Deep Water

0 m — a few metres down, still full of sun · 40 sources drifting, none of them checked yet

Research you can
prove and control.

Deep Water reads thousands of sources, checks every fact against the page it came from, and hands back a report you can trust — with the receipts attached.

Scroll to descend

−300 m — the problem

AI sounds sure of itself.
That doesn't make it right.

Most AI reads a few web pages and stops. Five or ten pages, in English, whatever came up first — then it tells you the answer like it's certain. Everything else stays unread: the papers, the PDFs, and anything not written in English.

−700 m — the sweep

We check every source. Then we throw some away.

We read each page. We check it really says what we say it says. If it doesn't hold up, it doesn't go in the report. Keep scrolling — the light is passing over them now.

0 checked 0 verified · kept 0 fake · dropped

−2,400 m — the proof

Every sentence tells you where it came from.

Nothing is in the report without a source. Hover a sentence and its evidence lights up on the right. Never “studies show”.

Report example 0442 · 104 sources · Deep Fully sourced

Browser-native compute matured sharply this year, with workgroup memory limits raised across all three major engines and a common subset finally shipping by default.12

Independent benchmarks recorded a median 3.1× throughput gain on fused kernels against the 2024 baseline, holding across discrete and integrated hardware.07

Adoption stayed gated by driver parity on mobile, where two vendors still trail the specification by a full release and expose only a reduced feature set.23 31

Japanese conformance testing surfaced a regression that no English-language source reported — モバイルGPUドライバの適合性に回帰が確認された — filed against two shipping driver builds.23

German trade press put the driver gap at two release cycles, which the vendors have not disputed publicly, though neither has committed to a date.44

Chinese developer forums report the same regression reproducing on three mid-range chipsets, with a workaround that costs roughly 18% of the gain.52

Patent filings from one vendor describe a scheduler change that would close the gap, but the filing carries no ship signal.61

Where the record is thin, the report says so instead of filling the gap: no source we could verify reports shipped hardware using the new limits in production.08

Some teams report 5× gains. could not be verified · dropped

Arrived from the sweep0 / 0
12 GPU for the Web — working note w3.org · EN · standards body
07 Cross-engine kernel benchmark suite arxiv.org · EN · university
23 モバイルGPUドライバ適合性レポート techblog.jp · JA → EN · company
31 Driver parity tracker, Q3 ieee.org · EN · standards body
44 GPU-Treiber Konformität heise.de · DE → EN · press

hover a line. its evidence lights up.

−1,500 m — how deep do you want to go?

104 sources in this run

You choose how deep we go.

You pay for the work you order, not per person. Deeper means more sources, more time, and more cost. Pick a tier — the sediment on the left is every source that run would read.

−3,300 m — for people building AI agents

Your agents sit on top. We are the layer underneath.

Your agents write · plan · ship
◫ writer ◇ planner ⌗ coder ◍ analyst ⊞ ops ◈ support
Deep Water — the research layer reads · verifies · cites
The open record 83 languages · papers · filings
▤ pdf ▦ docx § papers ◷ news ▷ tv ▥ filings ⌸ patents ◰ standards ⊟ pricing ◎ ecommerce ↗ trends ✎ blogs ⌖ forums ▤ reports ◌ archives

An agent that ships work needs to know how it's done today.

Most guess from training data. What works now, what failed last year, what's different in Germany than in Japan — none of that is in there.

We do the reading first. Your agent gets facts with sources attached, before it starts working.

Audience

For your work

Research you can defend to a reviewer For researchers.
Every claim linked to a real source Non-English and scanned sources read too Conflicting findings surfaced, not averaged
The research layer your agent calls For developers.
One call in, structured findings out Evidence your agent can act on It can also see when there is no proof, and stop

For developers and researchers

Three ways in.

Pick the one you already use. One line and it's running.

In your own code01

Send us a question. We send the finished report back when it's ready, or you can watch it come in live.

On the command line02

npm install -g @unlikeotherai/deepwater deepwater research "EU battery rules 2026"

In your AI assistant03

npx -y @unlikeotherai/deepwater-mcp
Run your first research →

−4,100 m — the lamp turns on us / for researchers and scientists

Nothing here is hidden from you.

83 languages01 / 06 We read in 83 languages, not just English. The original text stays next to the translation.
Source type02 / 06 University, government, company, news, social media — written next to every citation.
OCR03 / 06 Scanned PDFs get read too, page by page.
Disagreement04 / 06 When sources disagree, we say so. We don't quietly pick something in the middle.
Reverse check05 / 06 Every citation is read back against its source. What doesn't hold up gets dropped.
Still there06 / 06 Every report keeps its sources, so you can go back and check next year.

−4,700 m — public or private

You decide who sees it.

Reports are published to our open library by default. That library is free for anyone to read — it's how you can look at hundreds of finished reports right now without paying anything.

If your work has to stay in your team, private research is $50 a month. Then nothing leaves your workspace.

−5,100 m — price

You pay for the work you order.

Not per person. Your team shares one pot of credits, and 1,000 credits is one dollar. A short report costs a little. A deep one costs more, because it reads more.

Before you start, we tell you how long it will take. You are charged for what the run actually used.

Everyone on your team can see what's left.

What one report costs

Small a quick answer 18 sources ~1,400 credits $1.40
Medium a proper summary 33 sources ~2,900 credits $2.90
Large the full picture 104 sources ~9,600 credits $9.60
Huge everything we can find 186 sources ~18,200 credits $18.20

Indicative — you are charged for what the run actually used, and we tell you how long it will take before you start.

−5,600 m — questions people ask

Q.01

Is it really checking, or just guessing better?

Every citation gets read back against the page it came from. What doesn't match gets dropped before you see it.

Q.02

How long does one take?

A quick one takes minutes. The deepest one takes a lot longer, because it's reading hundreds of pages. We show you the estimate before you start.

Q.03

What if I don't speak the language of the source?

We translate it for you and keep the original next to it, so you can always check.

Q.04

Can I see it before I pay?

Yes. Our open library is full of finished reports, free to read. Open one and click through the sources yourself.

Q.05

What can't it do?

It doesn't watch videos or listen to podcasts. It reads text — web pages, papers, and scanned PDFs.

Back up

Come back up with proof.

Ask your question. Get an answer you can show to anyone.