Evidence · context · receipts
Evidence for Agents
Give agents compact, citation-ready evidence about what changed, what launched, what people are arguing about, what is worth reading, and which narratives are emerging. Each receipt is a published record with a canonical link.
How to read a receipt
Cite the canonical URL
Open the Tech Twitter page on the receipt so another reader can inspect the same record.
Keep the attribution
Author, time, and topic belong with the statement they describe.
Do not invent access
These receipts are curated site evidence, not official X access.
- Mode
- Read only
- Form
- Receipts
- Cite
- Canonical URL
Record
receiptA published statement, not a generated answer
Each receipt identifies a published Tech Twitter record: title or source text, author when known, timestamp, topics, and a short reason it was included.
Citation
receiptA durable link another reader can open
Cite the canonical Tech Twitter URL on the receipt. Follow the original source when exact wording or media matters. A summary is a navigational aid, not a quotation.
Evidence lookup
live · read onlyAsk for recent receipts
This lookup reads published evidence on this deployment. It cannot mutate data, post to X, or expand the curated corpus into an arbitrary search of X.
Evidence readout
Ask the evidence index
Auto classifies the question, filters the recent evidence window, and returns ranked source records with canonical citation URLs.
- window
- 24h
- limit
- 5
- mode
- read
Citation rule
canonical URLCite the record, not a generated summary
A machine should attach the canonical URL to any claim it makes from a receipt. Rankings can show attention or disagreement; they do not establish truth or endorsement. If exact language changes the answer, open the original source before quoting it.
Scope
curatedEvidence from this site, not official X access
Tech Twitter watches a maintained set of public accounts and publishes only accepted records. This page is for reading those receipts. It is not official X access, a firehose of public posts, or a way to post, like, follow, or manage an account.
Use
citeReceipts need a citation, not a paraphrase-as-source
Prefer several independent posts before making a broad claim. Keep author, time, and topic attached to the text they describe. Absence of a receipt is not proof that an event did not happen.
FAQ
evidence · receiptsWhat is Evidence for Agents?
A page of citation-ready evidence, context, and receipts drawn from published Tech Twitter records. Each receipt points at a canonical page another reader can inspect.
Is this official X access?
No. Tech Twitter publishes its own curated evidence. It is not official X access, a firehose of public posts, or a way to act on someone else’s account.
How should an agent cite a receipt?
Use the canonical Tech Twitter URL attached to the receipt. Treat the text as evidence of a public statement, not as proof, consensus, or a generated answer.
What does a receipt include?
A title or source text, author when known, timestamp, topics, a short reason the item was included, and a canonical citation link. When stored analysis is available, it can also include evidence role, relative performance, conversation breadth, emerging-voice momentum, source breadth, and lineage with explicit coverage. A summary is a navigational aid, not a quotation.
Can an agent call Tech Twitter from inside the browser?
Yes, on a browser that supports WebMCP. Pages register read tools on document.modelContext, and the monitor grid adds two tools that move what the reader is seeing. Call document.modelContext.getTools() to discover the live set, and use the HTTP routes when WebMCP is unavailable.
What is out of bounds?
No posting, liking, following, accounts, or private data. A missing receipt is not proof that something did not happen. Rankings are discovery aids, not endorsements.