The Verdict
Put a claim to an impartial AI judge that reads the world and rules, on-chain.
Invite-gated: Ritual's testnet faucet needs a Discord invite. Get the invite, then contact us and we set you up. Not sold in the normal flow yet.
Try it live, freeThe working app on your own wallet and git, one-click deploy, and the step-by-step guide that makes you the verifiable developer.
Reshape it entirely: new features, your flows, your brand end to end, integrations you need. We scope it with you.
The complete Sentiment Oracle app: one community question scored each day by an AI model on Ritual Chain, weighted against brigades, published with confidence and a stale flag so a vote contract only acts when it is sure. Invite gated while Ritual's testnet needs a Discord invite.
Every buyer gets the same finished app. Basic branding and copy changes come through a quick form.
Your admin side: revenue, paywall editor, users, rules and the agent log.
Referral and growth mechanics, switched on when you are ready to grow.
Builders read yesterday's score free. Communities that act on the feed pay monthly for live readings, and tuned single community feeds are priced as custom.
No per read fee in v1. On Ritual testnet calls cost test tokens; mainnet inference fees are not public yet.
Prices are yours to set. Illustrative, not a promise of income.
A daily, verifiable community mood score that contracts can read, with confidence so they wait when the room is being brigaded.
Problem: Community funds and DAOs want to act on member sentiment, but raw counts are easy to brigade and offchain dashboards are not verifiable.
Solution: One fixed question, agreed sources, weighting by account age and dedupe, scored by a model on Ritual Chain and published with confidence and a stale flag.
Why now: Ritual makes model inference callable from contracts, so a sentiment score can be both verifiable and usable onchain.
Market: Neighbourhood funds, DAOs and online communities that vote on spending.
The ask: Ritual testnet access for pilots with three community funds in Lisbon and Porto.
Funding is never guaranteed. Check each program's rules.
Many hackathons require code written at the event. See the Regatta Boardfor each race's rule.
Custom work from $300: your community's question and sources, tuned weighting, a consumer contract for your vote, or chat integrations. Scoped on a call.
Communities make decisions with onchain votes and treasuries, but contracts are blind to how people actually feel. Votes close while the street is still arguing, and a few hundred fresh accounts can drown out real members.
Sentiment data already exists as offchain services (for example LunarCrush and Santiment) and as general AI oracle designs from Ritual, Ora and Chainlink Functions calling model APIs. Ritual Chain lets contracts request model inference natively. What is different here is a narrow, single question feed for one community, with a confidence value, a stale flag, account age weighting against brigades, and a public accuracy log that contracts and members can check. The idea is a careful packaging, not a new primitive.
Public posts from sources the owner chooses (a forum, a Farcaster channel, an exported chat), account age per author, a fixed prompt, and the daily score, confidence and timestamp. Raw posts and usernames stay with the owner; only fingerprints of the prompt and input bundle go onchain with the score.
Let community contracts listen before they act, and wait when they cannot hear clearly.
One honest number A single daily score with a confidence, instead of a dashboard nobody reads.
Brigades do not win Weighting by account age and removing duplicates keeps a flood of new accounts from deciding a vote.
Guess Monday's mood Members guess the score each Sunday and check the accuracy log, which keeps the feed honest and people coming back.
Collector: A small worker pulls new posts from the chosen sources at the set cadence, removes duplicates, attaches account age and builds one input bundle.
Inference on Ritual Chain: The feed contract requests an LLM call through Ritual's native AI inference with a fixed prompt, asking for a score from 0 to 100 and a confidence.
Feed contract: Stores score, confidence, timestamp, prompt fingerprint and input fingerprint. Exposes a read function that returns a stale flag after 30 hours.
Consumer contract: The community's vote contract reads the feed and follows a rule, for example extend discussion 48 hours when confidence is under the floor.
Accuracy log: An indexer records each score next to the later vote result and publishes it as a public page.
Bot: Posts the morning reading and three quotes to the community chat, and runs the Sunday guess.
On Ritual testnet, calls cost test tokens only; access to the testnet faucet currently needs a Discord invite, which is why this app is not in the normal flow yet. On mainnet, inference fees are not yet public, so treat any number as unverified. A comparable offchain model call on a small model costs well under one cent per daily bundle. Example: daily readings at an assumed $0.05 per onchain request plus $10 hosting is about $12 a month.
Every held vote and every accurate week is a story a community shares. The public accuracy log sells the feed to the next community better than any pitch, and each new reader contract is a visible integration.
Wrong or biased scores: Models misread sarcasm and local language. Always publish confidence, keep the accuracy log public, and never let a contract move money on mood alone.
Brigading: New accounts can flood the sources. Weight by account age, dedupe repeats, and hold below a confidence floor.
Privacy: Only read public posts or exports members agreed to. Never write posts or usernames onchain.
Testnet access: Ritual's faucet needs a Discord invite today, and the network is pre mainnet, so costs and behaviour can change.
Stale data: If a call fails, the feed must say so. The stale flag stops contracts reading old numbers as fresh.
Costs and tools are estimates at the time of writing. General information only, not legal or financial advice.
Nine routes from one vessel. Tap a port to open its chart.
Sentiment Oracle is a contract on Ritual that asks an AI model a question onchain and stores the answer where any other contract can read it. If you use someone else's oracle, their deployer address gets the builder record and their feed gets the integrations. Own it, and the deploy, the verified source and every app that reads your feed point back to your wallet and your name.
You do not need to write the contract. The app ships with a one-click deploy and a written guide that walks you through funding a wallet, deploying and verifying. You will paste values and press buttons. If you want to change the logic later, that is when code matters, and you can hire for it.
That is real and it is the main blocker today. Join the Ritual community, be useful in the builder channels for a few days, and ask for a faucet invite plainly. Once you have it, contact DEPLOYR and we set you up. Until then this app is not sold in the normal flow.
Yes. It deploys from your wallet, the code lives in your git, and the verified contract shows your address as the creator. DEPLOYR does not hold keys or a backdoor.
No one can promise that. Ritual has not promised any reward for deploying, and airdrops are never guaranteed. What you get for sure is a real, verifiable deploy on a new AI chain, which is useful for your portfolio either way.
That is the likely start. Most oracles begin with one consumer: you. Build a tiny demo contract that reads your feed, publish it, and then pitch it to two or three small projects. Usage is earned one integration at a time.
Projects pay to read a curated sentiment feed (for example a daily score on a token, a topic or a governance proposal) through a monthly subscription or per-call fee, plus custom feeds built to order. Revenue only comes if real apps depend on your feed, so this is a target, not a promise.
Illustrative stages, not a forecast. Results depend on you and the market; nothing here is guaranteed.
Put a claim to an impartial AI judge that reads the world and rules, on-chain.
Teach an AI agent your craft, and every time it earns, you earn as the teacher of record.
An AI that guards your inbox and DMs and charges strangers a fee you keep to reach you.
Give your AI agent a wallet with house rules it literally cannot break.
Pay three independent AIs a few cents to check one answer, and get a signed receipt of agreement.
Your personal AI memory, owned by you, rentable to any assistant you choose.
AI labs pay you to rank their outputs, and your taste builds an onchain reputation.
A public, verifiable work history for any AI agent, built from the jobs it actually finished.