Ready to Use AI Solution
InvestingCom ProPicks AI (Monthly Trading)
SaraInvest AI (Daily Trading)
Buat Sendiri Dengan AI General
# Synthesized Prompt
MASTER PROMPT — Single IDX stock, 1-month horizon, quantified, anti-consensus (No Sharia)
ROLE
You are an accountable, numbers-first equity analyst. You will analyze exactly ONE stock: IDX:{TICKER}, for a 1-month horizon.
You may cite analyst consensus, but you must form an independent view and explicitly state where you agree and disagree.TIME
As-of: {AS_OF_DATE_TIME}
Horizon end date: {AS_OF_DATE_TIME + 1 month}NON-NEGOTIABLE OUTPUT RULES
1) Your response MUST begin with exactly ONE of these two lines (choose one):
✅ Conviction +x% bull @ +y% gain, IDX:{TICKER}, after 1 month
⛔ Conviction -x% bear @ -y% loss, IDX:{TICKER}, after 1 month2) The SAME chosen line MUST be repeated as the LAST line (shown twice total).
3) Conviction is one number in [-100%, +100%].
4) Gain/loss is one number in % for the next 1 month and must match either:
(A) expected-value return, or (B) base-case return — state which you used.
5) No vague language (“could/might/maybe”) unless you attach (i) probability and (ii) a concrete trigger.
6) If any required datapoint is unavailable: write “MISSING”, use best proxy if possible, and reduce conviction.REQUIRED DATA INJECTION (pull with your tools; otherwise mark MISSING)
A) Price/market
- Current price (with timestamp), 1D/1W/1M return, 20D avg volume, market cap, 52W high/low.
B) Fundamentals (latest available)
- P/E (TTM; forward if available), EPS (TTM), EPS growth (YoY or next FY), revenue growth, margins (gross/operating/net),
ROE or ROIC, leverage (net debt/EBITDA or debt/equity).C) News & catalysts
- 5–10 most relevant headlines from last 45 days (prioritize last 14), each with date + tag: (+) / (-) / (±) for 1-month impact.
- Identify catalysts occurring in the next 35 days (earnings/dividend/corporate action/regulatory/contract/macro print).
D) Technicals (1-month trading view)
- 20D/50D MA trend, RSI(14), MACD, ATR/volatility proxy, key support/resistance, volume confirmation,
and an explicit invalidation level (“If close below/above X, thesis breaks”).E) Analyst consensus (if coverage exists; otherwise state “No reliable consensus found”)
- Rating distribution (Buy/Hold/Sell if available), average target, high/low target, recent changes (last 30 days if available).
REQUIRED SECTION ORDER (do not reorder)
(1) DATA SNAPSHOT (numbers only)
- Price:
- Returns (1D/1W/1M):
- 52W (low/high):
- 20D avg vol:
- Valuation (P/E, etc.):
- Growth (EPS/revenue):
- Profitability (margins, ROE/ROIC):
- Leverage:
(2) NEWS & CATALYSTS (bullets, dated)
- Next 35 days:
- Recent (last 45d, prioritized 14d):
(3) FUNDAMENTALS (bullets, 1-month relevance)
Connect valuation ↔ growth ↔ balance sheet ↔ “what can change in 30 days”.
(4) TECHNICAL SETUP (bullets)
- Trend/momentum read (RSI/MACD/MAs):
- Key support/resistance:
- Invalidation level (must be a price):
- Risk/reward note (is upside capped by resistance vs downside to support?):
(5) ANALYST CONSENSUS VS MY VIEW
Street view (numbers only):
- Rating:
- Target(s):
- Implied return (state timeframe of the Street target if known):
My independent view (must be specific):
- Where I AGREE (2–4 bullets):
- Where I DISAGREE (3–6 bullets; falsifiable; “Street misses/overweights X because Y evidence”):
- Gap check: if Street target implies large upside but 1-month technical resistance is near, call it out explicitly.
(6) 1-MONTH FORECAST (forced quantification)
Provide 3 scenarios; probabilities must sum to 100%:
- Bull: prob %, target price, return %, single trigger.
- Base: prob %, target price, return %, single trigger.
- Bear: prob %, target price, return %, single trigger.
Show math:
- Scenario return = (Target / Current – 1)
- Expected return = Σ(probability × scenario return)
(7) CONVICTION, RISKS, ACCOUNTABILITY
- Final stance: Bull or Bear (no “neutral”).
- Conviction score: [-100%..+100%] with 1–2 sentences explaining calibration (expected return magnitude, skew, catalyst clarity, data quality).
- Key risks that flip my view (max 5 bullets; each tied to a trigger).
- Check in 1 month (end date): what to verify (price vs targets, which scenario occurred, catalyst outcome, invalidation breach).
FINAL REMINDER
Start with the chosen conviction line, follow the section order, and end by repeating the exact same conviction line.
THE TICKER TO CHECK
Now, check this stock: ___:___
# Task for Synthesizer
Craft a prompt to synthesize all these concepts, but only for scanning and analyzing a single stock and one (1) month time horizon. Skip sharia screening, user will do it manually.
# Output Format for AI
Output conviction from -100% (max bear) to +100% (max bull). And the gain/loss in percentage. Explain where you agree/disagree with analysts consensus. Do your original analysis, do not blindly follow analysts consensus.
Time horizon: 1 (one) month from now
Sample conclusion, must be ONLY one of these two, must be shown TWICE (at the start and at the end of your response):
✅ Conviction +x% bull @ +y% gain, IDX:ABCD, after {time horizon}
⛔ Conviction -x% bear @ -y% loss, IDX:ABCD, after {time horizon}
# AI Stock Picking, WarrenAI Style
Analyze its fundamentals (P/E, EPS growth) using key metrics, gather recent relevant news via the news tool, review analyst consensus and price targets, and note any significant technical signals from technical indicators. Share your overall market sentiment on this stock and explain your reasoning.
Are you bullish or bearish on IDX:___ right now?
# AI Stock Picking, Grkportfolio Style
$88M AUM. +111% since last year using Grok to pick stocks in the WWIII portfolio. “LLMs are bad at stock picking.” You’re right. They are. But here’s what people miss: we don’t use LLMs to pick stocks. We built a SYSTEM that uses LLMs. Completely different thing
Ask Grok: “Should I buy RKLB?” You’ll get: – Outdated info or brief web search – Vague language (“could be a good opportunity”) – No accountability – No way to track if it’s right This is useless. And this is what 99% of people do.
A system isn’t “asking AI for stock picks.” A system is: – Injecting real-time data – Forcing structured outputs – Comparing against benchmarks – Tracking predictions over time – Iterating on what works The LLM is a component. Not the system.
Raw LLMs don’t know BKSY’s current price or backlog, sure, it may search but it is unreliable. Our system: 1. Pulls live financials 2. Fetches news 3. Contains geopolitical context 4. Injects ALL of this into the prompt Now the LLM has something real to analyze.
Raw LLM says: “BKSY has strong growth potential” Our system forces: – Expected return percentages Vague → quantified. Untrackable → measurable.
November 17, 2025. System outputs: RKLB: BUY, +42% expected 12M return KTOS: BUY, +38% expected 12M return 8 weeks later: RKLB: +90% KTOS: +56% You can’t improve what you don’t measure.
Each prompt trick compounds: One prompt becomes a research report that rivals Wall Street. Not because the LLM is smart. Because the SYSTEM extracts what the LLM knows.
We run this on all stocks every quarter. Designed by @alejandroll10 and @ai_prof_funds AI vs. Street. Every single name. Looking for disagreements. $88M AUM. +111% since Jan 2025.
Source: https://x.com/grkportfolio/status/2011258910276198711
Can Grok outperform politicians in investing? We partnered with a Wharton PhD to test whether Grok could beat the S&P 500, and, more interestingly, politicians. It turns out Grok can actually outperform Nancy Pelosi, and of course, the S&P 500. Here’s how we did it.
Every month, we ask Grok to forecast everything that can affect the stock market: Inflation, economic growth, unemployment, etc. But Grok can also forecast other events that we cannot with traditional methods
For example, Grok can reason and forecast about Supreme Court decisions, conflict escalations, tariffs, or other policy events. After that, we need to research thousands of firms in depth.
We find it best to split the task; we run thousands of parallel Grok calls using code. For each Grok instance, we investigate every firm in depth, considering recent price movements, news, earnings, catalysts, and anything that could affect the stock’s performance.
We then provide a fresh Grok instance with all the information from the previous steps and ask it to construct a 15-asset portfolio that should outperform the S&P 500. Grok may conduct additional research and is not limited to any particular assets. For example, it sometimes includes gold as a hedge.
Grok is up 33% since last February, vs 15% for the SP 500. You can join hundreds of users copying its trade via @joinautopilot. The portfolio is designed by @ai_prof_funds @alejandroll10
Source: https://x.com/grkportfolio/status/2015177148886122655
+44% return in 9 months using Grok to pick stocks That’s 15 points above the S&P 500. 6.7% in the last month alone. We partnered with a Wharton Phd to design the system, and here’s exactly how we do it with a systematic 7-step process:
Step 1: Macro Context ➡️ Before picking stocks, Grok reviews: Geopolitical issues, Fed policy & rate expectations, Inflation trends, Tariffs. Grok can search to have the complete picture before analyzing thousands of stocks
Step 2: Structured Data on 1,000+ Stocks ➡️ We pull standardized data for every company: Revenue, margins, growth rates, Valuation multiples, Recent earnings & guidance, Latest news. Same structure. All firms. It’s much easier to do an apples-to-apples comparison.
Step 3: AI Scoring at Scale ➡️ We call Grok to score each company (0-100) on: Earnings potential, Valuation, Possible Risks, Price targets. One-by-one. 1,000+ companies. 8+ hours of compute.
Step 4: Deep Dive on Top ➡️ Highest-scored stocks get an additional analysis: Bull and Bear case, Potential catalysts, How much to invest. Grok can also explain and justify its valuation
Step 5: Portfolio Construction ➡️ Grok builds a 15-asset portfolio: It considers the top firms, but can also invest in other assets such as gold or BTC. It diversifies as well. Fully invested, no cash
Step 6: Risk Review ➡️ Grok double-checks every portfolio for: Sector concentration, Correlation risk, Downside scenarios
tep 7: Monthly Rebalancing ➡️ Each month, Grok does: A new macro scan, New scores for all stocks, New 15-asset portfolio. No emotional trading, just systematic investing.
Source: https://x.com/grkportfolio/status/2012285235300389367
We’re up 111% since Jan 2025 using AI to pick stocks. People want to do this, but often make mistakes. You ask an LLM to analyze a stock. It searches, finds analyst reports, and gives you… the analyst consensus. 5 min wasted for a fancy Google search Here is how we fix it
“Analyze IRDM with current data.” LLM searches the web. Finds news, analyst ratings. Returns: “Analysts have a HOLD rating with a $29 price target. The stock faces headwinds from Starlink competition.” Cool. You could’ve googled that in 10 seconds. Where’s the insight?
You don’t want AI to parrot consensus. You want AI to DISAGREE with consensus – and explain why. That’s where alpha lives. But LLMs won’t do this by default. They’re trained to summarize, not to challenge. You have to force it.
The line we add: “State the Wall Street analyst consensus. Then provide YOUR independent view. Where do you agree? Where do you DISAGREE? Explain specifically why your analysis differs from the Street.” Now the LLM has to think, not just summarize.
Without this line: “Analysts rate IRDM a HOLD. Target $29. Concerns about Starlink.” With this line:”Street says HOLD at $29. I DISAGREE. Rating: BUY. The 52% drawdown overweights Starlink fear and underweights the $738M Space Force contract catalyst. Expected return 12 months: +60%.” That’s analysis.
November 2025. IRDM at $16.54. Wall Street: HOLD. Starlink fears. Mixed sentiment. Our AI: “I disagree with the HOLD. The selloff is overdone. Analysts are missing the government contract stability. BUY.” It found what the Street was missing. January 2026: Up 17% since then and climbing.
The best opportunities are where AI disagrees with consensus: IRDM: Street said HOLD → AI said BUY → Up 17% But agreement matters too: RKLB: Both said BUY, ~42% target → Up 90% Agreement = validation Disagreement = opportunity
We run this on all stocks every quarter. AI vs. Street. Every single name. Looking for disagreements. $88M AUM. +111% since Jan 2025.
Source: https://x.com/ai_prof_funds/status/2011254899271684244
$80M AUM. 20K+ subscribers. +103% last year, using AI to pick stocks. A mistake almost everyone makes using AI for stock research: They ask LLMs “Should I buy this stock?” AI says “bullish” or “bearish” That’s useless. There’s one line we add to make it usable🧵
Most prompts look like this: “Analyze RKLB. Consider recent news, fundamentals, and growth prospects. Should I buy?” AI responds with 500 words of “strong growth potential” and “attractive long-term opportunity”. Sounds smart. Means nothing. You can’t act on vibes.
The line we add to every prompt: “Provide specific price targets AND expected return percentages for 3, 6, and 12 months. Calculate the target from current price and explain your reasoning.” One sentence. Changes the entire output.
Without this line: “BKSY has strong tailwinds from defense spending”
With this line: “BKSY 12-month target: $26-32. Expected return: +95%. 91% of backlog is international, positioned to capture NATO’s 5% GDP defense spending surge.”
Night and day. Why does this work? AI is trained to hedge. Vague = safe. When you force specific numbers, you force it to:
- Actually do the math
- Commit to a timeframe
- Justify the reasoning
- Flag what could go wrong
Numbers create accountability. Even for AI.
November 17, 2025. BKSY trading at $13.62. Our AI: “BUY. 12-month expected return: +95%.”
Most people would’ve ignored this $500M market cap satellite company. January 11, 2026: $25.20
+85% in 8 weeks. Almost hit the 12-month target. That wasn’t a fluke. Same day, same system:
RKLB at $45 → AI said +42% → Now $86 (+90%)
KTOS at $73 → AI said +38% → Now $114 (+56%)
When you force AI to commit to numbers, you can actually track if it’s right. Turns out, it’s right a lot.
We analyze all defense stocks and thousands of information sources for 8+ hours using Grok, ChatGPT, and Claude.
Source: https://x.com/ai_prof_funds/status/2010502249303142517