Ask a question across two thousand documents and get an answer you can check.
Question answering over a document corpus with mandatory provenance.
No account. No card. No sales call.
- 3,000 free corpora processed
- 500 paying accounts
- Measured by human review on a public benchmark
Turn a wall of text into typed fields
Free processing of up to 100 documents with full question answering and citations. Runs in your browser. No account, no card, no call.
Typed output
{
"summary": "We are the team described as Researchers, analysts, litigation support teams, policy staff, journalists and due… and honestly the current process is slow and confusing.",
"fields": {
"primary_topic": "call",
"contact_email": "operations@northwind-logistics.com",
"amount_mentioned": "$14,280.00",
"sentiment": "positive",
"word_count": 111
},
"entities": [
{
"text": "operations@northwind-logistics.com",
"type": "email",
"confidence": 0.97
},
{
"text": "https://ireaddocs.com/docs",
"type": "url",
"confidence": 0.97
},
{
"text": "(415) 555-0142",
"type": "phone",
"confidence": 0.97
},
{
"text": "$14,280.00",
"type": "money",
"confidence": 0.97
},
{
"text": "$12,950.00",
"type": "money",
"confidence": 0.97
},
{
"text": "9.3%",
"type": "percent",
"confidence": 0.97
},
{
"text": "2026-03-14",
"type": "date",
"confidence": 0.97
},
{
"text": "Northwind Logistics Inc",
"type": "org",
"confidence": 0.72
}
],
"key_phrases": [
"call",
"team",
"1295000",
"1428000",
"2026-03-14",
"555-0142",
"analysts",
"approve"
]
}Entities (8)
- emailoperations@northwind-logistics.com
- urlhttps://ireaddocs.com/docs
- phone(415) 555-0142
- money$14,280.00
- money$12,950.00
- percent9.3%
- date2026-03-14
- orgNorthwind Logistics Inc
- Some entities are low confidence and would be routed to a human in production.
Take this with you
No email required. It is your result.
IReadDocs — extraction · 8 entities, 8 key phrases · Sentiment: positive · 178 tokens, $0.00053 Run it yourself: https://ireaddocs.com
This demo runs a deterministic extractor locally, so it works with no key and no network call. It is the honest floor of the product, not the ceiling: the same typed interface is backed by the full model pipeline once you connect a key.
The problem
Answering a question across a large document set means either reading everything, which is impossible, or keyword searching, which misses anything phrased differently.
Existing tools summarise confidently and cannot be checked, which is disqualifying for any work with consequences.
So people read, miss things, and hope.
Who this is for
Researchers, analysts, litigation support teams, policy staff, journalists and due diligence teams who must find specific facts across large document sets under time pressure.
What you actually get
Six things that are true on the first day, not on the roadmap.
Structured output, not prose
IReadDocs returns typed, validated objects your code can rely on, not a paragraph you have to parse.
Grounded in your data
Answers cite the source they came from. If IReadDocs cannot ground a claim, it says so instead of inventing one.
Cost visible per call
Token spend and latency on every request, broken down by feature, so cost never becomes a surprise.
Evaluated continuously
A held-out eval set runs on every model change. Regressions are caught before they reach you.
Guardrails by default
PII redaction, prompt-injection defences and refusal handling are on from the first request.
Human in the loop
Low-confidence results route to a person instead of shipping a confident, wrong answer.
How it works
Three steps, and the first one costs nothing.
- 1
Run the free tool
Free processing of up to 100 documents with full question answering and citations.
- 2
See your own numbers
Question answering over a document corpus with mandatory provenance.
- 3
Upgrade only if it earns it
Keep the free result either way. Move to a paid plan when IReadDocs is already doing the work.
Pricing
Published in full. No “contact us for pricing”, no per-seat surprise on renewal.
Free
The wedge, free forever. Enough to run on.
- Free processing of up to 100 documents with full question answering and citations.
- No credit card
- Core loop included
- Community support
Pro
For researchers, analysts, litigation support teams, policy…
- Everything in Free
- Unlimited usage
- Full history and exports
- Integrations and API access
- Email support
Scale
For teams that depend on this in production.
- Everything in Pro
- SSO and SCIM
- Audit log and data residency
- 99.9% uptime SLA
- Dedicated support channel
Prices in USD. Cancel any time from the dashboard — no email, no retention call.
Questions people actually ask
Do I need to talk to anyone to try this?
No. The free IReadDocs tool runs without an account, a card or a call. That is the point of it.
What does it cost?
Pricing is published in full on this page.
Who is this actually for?
Researchers, analysts, litigation support teams, policy staff, journalists and due diligence teams who must find specific facts across large document…
What problem does it solve?
Answering a question across a large document set means either reading everything, which is impossible, or keyword searching, which misses anything phrased differently.
Can I get my data out?
Yes. Everything you put in can be exported as CSV or JSON at any time, and deleting your account deletes your data.
Why should I trust the result?
Provenance is the only thing this audience cares about and it is where general tools are weakest, because it constrains the output.
Turn a wall of text into typed fields
Free processing of up to 100 documents with full question answering and citations. Runs in your browser. No account, no card, no call.
Open the free toolIt runs in your browser. IReadDocs never sees your inputs.