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.
Thinking it through with ChatGPT or Claude? See where the conversation drifted, in Lens →
Same draft, two reviews. Switch presets, flip the toggle, or paste your own in Your draft.
Source draft
591 charsRFC: Redis cluster in front of the catalog database
Platform team · status: proposed
Adversarial review
pinned · quoted · computedPinned 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.
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.”
If it’s wrong: The cluster ships, average latency falls, and the SLO still fails at the same 380–450 ms tail.
Flip threshold
Cache hit rate at which p99 can fall under 150 ms
| Miss path: Postgres + cache lookup | 384–454 ms |
| Every miss vs the 150 ms SLO | over, 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
Session
A running thread for the problem that keeps not resolving. Bring what changed; Lenss keeps the thread.
Chrome extension
Lenss inside ChatGPT and Claude. Dormant until you trigger it.
Lenss Work Coming soon
For the thing at work that keeps not resolving.
Lenss for
Find your role
- Product managersPRDs and one-pagers · Deprecation and sunset plans · Experiment briefs · Pricing and packaging changes · Launch go / no-go memos
- EngineersRFCs and design docs · SLA and disaster recovery specs · Build vs buy memos · Migration plans
- Founders & growthPitch decks · Paid acquisition plans · Enterprise pilot agreements · Hiring and headcount plans · Budgets and runway models
Lenss to
Or start from the job
Product managers
Teardowns
Where plans like yours break
Engineering RFC
A cache that can't fix the tail
Hit rate ≥ 99.0%. The RFC expects 90%.
Pitch deck
The MRR slide that forgot its own churn
CAC ≤ $26.35. The deck holds $40.
Pricing memo
Usage pricing priced off the wrong median
$0.025 per call holds MRR. The memo proposes $0.020.
Hiring plan
Three AE hires and a pipeline that doesn't grow
174 qualified opportunities a year before the three hires pay back. The plan has 120.
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.
Already use Lenss?