate moves the p99. It does not: p99 is set by the slowest 1% of reads, and with 10% of reads missing, that slowest 1% is all misses.

“We expect a 90% hit rate based on the 80/20 access pattern we see in logs.”
verbatim · highlighted in source

If it’s wrong: The cluster ships, average latency falls, and the SLO still fails at the same 380–450 ms tail.

03

Flip threshold

Cache hit rate at which p99 can fall under 150 ms

≥ 99.0%RFC expects 90%
Figures behind the threshold
Miss path: Postgres + cache lookup384–454 ms
Every miss vs the 150 ms SLOover, always
p99 ≤ 150 ms needs misses ≤1.0% of reads
p99 at the expected 90% hit rate≥ 384 ms

At 90% the SLO fails. The decision turns on hit rate above 99%, not on the cluster.

Cheapest test: Replay one peak hour of read logs against an LRU of the planned size and measure the miss rate before provisioning.

One promise, three moments

AI agrees with you. Lenss shows you what your thinking took for granted, wherever you are doing it.

Before you ship a document

Studio

An adversarial audit of anything you are about to commit to, from a spec or a budget to a contract or a launch plan: what it is really for, what it rests on, quoted, and where it stops holding.

  • — Objective, assumptions, tensions and flip threshold
  • — Edit inline and re-verify
  • — Share a read-only link, export Markdown or PDF

While you think with AI

Lens

Paste a ChatGPT or Claude conversation. See where it drifted from what you came for, what the answers took for granted, and the one task that actually moves it.

  • — Whole threads, hundreds of turns long
  • — What the answer took for granted
  • — How to ask so it doesn't drift again

Before you hit send

Draft check

See what your email or message is doing before it lands: read against the people who will receive it.

  • — Read against up to three recipients at once
  • — Saved recipient profiles
  • — No rewriting, no advice: it shows, you decide

Lenss Work Coming soon

For the thing at work that keeps not resolving.

Lenss for

Find your role

Lenss to

Or start from the job

Teardowns

Where plans like yours break

All teardowns →

Privacy

Read, not trained on.

Studio and the free tools

Your draft is never written to a database or log, and never used for training. The finished review expires in an hour unless you create a share link, which lasts seven days.

Lens, Session and Draft check

These keep a record of each reading so your history works. Nothing runs in the background: you paste, you trigger.

Exactly what is kept, and for how long →