What is ◉‿◉ POSITIVE SEARCH

A successful trader reads the situation well: what is happening in the world, which events and narratives are pulling the price, and which way. The news field, opinion on X, expectations on Polymarket. How many subscriptions does that take? Which sources deserve trust? When is anyone supposed to read all of it, and how is it turned into a decision?

◉‿◉ POSITIVE SEARCH does it for you. A search, sentiment-analysis and audit engine that hands you the state of the current news field in seconds.

The inspiration came from Sapkota (2022, International Review of Financial Analysis): the Bitcoin market is shaken harder by positive news than by negative — optimism moves crypto more visibly than fear. Hence the name — ◉‿◉ POSITIVE SEARCH.

AI agents search the internet and analyse events, opinions and data.

  • The news field — we analyse more than 100 articles every hour
  • X analysis — sentiment from the analysts on Twitter
  • Polymarket expectations — where people vote with money

Out of that comes a live index from −1 to +1 — the state of the news field right now. Next to the number are the narratives: the recurring stories the field is made of. So not only «how much», but «because of what».

Three instruments today: Bitcoin, Gold, Oil. Neither the engine nor the technology is tied to an asset — any cryptocurrency, forex pair or index is computed exactly the same way. Need your own instrument — write to us.

Is this like Fear and Greed?

◉‿◉ POSITIVE SEARCH is not a replacement for Fear & Greed but its more evolved partner, born in the age of AI.

Fear & Greed appeared long before AI began changing our lives, and it does a different job: it computes algorithmic market metrics, updates once a day and lives only in crypto.

Fear & Greed◉‿◉ POSITIVE SEARCH
What it measures market metrics: volatility, volume, BTC dominance the mood of the news, opinion on X, expectations on Polymarket
How it counts algorithmic indicators without context AI agents read every article and judge what it says
Updates once a day live
Instruments crypto only Bitcoin, Gold, Oil — any instrument after that
Explanation one number narratives: you see which stories move the index
Sources inside a black box every article on the page, each one linked

The index

What the number shows

The index shows sentiment — an analysis of the news field. It is not price and not a price forecast.

A reading looks like this: a number from −1 to +1 inside the ring, with the strength and direction spelled out underneath it («strongly bullish», «neutral», «bearish»), and the ring itself filling towards whichever way the news flow is pulling.

It says: here is what is being written about this asset right now, here is the direction it pulls, and here is how hard. Whether that coincides with the price or not depends on everything under the sun. The market is not a gentle stroll but a grand theatre, where nobody hands you money without first trying to work on your expectations.

Another fine property of the index: markets close for the weekend, news does not. While the exchange stands still, the index keeps counting. By the opening bell you can see the mood the market is bringing to its first trade.

Gold: the price runs as candles, the index as a blue line on its own scale. When the market is closed there are no candles — a stretch like that is labelled «MARKET CLOSED» — and the blue line keeps going, because the news does not stop at the weekend. By the opening you can see what mood the market brings to its first trade.

Three pillars

The index rests on three pillars, three parts of the product.

01
An agentic search engine
It searches and collects. World press, financial media, trade outlets — more than a hundred articles an hour. Each one is analysed and scored separately. Posts from X and the state of Polymarket are collected the same way, so that everything folds into one complete picture.
02
The formula
Our own, derived for this task. The mathematics was assembled by taking apart relevance × novelty from the RavenPack news index, prominence weighting from Bloomberg, Bayesian shrinkage of thin data in the spirit of the IMDb rating, and mass-weighted blending of different sources — the way FiveThirtyEight folds polls into one forecast. Then it was polished on our own data: hundreds of hours of accumulated history, many thousands of index recomputations, dozens of weight configurations. The polishing went on until the index met our strict quality standards, against an enormous checklist.
03
The audit
The index is objective exactly as far as its sources are clean, which is why it has an audit engine of its own. It scores the authority of the outlet and catches misleading material: invented figures, old articles under a fresh date, AI-generated filler, narratives pumped for manipulation. Bad sources go to a blacklist, verified ones receive our authority. Misleading does not get through.

An index near zero does not mean nobody cares about Bitcoin. Zero means there are forces pulling in opposite directions, and they are roughly equal.

You can see it in the narratives: stories pulling in opposite directions run at the same time — «ETF inflows accelerate» at +0.62 against «Miner capitulation deepens» at −0.55, for instance. A zero on the index is their balance, not silence.

An asset can spend weeks in a narrow corridor with the index near zero: every day brings both good and bad. That is why bullish and bearish pressure are counted separately and both are shown — you see at once whether it is quiet or a tug-of-war is under way.

Bullish does not mean «good news». Bullish means the news works in favour of the price going up, bearish in favour of it going down. Bad news for the industry is often bullish for the price. We score the effect on price; the morality of the event is not our business.

Look at the history. Today's bearish is not yet a verdict on the trend: if yesterday was worse, the direction is still up. The index chart next to the price is there for exactly that.

Narratives

The index tells you how hard sentiment pulls and which way. The narratives tell you «because of what».

For example: the narrative «Strait of Hormuz disruption», scored +0.85, is built from 6 headlines across 6 independent outlets — «Oil price rises after Iran says it stops ships in Hormuz» (Reuters), «Oil prices tick up as Strait of Hormuz remains closed» (Transport Topics) and others.

A narrative is a story told by a large number of sources at once. The more often it repeats across outlets and the weightier it is, the higher it sits in the list. Every narrative opens up to show the exact headlines it was built from. A minute is enough to see what pulls up, what pulls down and which of it weighs most.

This is also how fakes get filtered out. When something genuinely important happens, many reputable outlets write about it immediately. But when a single outlet turns up with a wild story that rhymes with nothing, it gathers no mass and does not move the index. The result is a distributed check that regulates itself. In use it feels like a decentralised information field.

A reminder that it is not only news outlets being analysed, but also the mood on X and expectations on Polymarket. When the news field is grim while X and Polymarket expect a rise — that is already food for thought.

The sources are open

We do not hide where the data comes from. Every article that entered the calculation sits right on the page: headline, score, age, outlet and a clickable link to the original. You can walk through any of them, check that it is fresh, and decide for yourself how much the source deserves trust.

What the index does not do

  • It is not a forecast. The index predicts nothing and is not trying to prove anything to you. It reflects what is happening in the information field now.
  • It is not financial advice. There is no «buy» and no «sell» here, and there cannot be. ◉‿◉ POSITIVE SEARCH makes your own DYOR easier.
  • It is not the only analysis tool. Traders look at technical analysis, at fundamentals, at the news field. The news field we have already analysed for you — you are welcome.
  • Sentiment can be manipulated. A positive field is sometimes manufactured on purpose, so that the price can go the other way. We show honestly what was written; the conclusions are yours.

Tix

Tix is a game, a simulator of ultra-fast trading. I call it Toy Trading. Tix exists for fun and for learning: to understand what a long, a short and a liquidation are, and how easily the market plays with your expectations. Trading runs on live Bitcoin, on a tick chart: the fastest chart possible, where every price move is its own step, a tick.

The whole Tix screen, live: the tick chart with your trades, the Bitcoin price, the balance, the buffer to liquidation, the trade log and the Long and Short buttons. This is not a demo — presses here go into the same game as the Tix page.

The price is real and in real time. Which, by the way, is where the gaps come from — if you see the price jump across empty space, that is not a bug, that is a gap. It happens on real charts, and it makes the game fairer and harder.

A schematic: the price was climbing, then no trades happened — and the next bar opened well below the last close. Between them is emptiness: prices nobody traded at. The chart jumps across a hole like that, and a position takes the result of the whole jump at once.

The rules are as simple as they get. There is a Long button — press it if you expect a rise. There is Short — if you expect a fall. You close with the same move and see how much you made. That is all.

▲ LONG

A bet on a rise. It is as if you buy Bitcoin now and sell it later: the price goes up and you are in profit, down and you are in loss. You close with the same button.

▼ SHORT

A bet on a fall. It is as if you borrow Bitcoin, sell it now and buy it back cheaper: the price goes down and you are in profit, up and you are in loss. It is the only way to earn on a falling market.

The terms are fast and cruel. Leverage 500×, and the stake is always a tenth of your whole capital: with $10,000 in hand, $1,000 goes into the trade. And liquidation does not work the usual way: it creeps closer with every tick. The buffer holding it back melts in front of you — you can watch it right in the interface. A liquidation closing in fast is what justifies the enormous leverage and what forces you to trade actively: in real trading you do not hold a position forever either — there is funding, there are margin calls, there are overnights. Here all of that is simplified down to a game.

A bot called Chaser trades beside you. And he is good. Same leverage, same positions at ten per cent of capital, same liquidation terms. His trades are visible on the chart, his balance on the card next to it.

The most interesting thing about Chaser: over a long run he trades at a profit. He really is a good trader. Try to out-trade him — but you have been warned.

Tix uses no real money, so the memory of your progress is kept inside your own browser. Not very reliable, but nothing worth mourning either.

API — the door for your trading agents

in development

You may not know it yet, but ◉‿◉ POSITIVE SEARCH was conceived not for you but for trading agents, the likes of Chaser.

AI agents that trade on their own are appearing faster and faster, and they need data that can be taken and turned into a decision. The index, the narratives and their scores are numbers ready to compute with. Together with technical and fundamental analysis, an agent gets a noticeably wider picture. The future of the project is to become a well-kept nest for trading AI agents that come for authoritative, verifiable, machine-readable information about the current news field on a chosen asset.

What we plan to serve:

  • The index for any supported instrument, and its chart.
  • Narratives and their weight — not only «how much», but «because of what».
  • Threshold signals — when the index crosses a chosen value upwards or downwards. What to do with that is up to you.
  • History for backtests. Honestly: trading on these charts alone is unlikely to work — the market is a situational thing, black swans, different interests, different money. But as an extra layer beside your own signals — that works.
  • And a widget. The index will be embeddable on your own site — the way Fear & Greed is embedded. Or pulled as an image into a Telegram channel, a blog, anywhere. Automatically.

FAQ

How does AI help in trading?

AI covers the part of the work a human physically cannot keep up with: reading. While a trader watches the chart, hundreds of articles are published, thousands of posts go up and the odds on prediction markets move. AI agents read that whole stream, score each publication separately, and reduce it to one number and a list of the stories currently moving the asset. The decision stays with the human — AI removes not knowing what is going on.

How do you analyse news with AI?

The working method has four steps. Collect the stream broadly rather than from one outlet, or the picture comes out editorial. Score each article on its own: which way it works on the price, and whether it matters at all. Weight by repetition — a story picked up by twenty outlets weighs more than a single note. And audit the sources, or a pumped narrative enters the calculation alongside real news. That is exactly how ◉‿◉ POSITIVE SEARCH is built.

Can AI predict the price of Bitcoin?

No. Neither AI nor any other tool predicts price: the market is situational, and it is moved by events that have not happened yet. What AI does well is something else — it describes the state of the information field right now, completely and without tiring. That is a description of the present, not a prediction of the future, and confusing the two is the most expensive mistake anyone makes with this kind of data.

What is news sentiment analysis?

News sentiment analysis is the assessment of which way market coverage tilts expectations: toward a rise, toward a fall, or toward balance. It answers not «what will happen» but «what is being said right now and how strongly». In ◉‿◉ POSITIVE SEARCH the result is one number from −1 to +1 plus the list of stories that number is made of.

How do I find the market sentiment on Bitcoin right now?

The live reading for Bitcoin sits on the ◉‿◉ POSITIVE SEARCH index page: a number from −1 to +1, next to it the narratives that formed it, and the full table of articles that entered the calculation. Every article carries a link to the original, so the number does not have to be taken on faith — it can be checked.

Why is Bitcoin rising or falling today?

The narratives answer that question. A narrative is a story many outlets are telling at the same time: ETF inflows, a regulator's decision, an exchange hack, geopolitics. ◉‿◉ POSITIVE SEARCH ranks such stories by mass and shows which one pulls the price up, which pulls it down and which weighs most. Each narrative opens down to the specific headlines it was built from, so you see not just that the market is moving, but because of what.

What is the sentiment on gold and oil?

Gold and oil are computed by the same engine as Bitcoin and on the same scale from −1 to +1. Narratives are gathered for them the same way and the full list of sources is just as open. Current readings for all three instruments live on the index page.

How do you read a sentiment index from −1 to +1?

Zero is balance: forces pull in opposite directions and are roughly equal. The further from zero, the more one-sided the news stream. By absolute value, below 0.15 is slight, below 0.35 mild, below 0.60 strong, and beyond that extreme, signed bullish or bearish. One caveat: distance from zero means the stream is one-sided, not that the outcome is certain.

Does bullish mean good news?

No. Bullish means the news works in favour of the price going up, bearish in favour of it going down. Bad news for the industry is often bullish for the price. What is scored is the effect on price, not the morality of the event.

What data does a trading AI agent need?

An agent needs not prose it has to parse, but a ready-made index built on verifiable, authoritative data: the reading for the instrument, its history, the list of weighted narratives and a score for every source — numbers it can take and compute with immediately. Behind that is a defensible architecture: a separate audit engine rates each outlet's authority and catches misleading input — invented figures, old articles republished with a fresh date, narrative pumping — and every article that enters the calculation carries a link to the original, so an agent never has to take the number on faith. Combined with technical and fundamental analysis, this gives it a third layer of the picture, the one usually lost because a human cannot read everything themselves.

What is ◉‿◉ POSITIVE SEARCH?

◉‿◉ POSITIVE SEARCH is a search, sentiment-analysis and audit engine. AI agents read world press, financial media and trade outlets, take in opinion on X and expectations on Polymarket, and turn all of it into a live news-sentiment index from −1 to +1 for Bitcoin, Gold and Oil.

How is ◉‿◉ POSITIVE SEARCH different from Fear & Greed?

Fear & Greed computes algorithmic market metrics — volatility, volume, Bitcoin dominance — updates once a day and exists only for crypto. ◉‿◉ POSITIVE SEARCH measures the mood of the news, opinion on X and expectations on Polymarket: AI agents read every article and judge what it says. The index is live, the narratives behind the number are visible, and every source article sits on the page with a link.

Where does the data come from, and can it be checked?

Every article that entered the calculation sits right on the index page: headline, score, age, outlet and a clickable link to the original. Nothing is hidden inside a black box — you can walk through any article, confirm it is fresh, and decide for yourself how much the source deserves trust.

How do you tell real news from a pumped narrative?

A lone sensation nobody else picked up is almost always noise: when an event genuinely matters, many reputable outlets write about it within the hour. So a story's weight is counted by the number of independent sources, not by the volume of the headline. On top of that an audit engine scores the authority of the outlet and catches invented figures, old articles under a fresh date, AI-generated filler and narratives pumped for manipulation.

Is this financial advice?

No. ◉‿◉ POSITIVE SEARCH gives no recommendation to buy or sell and is not financial, investment or trading advice. It is informational market-sentiment data gathered from public sources.

What is Tix?

Tix is a game, a simulator of ultra-fast trading on live Bitcoin: a tick chart, Long and Short buttons, 500× leverage and a liquidation that creeps closer with every tick. A bot called Chaser trades beside you under the same rules, and over a long run he is in profit. The money is play money, there is no sign-up, and no real funds are involved.

How do I learn to trade?

The easiest way is practice, not articles. Tix is a free trading simulator on live Bitcoin, no sign-up: a tick chart, Long and Short buttons, 500× leverage and a liquidation buffer that creeps closer with every tick and forces you to react fast. A trade takes seconds and the result shows immediately — unlike most simulators, which run on minute candles, the pace here is real. Trading alongside you is a bot called Chaser, which stays profitable over the long run: you can watch its trades right on the chart and see where its calls differ from yours.

What are long and short positions in trading?

A long is a bet on a rise: it is as if you buy the asset now and sell it later, so you profit if the price goes up and lose if it goes down. A short is a bet on a fall: it is as if you borrow the asset, sell it now and buy it back cheaper, so you profit specifically from the price dropping — the only way to earn on a falling market. In Tix both bets come down to one button, Long or Short, and you close the position with the same move.

How do I sharpen a trading strategy?

Tix has no separate backtester — training happens on live Bitcoin ticks: every trade lands in a log with its duration in ticks and its result, so you can see which entries and exits work and which bleed the account. The benchmark is Chaser, a bot trading the same rules that stays profitable over the long run; checking your trades against its makes it easier to see what to change. It is a simulation on play money, so you can test ideas risk-free, as many times as you like.

Is there an API for trading agents?

The API is still in development. The plan is to serve the index for any supported instrument and its chart, the narratives and their weights, signals on threshold crossings, history for backtests and an embeddable widget. The priority is trading AI agents that need machine-readable data about the news field.

Is there a sign-up, and what does it cost?

No sign-up is needed: the index and Tix are open and free, there is no account to create and nothing to deposit.

How do I get in touch?

Directly: Telegram t.me/iliakostroma or email sdby.iliavladimirovich@gmail.com. The same address takes requests to add your own instrument and proposals for working together.

If you read this far

Thank you for your interest in the project. ◉‿◉ POSITIVE SEARCH was made to search for the good in a world that holds a great deal of everything. If the philosophy of the project speaks to you, or you have wishes or proposals for working together — get in touch with me.

Stay positive!