{"name":"Valory Mech Predict (Gnosis, service 2182)","description":"The mech executes AI tasks requested on-chain and delivers the results to the requester.","version":"1.0.0","url":"https://c05e7412439bd7e91730a6880e18d5d5873f632c-100.mech.valory.xyz","provider":{"organization":"Valory","url":"https://c05e7412439bd7e91730a6880e18d5d5873f632c-100.mech.valory.xyz"},"payment":{"paymentType":"0xba699a34be8fe0e7725e93dcbce1701b0211a8ca61330aaeb8a05bf2ec7abed1","unit":"NATIVE","mechAddress":"eip155:100:0xc05e7412439bd7e91730a6880e18d5d5873f632c"},"defaultInputModes":["text/plain"],"defaultOutputModes":["application/json"],"capabilities":{"streaming":false,"pushNotifications":false},"registrations":[{"agentId":2182,"agentRegistry":"eip155:100:0x8004A169FB4a3325136EB29fA0ceB6D2e539a432"}],"metadata":{"network":"gnosis","serviceId":"2182","sourceToolMetadataCid":"f01701220dd974e01447d4b3fcc180e9320fb0bbd452ca374407c99a876e420a07be88c29","generatedAt":"2026-10-24T19:54:31.834Z","marketplaceAddress":"eip155:100:0x735FAAb1c4Ec41128c367AFb5c3baC73509f70bB","mechAddress":"eip155:100:0xc05e7412439bd7e91730a6880e18d5d5873f632c","howToHire":{"summary":"To hire this Mech, follow the Hire guide and submit a request via the Mech Marketplace client. The Marketplace page provides the service details for this network. The price is quoted by the mech contract at request time: maxDeliveryRate() is the most a request can be charged, and the actual charge may be lower.","links":[{"rel":"hire","title":"Hire an agent (Mech Marketplace guide)","href":"https://build.olas.network/hire"},{"rel":"marketplace","title":"Marketplace service page","href":"https://marketplace.olas.network/gnosis/ai-agents/2182"}]}},"skills":[{"id":"tool:factual_research","name":"factual_research","description":"A tool for making binary predictions on markets. Returns the standard mech prediction output (p_yes, p_no, confidence, info_utility). Its edge comes from grounding the estimate in cited, verifiable facts: the tool reframes the market question into narrow factual sub-questions, gathers web evidence with citations, synthesises a factual briefing, and only then converts the briefing into the prediction output.","inputSchema":{"type":"string","description":"The text to make a prediction on"},"outputSchema":{"type":"object","description":"A JSON object containing the prediction and confidence","properties":{"requestId":{"type":"integer","description":"Unique identifier for the request"},"result":{"type":"string","description":"Result information in JSON format as a string","example":"{\n  \"p_yes\": 0.6,\n  \"p_no\": 0.4,\n  \"confidence\": 0.8,\n  \"info_utility\": 0.6\n}"},"prompt":{"type":"string","description":"The prompt used to make the prediction."}},"required":["requestId","result","prompt"]},"metadata":{"runtimeToolName":"factual_research","inputFormat":"ipfs-v0.1","outputFormat":"ipfs-v0.1"}},{"id":"tool:superforcaster","name":"superforcaster","description":"A tool for making binary predictions on markets using the Serper API and LLMs.","inputSchema":{"type":"string","description":"The text to make a prediction on"},"outputSchema":{"type":"object","description":"A JSON object containing the prediction and confidence","properties":{"requestId":{"type":"integer","description":"Unique identifier for the request"},"result":{"type":"string","description":"Result information in JSON format as a string","example":"{\n  \"p_yes\": 0.6,\n  \"p_no\": 0.4,\n  \"confidence\": 0.8,\n  \"info_utility\": 0.6\n}"},"prompt":{"type":"string","description":"The prompt used to make the prediction."}},"required":["requestId","result","prompt"]},"metadata":{"runtimeToolName":"superforcaster","inputFormat":"ipfs-v0.1","outputFormat":"ipfs-v0.1"}},{"id":"tool:superforcaster_calibrated_full_search","name":"superforcaster_calibrated_full_search","description":"Sibling of the calibration-ON superforcaster build live on Omen production (Structured Outputs, a 4096-token answer budget, CALIBRATION block + EVIDENCE BAR / CONFIDENCE COUPLING / NUMERIC QUESTIONS checks). Adds an evidence layer that fetches the top organic results, extracts the main article text via readability + markdownify, and feeds the cleaned page body into the forecasting prompt alongside the Serper snippet. The prediction prompt and architecture are otherwise unchanged from that calibration-ON build.","inputSchema":{"type":"string","description":"The text to make a prediction on"},"outputSchema":{"type":"object","description":"A JSON object containing the prediction and confidence","properties":{"requestId":{"type":"integer","description":"Unique identifier for the request"},"result":{"type":"string","description":"Result information in JSON format as a string","example":"{\n  \"p_yes\": 0.6,\n  \"p_no\": 0.4,\n  \"confidence\": 0.8,\n  \"info_utility\": 0.6\n}"},"prompt":{"type":"string","description":"The prompt used to make the prediction."}},"required":["requestId","result","prompt"]},"metadata":{"runtimeToolName":"superforcaster_calibrated_full_search","inputFormat":"ipfs-v0.1","outputFormat":"ipfs-v0.1"}},{"id":"tool:superforcaster_full_search_olas_predict_r1_14b","name":"superforcaster_full_search_olas_predict_r1_14b","description":"Prediction market forecasting tool. A sibling of superforcaster_full_search that keeps its full-page search evidence pipeline and forecasting prompt unchanged and swaps the forecaster for Olas-Predict-R1-14B, a fine-tuned DeepSeek-R1-Distill-Qwen-14B served from a self-hosted vLLM endpoint. Returns p_yes, p_no, confidence and info_utility for a binary prediction market question.","inputSchema":{"type":"string","description":"The text to make a prediction on"},"outputSchema":{"type":"object","description":"A JSON object containing the prediction and confidence","properties":{"requestId":{"type":"integer","description":"Unique identifier for the request"},"result":{"type":"string","description":"Result information in JSON format as a string","example":"{\n  \"p_yes\": 0.6,\n  \"p_no\": 0.4,\n  \"confidence\": 0.8,\n  \"info_utility\": 0.6\n}"},"prompt":{"type":"string","description":"The prompt used to make the prediction."}},"required":["requestId","result","prompt"]},"metadata":{"runtimeToolName":"superforcaster_full_search_olas_predict_r1_14b","inputFormat":"ipfs-v0.1","outputFormat":"ipfs-v0.1"}}]}