Agentic Workflows for Crypto Research

insights.glassnodePublicado a 2026-04-01Actualizado a 2026-04-01

Resumen

AI coding agents are transforming crypto research by automating data analysis through natural language. This article demonstrates using an agent (like Claude Code) with the Glassnode CLI to test a hypothesis: whether extreme Bitcoin exchange inflows predict 7-day price drawdowns. The agent autonomously discovers metrics, fetches data, performs statistical analysis, and generates insights. Results show a moderate association—spike days saw ~1.9% greater drawdowns—though the sample is small. A follow-up prompt produces visualizations for validation. The workflow allows rapid iteration and is applicable to various research questions using Glassnode data, requiring only an API key and an AI agent.

AI coding agents are changing the way analysts and researchers interact with data. Instead of writing scripts line by line, you provide a hypothesis or research question to an AI agent and – it writes the code, fetches the data, runs the analysis, and returns results.

In this article we present a step-by-step real-world example: Asking an AI agent to download data via the Glassnode CLI, run a statistical analysis, and generate publication-ready charts, all from natural-language prompts.

What you will need

Access to an AI agent

We use Claude Code in this walkthrough, but any agent able to execute Python and shell commands will work, including ChatGPT's Codex, Cursor, Github Copilot, Google Gemini CLI, OpenClaw, or similar tools.

The Glassnode CLI (gn)

A command-line interface for the Glassnode API. Install it and configure your API key by following the Glassnode CLI docs. An API key is required.

The prompt

We will evaluate the following hypothesis: Extreme BTC exchange inflow events are predictive of 7-day forward drawdowns. To do that, we will instruct Claude Code using the following prompt:

Using the Glassnode CLI, download BTC daily exchange inflows and closing price for the last year. Analyze whether inflow spikes (days with inflows > 2 standard deviations above the mean) predict drawdowns in the following 7 days. Show me a summary with statistics and results.

That's it. One sentence describing the question, and another sentence defining the methodology. The agent takes it from there.

What the agent does

Behind the scenes, the agent executes a sequence of steps:

Discovers the right metrics by running gn metric list and gn metric describe to find the correct metric paths and valid parameters.
Downloads the data via gn metric get, saving CSV files for both exchange inflows (transactions/transfers_volume_to_exchanges_sum) and closing price (market/price_usd_close).
Writes and runs a Python analysis that computes the spike threshold, identifies spike days, calculates forward 7-day max drawdowns, and compares spike days to normal days.

The agent comes back with a readable summary:

While this is just an illustrative example, our experiment does reveal a moderate association between exchange inflow spikes and subsequent drawdowns. Spike days see roughly 1.9 percentage points more drawdown on average. That said, with only 10 spike days in the sample and the effect concentrated in two volatile periods, the signal is suggestive rather than statistically robust. A rigorous backtest would need to account for overlapping windows, control for volatility regimes, use point-in-time data, and validate out-of-sample.

Visualizing the results

Visualizing the data is a good way to validate whether the numbers hold up. In this process, a simple follow-up prompt is enough:

Create a visualization that shows the data as a timeseries.

From here, you can keep iterating: adjust the chart, refine the analysis, or take the research in a different direction, all through natural language conversation.

The AI-generated visualisation of Glassnode data

Get started with AI Crypto Research on Glassnode Data

The Glassnode CLI requires an API key, available to Glassnode Professional subscribers.

Install the Glassnode CLI and configure your API key. See documentation
Open your preferred AI coding agent (Claude Code, Codex, Cursor, Gemini CLI, OpenClaw, etc.)
Start prompting. Try questions such as:
- "Download ETH staking deposits for the last 6 months and plot the trend"
- "Compare BTC and ETH exchange netflows over the last 90 days"
- "Find which metric has the highest correlation with BTC 30-day returns"

The Glassnode CLI allows agents to discover and retrieve metric data without requiring manual API lookup or writing boilerplate code. Combined with an AI coding agent, the Glassnode CLI turns a research question into results in minutes.

Preguntas relacionadas

QWhat is the main advantage of using AI coding agents for crypto research as described in the article?

AThe main advantage is that AI coding agents automate the entire research workflow, allowing analysts to provide a natural-language hypothesis or research question, and the agent handles writing the code, fetching data, running analysis, and returning results, significantly speeding up the process.

QWhich specific AI agent is used in the walkthrough example for analyzing BTC exchange inflows?

AThe walkthrough uses Claude Code, but it notes that any AI agent capable of executing Python and shell commands, such as ChatGPT's Codex, Cursor, GitHub Copilot, Google Gemini CLI, or OpenClaw, would work.

QWhat hypothesis is tested in the example prompt given to the AI agent?

AThe hypothesis tested is: 'Extreme BTC exchange inflow events (days with inflows > 2 standard deviations above the mean) are predictive of 7-day forward drawdowns.'

QWhat are the key steps the AI agent performs behind the scenes after receiving the prompt?

AThe agent discovers the right metrics using Glassnode CLI commands, downloads the data (exchange inflows and closing price), writes and runs a Python analysis to compute spike thresholds and drawdowns, and returns a statistical comparison and summary.

QWhat is required to use the Glassnode CLI for AI-assisted research as mentioned in the article?

ATo use the Glassnode CLI, you need an API key, which is available to Glassnode Professional subscribers, and you must install and configure the CLI tool following the documentation.

Lecturas Relacionadas

From 'Old Dogs' to 'New Darlings': How AI is Revaluing Old Infrastructure, from Dell to Nokia

"Old Dogs" Become AI's New Darlings: Revaluing Legacy Infrastructure The AI investment narrative is shifting. Beyond the spotlight on core chipmakers like Nvidia, a new wave of interest is rising for legacy tech companies—Dell, HPE, Nokia, Cisco, Corning, Western Digital—once labeled as slow-growth, outdated stories. This resurgence stems from AI's evolution from model development to real-world deployment, creating massive demand for physical infrastructure. As AI moves into data center construction and enterprise adoption, the focus turns to who can actually build and deliver complex systems. These established players hold decades of experience in supply chains, integration, networking, and enterprise delivery—assets now critical for scaling AI. The revaluation can be grouped into three key infrastructure areas: 1. **Servers & Integration (e.g., Dell, HPE):** They are becoming essential system integrators, transforming GPUs into full-scale AI servers with networking, power, and cooling, then delivering them to clients. Strong recent earnings and AI-specific revenue/order growth for Dell and HPE underscore this shift. 2. **Networking & Connectivity (e.g., Corning, Nokia, Cisco):** As AI clusters grow, high-speed data transfer becomes paramount. Corning benefits from fiber demand for data center links, Nokia is exploring AI-integrated wireless networks (AI-RAN), and Cisco sees surging orders for data center switches—all critical for efficient AI operations. 3. **Storage (e.g., Western Digital, Seagate):** The AI data explosion requires vast capacity. Beyond high-speed memory (HBM), there's growing need for high-capacity HDDs to store training data, logs, video, and cold/archival data cost-effectively. This revaluation, however, is not a blanket endorsement. True reassessment requires concrete proof: AI-driven orders and revenue growth, upward revisions to company guidance, and sustainable improvements in profit quality, not just top-line sales. In essence, AI is not turning all old tech firms into high-growth stocks; it is selectively re-pricing the "old assets" of companies that are mission-critical for building the new AI infrastructure, transforming their legacy capabilities into renewed growth engines.

marsbitHace 4 min(s)

From 'Old Dogs' to 'New Darlings': How AI is Revaluing Old Infrastructure, from Dell to Nokia

marsbitHace 4 min(s)

The Bitcoin Roadmap To $500,000: Analyst Shows How Price Will Get There

An analyst projects Bitcoin could reach $500,000 based on technical chart analysis, mapping out a multi-phase roadmap within a long-term ascending channel. The analyst, Crypto Tice, states Bitcoin has completed the first phase ("First touch") of the pattern and is entering a second phase that could trigger its strongest rally yet, potentially driving a more than 693% increase from current levels above $63,000. This would be followed by a final pullback. This outlook comes as Bitcoin faces significant selling pressure, having fallen 17% over three days to around $61,300, erasing roughly $250 billion in market cap. The downturn has also impacted other major cryptocurrencies like Ethereum. Despite the crypto market decline, U.S. equities remain near highs, creating a notable divergence that some suggest could indicate market manipulation or crypto front-running a potential stock market correction.

bitcoinistHace 16 min(s)

The Bitcoin Roadmap To $500,000: Analyst Shows How Price Will Get There

bitcoinistHace 16 min(s)

Expected $1 Billion Crypto Windfall Shrinks To Fraction In Israel Disclosure Program

Israel's voluntary crypto disclosure program has seen a much weaker response than expected, with only 58 individuals coming forward. Tax authorities had projected up to $1 billion in revenue from the initiative, but early reports indicate declared crypto capital totals only about $50 million. The program offered immunity from criminal charges for correcting past reporting errors, but its lack of an anonymous option reportedly deterred many holders who feared putting their names on record. With an estimated $1 billion in digital assets held by Israeli residents, the disclosures so far represent only a small fraction of the market. The filing window, which has specific conditions and runs until August 2026, remains open.

bitcoinistHace 28 min(s)

Expected $1 Billion Crypto Windfall Shrinks To Fraction In Israel Disclosure Program

bitcoinistHace 28 min(s)

Breaking News! Anthropic Calls for a Universal Pause in AI Research

Anthropic warns of AI self-evolution, reporting that over 80% of its internal code is now written by its AI, Claude. Productivity has surged, with engineers merging 8x more code than in 2024. Claude's performance on complex, open-ended tasks jumped from 26% to 76% success in six months, nearing human parity. The company introduces a new metric: "AI task duration." In 2024, AI handled 4-minute tasks; by 2026, it manages 16-hour tasks, with capability doubling every 4 months. Claude also reviews code, catching bugs that previously caused outages, and significantly outperforms humans in research tasks like optimizing code (52x speedup) and conducting AI safety experiments. Anthropic outlines three potential futures: 1) Progress plateaus, 2) AI accelerates but humans remain in control, or 3) AI achieves full recursive self-improvement (RSI), designing its own successors. This final path could revolutionize fields like medicine but also risks catastrophic alignment failure if control is lost. The call echoes similar concerns from OpenAI. Anthropic proposes a coordinated pause on AI development—if a verifiable mechanism to ensure all labs comply can be established.

marsbitHace 33 min(s)

Breaking News! Anthropic Calls for a Universal Pause in AI Research

marsbitHace 33 min(s)

Probability in the Price: How World Cup Odds Are Calculated

**The Probability in the Price: How World Cup Odds Are Calculated** Two major systems released their "championship probabilities" before the 2026 World Cup, and they disagreed on the favorite. Prediction market aggregators listed France at around **17%**, while the Opta supercomputer gave European champion Spain **16.1%**. These numbers look similar, but their production methods are fundamentally different. The market's **17%** is the **price** that clears after hundreds of millions of dollars in trading across platforms like Polymarket and Kalshi, where contracts trade between 0 and 100 cents, directly representing implied probability. This liquidity is provided by crypto-native market makers like Wintermute, though the market still has "the liquidity profile of an early-stage" asset class. In contrast, Opta's **16.1%** is a **simulated frequency**. Its model uses team data (including betting market odds as an input) to estimate match probabilities, then runs **10,000 full tournament simulations**, counting how often each team wins. Which is more accurate? There is **no rigorous, cross-tournament academic study** directly comparing their track records. However, a persistent **longshot bias**—where low-probability outcomes are systematically overvalued—observed in traditional betting for nearly a century, has also been found in modern crypto prediction markets. Research shows low-price contracts on Kalshi/Polymer less likely to pay out than their implied odds suggest. Unlike traditional bookmakers, prediction markets operate on **public blockchain ledgers**, making every transaction auditable and enabling such research. However, price formation is also influenced by **regulatory uncertainty**, as seen in recent US state-level bans and legal battles over jurisdiction. In summary, the "probability" you see is either a **market-clearing price** subject to behavioral biases and liquidity constraints, or a **model-simulated frequency** that partially incorporates market data. The question of which method is more reliable remains open, highlighting the importance of asking: **How was this number produced?**

marsbitHace 33 min(s)

Trading

Spot

Futuros