Verdikt

Lenz is an audit-grade fact-checking API for AI-drafted text, built for teams that need to check factual claims before customers or clients see them. It reads a draft, memo, model answer, or page of copy, extracts the factual statements that can be checked against independent public sources, and returns a result for each. Its workflow follows four API primitives: extract verifiable claims, assess them in bulk with a fast multi-model verdict, escalate uncertain statements to a full verification, and ask follow-up questions grounded in the verification. Full verification runs through a structured five-stage pipeline of framing, research, debate, panel review, and conclusion. Lenz searches public sources, scores evidence for authority, relevance, and recency, has models from multiple vendors argue both sides of a claim, and returns a verdict, confidence score, cited sources, and reasoning trace that users can audit.

SynthBoard turns hard decisions into structured calls. Instead of asking one AI for advice — and getting a single agreeable answer — you deploy a boardroom of 24 expert AI advisors. Each one has distinct expertise (CFO, Strategist, Skeptic, Customer, Lawyer, Operator, Visionary, and more), a different cognitive reasoning framework (Bayesian, first-principles, adversarial, game theory), and a built-in commitment to hold its position rather than fold for politeness. Bring any decision worth getting right — pricing, hires, pivots, fundraising, vendor selection, M&A, even a hard career call. The Synths debate it across rounds, challenge each other, and produce a synthesized recommendation with action items, confidence scores, and trade-offs. Each Synth runs on the model that suits its mind: Claude Opus for contrarians, GPT for operators, Gemini for breadth, Perplexity for live research. Connect Stripe, HubSpot, Slack, Gmail, Linear, Calendar, and 55+ other tools.