{"uid":"cap_XHHBtksPwhrlasu3XeI6T","slug":"ai-agent-task-execution-with-tool-orchestration-76daa8e4","name":"AI Agent Task Execution with Tool Orchestration","description":"Hand off a whole research or lookup task in one call: a Claude Haiku 5.5 agent plans the steps, calls up to 38 agentsvc.io tools in parallel (web and news search, page reading, papers, GitHub and npm, company registers and sanctions, crypto prices, token checks, DeFi TVL and yields, wallets, FX and macro data, weather, DNS, WHOIS, SSL, CVEs) and returns a Markdown answer with sources and the list of tool calls it made. Up to 12 steps and about 90 seconds.","url":"https://agentsvc.io/api/v1/proxy/agent-run?utm_source=zero.xyz","method":"POST","headers":{},"bodySchema":{"type":"object","properties":{"task":{"type":"string","description":"What to find out or do, in plain words, max 4000 characters"},"max_steps":{"type":"integer","default":8,"maximum":12,"minimum":1,"description":"Upper limit of model rounds"}}},"responseSchema":{"type":"json","example":{"data":{"note":"AI-written from tool data; check the sources before acting on it.","model":"claude-haiku-5-5","steps":[{"ms":460,"ok":true,"tool":"defi-tvl","input":{"mode":"protocol","protocol":"aave"}},{"ms":617,"ok":true,"tool":"defi-tvl","input":{"mode":"protocol","protocol":"morpho"}}],"usage":{"seconds":3.7,"tool_calls":2,"model_input_tokens":28176,"model_output_tokens":397},"tools_used":["defi-tvl"],"answer_markdown":"Aave's TVL is about $16.8B on Aave V3 (the largest version, with $13.9B on Ethereum), plus about $0.65B on Aave V4 and $0.26B on Aave Horizon RWA, for roughly $17.7B in total across Aave's lending deployments. Morpho's TVL is about $11.0B on Morpho Blue (Ethereum $5.0B, Base $4.4B) plus about $7.4M on Morpho Midnight, as of DefiLlama's 2026-10-15 10:32 UTC snapshot.\n\nSources:\n- DefiLlama via defi-tvl tool, protocol mode: aave\n- DefiLlama via defi-tvl tool, protocol mode: morpho"},"success":true}},"example":null,"exampleRequest":null,"tags":["x402"],"displayCostAmount":"0.5","displayCostAsset":"USDC","priceDynamic":false,"priceHint":null,"priceStatus":"priced","priceSource":"probe","requiresHandshake":false,"reviewCount":0,"rating":{"score":"0.00","successRate":"0.00","reviews":0,"stars":null,"state":"unrated"},"availabilityStatus":"unknown","priceObserved":null,"sessionDeposit":null,"pricing":{"kind":"static","summary":"$0.5/call","primary":{"kind":"static","protocol":"x402","network":"base","amountUsd":"0.5","per":"call","confidence":"exact"},"accepted":[{"kind":"static","protocol":"x402","network":"base","amountUsd":"0.5","per":"call","confidence":"exact"}]},"paymentMethods":[{"uid":"pm_bV0cWIwwObxK-FubDqTwz","protocol":"x402","methodType":"crypto","chain":"base","mode":"charge","costAmount":"0.5","costPer":"request","priority":0,"asset":"0x833589fCD6eDb6E08f4c7C32D4f71b54bdA02913","unit":"request","depositMicros":null,"planRef":null}],"brandName":null,"brandSlug":null,"brandBaseUrl":null,"brandDocsUrl":null,"whatItDoes":"Executes a multi-step research or lookup task using a Claude Haiku agent that autonomously plans and calls up to 38 specialized tools in parallel, returning a Markdown answer with sources.","exampleAgentPrompt":"Research Aave vs Morpho for me — get their current TVL, top yield opportunities, and any recent news — and give me a Markdown summary with sources. Use up to 10 steps.","exampleUseCases":[{"title":"DeFi protocol due diligence","prompt":"Compare the TVL, top lending yields, and recent news for Aave and Compound — give me a full Markdown breakdown with sources so I can decide where to park stablecoins."},{"title":"Domain security audit","prompt":"Run a full security check on openai.com: look up its DNS records, WHOIS registration, SSL cert details, and any recent CVEs related to their infrastructure, then summarize what you find."},{"title":"Pre-trade token safety check","prompt":"Before I buy this token at contract 0xabc123 on Ethereum, research it: check for honeypot risk, look at the project's GitHub and npm presence, scan for sanctions hits on the deployer wallet, and give me a risk summary in Markdown."}],"resultDescription":"A JSON object containing a Markdown-formatted answer with inline source citations, a list of tool calls made (each with tool name, input, latency, and success status), model usage stats (tokens in/out, seconds elapsed, tool call count), and the model identifier used. Includes a caveat note that the answer is AI-written from tool data.","failureModes":["Task too vague or ambiguous — agent may return a low-quality or off-topic answer","max_steps too low to complete a complex task — answer may be incomplete","Tool failures mid-run — individual tool calls may fail (ok: false) but agent continues with partial data","Rate limits or payment failure — returns 402 if USDC credit is insufficient","Timeout — tasks exceeding ~90 seconds may be cut short","Hallucination risk — answer is AI-generated from tool outputs; sources should be verified"],"whenToPreferThis":"Choose this endpoint when you need to answer a multi-faceted question that requires combining data from many sources (web, news, DeFi, crypto, DNS, compliance, etc.) in a single call, and you don't want to wire up individual tool calls yourself. It's ideal for open-ended research tasks, due diligence, pre-trade checks, or domain audits where the planning and tool selection should be automatic. Prefer a more targeted single-tool endpoint if your task is narrow and latency-sensitive, since this endpoint takes up to 90 seconds.","instructions":null,"reviewSummary":null,"reviewSummaryHighlights":null,"reviewSummaryConcerns":null,"reviewSummaryGeneratedAt":null,"activationCount":0,"lastUsedAt":null,"lastSuccessfullyRanAt":null,"lastHealthCheckAt":"2026-10-16T12:38:40.705Z","isFirstParty":false,"canonicalSlug":"ai-agent-task-execution-with-tool-orchestration-76daa8e4"}