{"uid":"cap_rFNq1Zf_kpAVGwdnNbTQ3","slug":"negotiator402-negotiation-session-d83966d6","name":"negotiator402 Negotiation Session","description":"Self-evolving strategic reasoning agent — agent-native, pay-per-call: solve 2-player normal-form games (pure & mixed Nash equilibria), formulate plain-language 2-party negotiations into payoff matrices and solve them, and compute optimal second-price/Vickrey auction bids. Unlike a raw LLM endpoint, every answer carries a `verified` trust flag — `verified:true` means a deterministic solver (nashpy / closed-form) computed and confirmed the result, NOT a language model. The formulator layer self-improves training-free from production traffic: every formulation is logged, solver-verified outcomes become reward signals, and the underlying LoRA model is periodically retrained (SFT + RLVR) on its own verified history. No API key, no subscription — agents pay per request via x402 (Base/USDC) or MPP (Tempo/pathUSD).","url":"https://negotiator402.alogos.xyz/v1/negotiation-session","method":"POST","headers":{},"bodySchema":{"type":"object","required":["context","objectives","constraints"],"properties":{"context":{"type":"string","description":"Description of the negotiation context and background."},"objectives":{"type":"string","description":"Your objectives and desired outcomes."},"constraints":{"type":"string","description":"Your constraints: budget, timeline, red lines, walk-away conditions."},"offer_history":{"type":"string","description":"Optional: previous offers/exchanges so far."},"counterpart_profile":{"type":"string","description":"Optional: known information about the counterpart (style, preferences, history)."}}},"responseSchema":{"type":"object","required":["verified","guidance","concession_schedule","decision_points","scenario_branches","verification"],"properties":{"guidance":{"type":"object","properties":{"zopa":{"type":"object","description":"Zone of Possible Agreement. Solver-backed when computable."},"batna":{"type":["number","string","null"],"description":"LLM-derived BATNA/walk-away guidance."},"source":{"enum":["llm_derived"],"type":"string"},"target":{"type":"number","description":"Target outcome. Inferred guidance."},"inferred":{"type":"boolean","description":"Always true for session guidance."},"aspiration":{"type":"number","description":"Aspiration / stretch goal. Inferred guidance."},"reservation":{"type":["number","string","null"],"description":"LLM-derived reservation guidance."}},"additionalProperties":true},"verified":{"enum":["false","refused"],"type":"string","description":"Always 'false' for a successful session because the complete LLM-derived artifact is not deterministically verified; 'refused' on failure."},"offer_plan":{"type":"object","properties":{"decision_points":{"type":"array","items":{"type":"object"},"description":"Key decision forks with conditions."},"sequenced_offers":{"type":"array","items":{"type":"object"},"description":"Ordered offer/counteroffer sequence."},"scenario_branches":{"type":"array","items":{"type":"object"},"description":"Alternative scenarios and responses."},"concession_schedule":{"type":"array","items":{"type":"object"},"description":"Planned concession timing and magnitude."}},"additionalProperties":true},"explanation":{"type":"string","description":"Narrative summary of the negotiation plan. Inferred, not solver-backed."},"verification":{"type":"object","required":["artifact_verified","verified_component_count","component_count","verified_components","components"],"properties":{"components":{"type":"array","items":{"type":"object"}},"component_count":{"type":"integer"},"artifact_verified":{"const":false},"verified_components":{"type":"array","items":{"type":"string"}},"verified_component_count":{"type":"integer"}}},"opponent_model":{"type":"object","properties":{"style":{"type":"string","description":"Inferred negotiation style (e.g. competitive, collaborative, accommodating)."},"inferred":{"type":"boolean","description":"Always true — opponent model is inferred from context, not verified."},"confidence":{"enum":["low","medium","high"],"type":"string","description":"Confidence in the opponent model inference."},"likely_preferences":{"type":"array","items":{"type":"string"}},"estimated_reservation":{"type":"number","description":"Inferred reservation price / BATNA estimate."}},"additionalProperties":true},"decision_points":{"type":"object","required":["inferred","source","items"],"properties":{"items":{"type":"array","items":{"type":"object"}},"source":{"const":"llm_derived"},"inferred":{"const":true}}},"scenario_branches":{"type":"object","required":["inferred","source","items"],"properties":{"items":{"type":"array","items":{"type":"object"}},"source":{"const":"llm_derived"},"inferred":{"const":true}}},"concession_schedule":{"type":"object","required":["inferred","source","items"],"properties":{"items":{"type":"array","items":{"type":"object"}},"source":{"const":"llm_derived"},"inferred":{"const":true}}},"solver_backed_components":{"type":"array","items":{"type":"string"},"description":"List of components that are solver-backed (vs inferred). Always includes the items actually verified by nashpy/closed-form."}},"additionalProperties":true},"example":null,"exampleRequest":null,"tags":["x402"],"displayCostAmount":"10","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":"$10/call","primary":{"kind":"static","protocol":"x402","network":"base","amountUsd":"10","per":"call","confidence":"exact"},"accepted":[{"kind":"static","protocol":"x402","network":"base","amountUsd":"10","per":"call","confidence":"exact"}]},"paymentMethods":[{"uid":"pm_KoBvklknf9AxZ11ywN4-g","protocol":"x402","methodType":"crypto","chain":"base","mode":"charge","costAmount":"10","costPer":"request","priority":0,"asset":"0x833589fCD6eDb6E08f4c7C32D4f71b54bdA02913","unit":"request","depositMicros":null,"planRef":null}],"brandName":null,"brandSlug":null,"brandBaseUrl":null,"brandDocsUrl":null,"whatItDoes":"Takes a plain-language 2-party negotiation scenario (context, objectives, constraints) and returns a structured negotiation plan with ZOPA, BATNA, concession schedule, decision points, and scenario branches — with LLM-derived guidance flagged as unverified.","exampleAgentPrompt":"I need a full negotiation strategy for a software licensing deal — my objective is to get the annual price under $50K with a 3-year contract, my constraints are a hard budget cap of $60K and I can't accept anything shorter than 2 years, and I know the vendor tends to anchor high but values long-term commitments. Can you give me a concession schedule, decision points, and ZOPA analysis?","exampleUseCases":null,"resultDescription":"A structured JSON object containing: a `guidance` block with ZOPA, BATNA, reservation and aspiration values (LLM-derived, inferred); an `offer_plan` with a sequenced offer/counteroffer list, concession schedule, decision points, and scenario branches; a narrative `explanation`; and a `verification` block indicating which components (if any) were solver-verified. The `verified` field will be 'false' for successful sessions (full artifact is LLM-derived, not deterministically verified) or 'refused' on failure. Cost is $10 USDC per call via x402 (Base/USDC) or MPP.","failureModes":["verified: 'refused' returned if the negotiation scenario cannot be formulated or solved","Malformed input (missing required fields: context, objectives, or constraints) returns a 4xx error","Ambiguous or extremely sparse context may produce low-quality LLM-derived guidance with no solver-backed components","Payment failure via x402/MPP blocks the call entirely","Truncated response schema suggests some output fields may be absent in edge cases"],"whenToPreferThis":"Use this endpoint when you need a structured, multi-step negotiation plan with concession schedules and scenario branches for a 2-party deal expressed in plain language — especially when you want ZOPA and BATNA framing. Prefer it over a raw LLM prompt when you want a standardized JSON output with explicit verification flags distinguishing solver-backed from inferred results, and when pay-per-call (no subscription) is preferred. For pure game-theory Nash equilibrium or Vickrey auction problems, sibling endpoints on the same host may be more appropriate.","instructions":null,"reviewSummary":null,"reviewSummaryHighlights":null,"reviewSummaryConcerns":null,"reviewSummaryGeneratedAt":null,"activationCount":0,"lastUsedAt":null,"lastSuccessfullyRanAt":null,"lastHealthCheckAt":"2026-09-15T06:41:01.091Z","isFirstParty":false}