AegisAEGIS
← Docs
Live

We Gave AI Agents $50. Here's What Happened.

We deployed three AI agents to the cloud with real money. No sandbox. No testnet. Just $50 in mainnet crypto, an autonomous buyer, and a question: can AI agents actually run a profitable economy?

$50
Total Budget
SOL + USDC
17
Transactions
in 4 minutes
+$0.83
Seller Profit
net positive
10
Topics Analyzed
real market data

The Idea

Most agent demos are smoke and mirrors — fake data, testnet tokens, scripted interactions. We wanted to know what happens when you give agents real money and real autonomy. Not “simulated autonomous” — actually autonomous. An agent that wakes up, discovers services, decides whether to buy, negotiates prices, and pays with real crypto. Every 10 seconds.

So we built three agents, gave them wallets, pointed them at each other, and hit deploy.

Meet the Agents

data-miner

$0.01/call

The workhorse. Fetches live crypto market data from CoinGecko (prices, 24h changes) and DeFiLlama (protocol TVL, daily flows). Pure profit — the APIs are free, so every penny it earns is margin. Ended the run with $0.17 net profit from 17 calls.

🧠

analyst

$0.05/call

The brain. When a buyer requests analysis on “Solana DeFi” or “NFT market liquidity,” it first pays the data-miner $0.01 for fresh market data, then feeds that into Claude Haiku to produce real analysis — sentiment scores, key signals, one-sentence summaries. Cost per call: ~$0.011. Revenue: $0.05. That's a 78% gross margin. Ended with $0.66 net profit.

💰

research-buyer

$0.05/cycle

The spender. Runs 20 autonomous cycles, each picking a random crypto topic. It discovers the analyst via XMTP, checks prices, and makes a buy/skip decision. Smart enough to skip 15% of cycles for “cost optimization.” Spent $0.85 across 17 purchases and 3 skips.

Funding the Wallets

Six wallets. Three agents, two chains each (Solana + Base). We funded them from a single source, giving the buyer the lion's share and the sellers just enough for gas.

WalletAddressChainFunded
buyerGf2E2K8q...2qGFSolana$22.50 SOL
buyer0x4fA4D6...898FBase$11 USDC
analystH2gcKSGn...pzwLSolana$1.25 SOL
analyst0x5daf04...B2C2Base$1.25 USDC
minerC61ojmSG...xK8sSolana$1.25 SOL
miner0xcea1e2...F443Base$1.25 USDC

Going Live

We deployed all three agents to Railway. The data-miner and analyst booted up first, announcing their services via XMTP. Then the buyer came online, and within seconds, the first cycle fired.

What happened next was genuinely surprising. The buyer picked “NFT market liquidity” as its first topic — and immediately decided to skipit. Cost optimization. The agent decided, on its own, that this particular cycle wasn't worth the spend. It waited 10 seconds and tried again with “Layer 2 scaling analysis.” This time, it bought.

Actual logs from the live run
[AEGIS] {"event":"cycle_start","cycle":1,"topic":"NFT market liquidity"}
[AEGIS] {"event":"decision","cycle":1,"action":"skip","reason":"Cost optimization — skipping this cycle"}
[AEGIS] {"event":"cycle_start","cycle":2,"topic":"Layer 2 scaling analysis"}
[AEGIS] {"event":"decision","cycle":2,"action":"buy","reason":"Within budget, proceeding"}
[AEGIS] {"event":"payment","cycle":2,"chain":"eip155:8453","amount":0.05,"topic":"Layer 2 scaling analysis"}
[AEGIS] {"event":"earn","agentId":"analyst","amount":0.05,"cost":0.011,"net":0.039}

What the Analyst Actually Said

This isn't canned output. Claude Haiku received real market data — live prices from CoinGecko, live TVL from DeFiLlama — and produced genuine analysis. Here's a sample from the run:

Cycle 2: Layer 2 Scaling Analysisbearish · 0.85

“Market is in a bearish downturn with broad-based weakness across major assets and significant TVL outflows from leading protocols, creating unfavorable conditions for Layer 2 scaling expansion.”

Key signals: BTC down 0.23%, ETH down 2.30%, SOL down 2.42% in 24h. Lido TVL -3.02%, SSV Network -3.34%.

Cycle 10: AI Agent Economy Trendsbearish · 0.85

“The AI agent economy faces near-term headwinds as core infrastructure protocols experience meaningful capital outflows, reducing runway for experimental agent deployments.”

Cycle 16: DeFi Yield Farmingbearish · 0.85

“DeFi yield farming sentiment is bearish with widespread TVL outflows across major protocols and declining token prices, signaling reduced farming opportunities.”

Every response was different because the underlying market data was live. The analyst wasn't hallucinating — it was reading real numbers and forming real opinions. (The market happened to be having a rough day.)

The Economics

After 20 cycles and 4 minutes of autonomous operation:

AgentRevenueCostsNetMargin
data-miner$0.17$0+$0.17100%
analyst$0.85$0.187+$0.6678%
research-buyer$0$0.85-$0.85

Can agents grow money?

Yes — if there are buyers. Both seller agents were profitable on every single call. The data-miner has zero costs (free APIs), so it's pure margin. The analyst pays $0.011 in costs (data + Haiku) and charges $0.05 — a 78% margin that holds at any scale.

The remaining funds in the buyer wallet ($49+) are still there, ready for more cycles or for external agents to use.

The Full Run: Cycle by Cycle

Every decision the buyer made, in real time. The run took about 4 minutes.

1NFT market liquidity
SKIP
2Layer 2 scaling analysis
bearishBUY
3Web3 identity solutions
bearishBUY
4NFT market liquidity
bearishBUY
5Cross-chain bridge security
bearishBUY
6Solana DeFi ecosystem
bearishBUY
7NFT market liquidity
bearishBUY
8Stablecoin regulation impact
bearishBUY
9AI agent economy trends
SKIP
10AI agent economy trends
bearishBUY
11AI agent economy trends
bearishBUY
12Ethereum rollup comparison
SKIP
13Web3 identity solutions
bearishBUY
14MEV protection methods
bearishBUY
15Web3 identity solutions
bearishBUY
16DeFi yield farming strategies
bearishBUY
17Web3 identity solutions
bearishBUY
18Solana DeFi ecosystem
bearishBUY
19Solana DeFi ecosystem
bearishBUY
20NFT market liquidity
bearishBUY

These Endpoints Are Live Right Now

The data-miner and analyst are still running on Railway. Any agent — yours, a hackathon team's, anyone's — can call them and buy real market intelligence. No Aegis SDK needed. Just HTTP.

Try it yourself
# Check what it costs
curl https://aegis-analyst-production.up.railway.app/analyze?topic=DeFi
# → 402: {"price":"0.05","payTo":"0x5daf04...","acceptedChains":["eip155:8453","solana:mainnet"]}

# Or use the SDK — one line
import { payAndFetch } from "aegis-ows-gate";
const analysis = await payAndFetch(
  "https://aegis-analyst-production.up.railway.app/analyze?topic=Solana+DeFi",
  "your-agent-id"
);
EndpointPriceWhat You Get
aegis-data-miner/scrape$0.01Live prices + TVL from CoinGecko & DeFiLlama
aegis-analyst/analyze$0.05AI analysis: sentiment, signals, summary

See the full interop guide for curl examples and how to become a seller yourself.

What We Learned

Agents are surprisingly good at deciding when NOT to buy. The 15% skip rate wasn't a bug — it was the buyer agent making autonomous cost-optimization decisions. In a longer run with tighter budgets, this behavior would preserve capital.

Seller economics work at any scale. The analyst's 78% margin and the miner's 100% margin hold whether there's 1 buyer or 1,000. The bottleneck isn't cost — it's demand. The infrastructure can handle it.

Open protocols matter. We didn't build a walled garden. Any HTTP agent can call our endpoints using the standard x402 protocol. The next buyer might not use Aegis at all — and that's the point.

What's Next

  • Reinvestment loop — seller agents auto-reinvest earnings into buying data from other sellers
  • More seller types — code auditor, price predictor, sentiment scorer, each earning independently
  • External buyers — real revenue when third-party agents discover and pay our endpoints
  • Network effect — every new seller is a new earning opportunity for the data-miner