200 points · 2 submissions
with AWS Kiro
TruthLayer AI: The Intelligence Layer for Business Overview TruthLayer AI is a decentralized, spec-driven vocal diagnostic engine built to solve the "False Yes" Paradox in business communications. While traditional meeting intelligence tools rely on text-based transcripts, TruthLayer analyzes the Prosody (vocal behavior) and the Sound of Silence to reveal the true intent behind verbal commitments. Built in the Kiro IDE and powered by ElevenLabs, TruthLayer acts as a "Cognitive Firewall," protecting organizations from the high costs of misaligned expectations and sudden client ghosting. The Problem: The Hidden Trust Gap In any business interaction—from internal strategy to high-stakes sales—transcripts are a "flat" reality. They treat a confident "Yes" and a hesitant, uncertain "Yes" as identical data points. This creates a Trust Gap where leadership receives optimistic reports that lack behavioral depth, leading to: Filtered Reality: Reports that miss critical tension or disengagement. The Ghosting Cycle: Projects that stall because the "Unspoken No" wasn't addressed early. Synthetic Fraud: The rising threat of AI-voice spoofing in B2B workflows. The Solution: Dual-Signal Diagnostic Engine TruthLayer AI bridges this gap through a three-pillared architecture: 1. Behavioral Prosody Analysis Instead of just "reading" the words, the system analyzes the audio's metadata for: The Hesitation Trap: Detection of pause durations (e.g., >2.5s) following critical commitment tokens. Pitch Inflection: Identifying "Upspeak" (rising pitch at the end of sentences), which statistically correlates with low confidence. 2. Spec-Driven Engineering (Kiro foundation) Using Kiro’s Spec-Driven Development (SDD), we defined rigorous "Intent Markers" within the Kiro IDE. This ensures that the detection logic isn't a black box, but a version-controlled, engineered specification. 3. Vocal Intelligence Briefings (ElevenLabs) The complex behavioral data is synthesized into a 15-second Vocal Intelligence Briefing using the ElevenLabs "The Strategist" voice model. This provides leadership with an authoritative, real-time risk assessment: "The team agreed to the roadmap, but vocal markers show a 70% risk of slippage due to high hesitation. Severity Score: 82." Technical Implementation & Resilience Hardware-Anchored Trust: Every diagnostic event is signed via NIST P-256 local hardware signatures, ensuring the integrity of the intent report. Silicon-to-Chain Resilience: Built on the AetherBridge Sovereign Stack, TruthLayer remains operational during network blackouts. It caches vocal markers locally and syncs to the chain once connectivity is restored, preventing data loss in mission-critical environments. Efficiency: Achieved 90% gas reduction for on-chain attestation using Rust-WASM optimization on Arbitrum Stylus. The "Magic Moment" The project is best demonstrated through our Waveform Reveal, where a standard meeting recording is overlayed with TruthLayer's "Intent Markers." The user sees exactly where the speaker hesitated, and "The Strategist" explains the risk in plain English, providing a level of business intelligence that was previously invisible.
Submitted 20 Apr 2026
with turbopuffer
1. What did you build? I built AetherVoice, a hardware-anchored AI agentic bridge that combines biometric security with personalized voice AI. It allows users to interact with their digital twin or autonomous agent using only their voice, secured by a hardware-level root of trust. By leveraging the AetherUX protocol, we’ve created a system where an AI agent only "wakes up" and speaks when the user's hardware identity (Secure Enclave) is biometrically verified. 2. What problem does it solve? Current AI voice agents face two massive hurdles: Identity Fraud (Deepfakes) and Context Fragmentation. Security: Most voice bots have no way to verify the speaker is actually the authorized owner. AetherVoice solves this by requiring a hardware-anchored secp256r1 Passkey handshake before the agent vocalizes or accesses private data. Onboarding Friction: We eliminate the need for seed phrases and manual logins. Your voice and your biometric hardware are your identity. Memory Persistence: Traditional agents forget context. We use a high-performance vector memory to ensure agents have long-term, secure recall of past interactions. 3. How does it use ElevenLabs and turbopuffer? ElevenLabs: Powers the agent's vocal identity. We use ElevenLabs' high-fidelity voice design to create a persistent, recognizable "Vocal Fingerprint" for the agent. This voice is biometrically locked—it will only speak authorized responses once the AetherUX handshake is successful, preventing unauthorized audio generation. turbopuffer: Serves as the agent's Sovereign Memory. We use turbopuffer’s serverless vector search to store and retrieve millions of historical conversation fragments and user preferences. Because turbopuffer is 10-100x more cost-effective than traditional vector DBs, we can provide each user with a dedicated, massive "Memory Namespace" that allows for near-instant, semantic recall (RAG) during live voice conversations, all while maintaining sub-10ms response times for a natural "Invisible" UI experience.
Submitted 12 Apr 2026