AI Engineering

Turn approved specs and tickets into a verifiable execution goal without re-interviewing the user. Gathers evidence, selects scope, and drafts goals for coding agent sessions.

X2 Extract runs after an X2 project reaches a milestone to compute metrics, churn, and sanitized method-level findings from the turn ledger and decision records. It prepares candidates, confirmations, and negative-space nominations for a human rulings pass without exposing raw project material.

X2 Kernel maintains the claims catalog, editions, and conformance records for the X2 method. Use it to add or retire claims, manage editions, measure enforcement, or verify the kernel stays coherent.

ZK Proofs covers zero-knowledge patterns for Stellar, including Circom Groth16 verification in Soroban and attestation flows for Noir and RISC Zero. Use it for privacy-preserving dApps, verifier contracts, and proof-system integration.

Enforce a hard cap and drift-check when a cheap executor consults an expensive advisor, computing effective cost from actual calls instead of assumed rates. Use when adopting the advisor pattern or quoting benchmark discounts.

Before swapping to a cheaper AI model, declare the cases where the premium model still dominates and enforce routing rules. Use when evaluating cost-cutting model swaps for text, image, or video tasks.

Reduce token usage by indexing a codebase so agents query the index instead of re-reading files. Use when context windows fill up fast or the bill scales with conversation length.

Performs a five-lens decomposition of project stories to define architecture, record persistent schema decisions, and plan the first slice. Use after repo seeding or when foundational decisions need revisiting.

Find Anyone builds a sourced profile of one specific person from public records, professional profiles, court filings, and other open sources. It is used to identify, verify, or background-check someone while avoiding name-mixups.

Follow The Crypto traces Bitcoin and Ethereum addresses and transactions across public blockchains using explorers and clustering heuristics. Use it to track ransom or scam payments, find off-ramps, and screen addresses for sanctions or fraud.

Routes high-volume, low-stakes content triage to free AI models, returning one-sentence summaries and a needs-reply flag to decide what to read without premium costs.

Size a big one-time batch job against a free tier's rate limit and token budget before starting, with a proven wall-clock ETA. Use for labeling datasets, summarizing archives, or processing large backlogs on free tiers.