# Asks

#### 1) ClaimCheck API (General Fact Oracle)

* **What it does:** Given a natural-language claim + optional URL/context, Cortensor runs the same “fact-check prompt” on multiple miners and returns:
  * `true/false/uncertain`
  * reasoning + citations
  * dispersion score (how much miners disagree)
* **Users:** Any app/site that wants a “verify this claim” button or API.

***

#### 2) DAO / Governance Proposal Fact Oracle

* **What it does:** For a DAO proposal text, miners answer structured questions:
  * “Are the background claims accurate?”
  * “Are key risks omitted?”
* Validators compare miner answers and produce a **governance report** (plus PoI-style score).
* **Output:** On-chain “fact-check artifact” that DAOs can reference before voting.

***

#### 3) News & Social Media Post Verifier

* **What it does:** Takes a tweet / post URL and asks multiple miners:
  * “Is this claim supported by reputable sources?”
  * “Summarize arguments for/against.”
* Uses consensus + validator scoring to tag posts as `supported`, `disputed`, or `unknown`.
* **Variant:** Browser extension that calls Cortensor in the background.

***

#### 4) Research Paper / Article Fact Scanner

* **What it does:** Upload a PDF or paste an article, then:
  * Split into claims.
  * Run each claim through redundant miners with a “verify & suggest citation” prompt.
* **Output:** A report marking:
  * ✅ well-supported
  * ⚠️ ambiguous / needs citation
  * ❌ likely incorrect\
    Great for blog posts, research summaries, or newsletters.

***

#### 5) Code-Change Risk Oracle

* **What it does:** Given a PR diff + repo context:
  * Miners classify risk level, list potential bugs and security issues.
  * Validators compare outputs and score agreement.
* **Use of multi-miner:** Same input to many miners with slightly different rubrics (security, performance, readability) → aggregated “risk report” for devs before merge.

***

#### 6) Contract / Terms-of-Service Explainer + Reality Check

* **What it does:** Upload a smart contract or ToS:
  * Miners summarize key points and **check for misleading marketing claims** vs the actual text.
* **Facts used:**
  * “Does the document *actually* guarantee X?”
  * “Are there hidden fees/clauses?”\
    Great for DeFi users and SaaS buyers.

***

#### 7) “Agent Watchdog” – AI Output Verifier

* **What it does:** Any existing AI agent (trading bot, research agent, etc.) sends its *own* answer + context to Cortensor.
* Cortensor miners re-run the task and:
  * confirm / dispute the agent’s answer,
  * assign a trust score,
  * highlight risky recommendations.
* **Variant:** On-chain guard that must sign-off (via Cortensor oracle) before a high-risk action is executed.

***

#### 8) Multi-Source Market Narrative Checker

* **What it does:** Input: “Why is BTC down today?” (+ timestamp / tickers).
* Multiple miners:
  * pull from allowed news/feeds (or provided text),
  * verify whether common narratives (“ETF flows”, “regulation X”) are actually supported.
* **Output:** Ranked possible explanations, with a “confidence” derived from miner agreement.

***

#### 9) “Proof of Reading” / Summary Verifier

* **What it does:** For education or compliance:
  * User submits their summary of a document/video.
  * Miners check: “Does this summary faithfully reflect the source?”
* **Use of consensus:** Multiple miners rate faithfulness; validator aggregates into a final score and feedback.

***

#### 10) On-Chain Truth Widgets (Simple Yes/No Oracle)

* **What it does:** Minimalist contracts that ask structured, binary questions like:
  * “Did event X occur before date Y?”
* Cortensor:
  * runs the question through multiple miners,
  * validators score agreement and evidence quality,
  * pushes an **attested boolean result** on-chain for other protocols to use.


---

# Agent Instructions: Querying This Documentation

If you need additional information that is not directly available in this page, you can query the documentation dynamically by asking a question.

Perform an HTTP GET request on the current page URL with the `ask` query parameter:

```
GET https://docs.cortensor.network/community-and-ecosystem/hackathon/hackathon-3/asks.md?ask=<question>
```

The question should be specific, self-contained, and written in natural language.
The response will contain a direct answer to the question and relevant excerpts and sources from the documentation.

Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.