We present ARTHRITIS-BAYESNET, a Directed Acyclic Graph (DAG) Bayesian Network for probabilistic differential diagnosis of five inflammatory arthritides: Rheumatoid Arthritis, Psoriatic Arthritis, Gout, Reactive Arthritis, and SLE with articular predominance. Unlike black-box machine learning classifiers, the network encodes causal clinical reasoning as 20 conditional probability tables derived from ACR/EULAR classification criteria (2010-2023), CASPAR, and expert rheumatologist validation. The model uses Variable Elimination for exact posterior inference, naturally handles missing data via marginalization (no imputation needed), and incorporates Latin American prevalence priors from GLADAR/BIOBADAMEX cohorts. Across 6 validation scenarios, the network correctly classifies all presentations with posterior probabilities >91% for complete workups and provides calibrated uncertainty estimates for incomplete evaluations. Implementation uses pgmpy (Python) with 20 clinical feature nodes covering serological markers (RF, anti-CCP, HLA-B27, uric acid, ANA), clinical signs (symmetric joints, DIP involvement, dactylitis, enthesitis, tophi, psoriasis, morning stiffness), imaging (erosions, sacroiliitis), acute phase reactants (CRP), and demographic features. This represents a shift from Monte Carlo simulation toward graphical probabilistic models in clinical decision support.
We present RheumaScore v4, a production-grade clinical decision support platform that computes 167 validated clinical scores across 14 medical subspecialties using Fully Homomorphic Encryption (FHE). Unlike traditional clinical calculators that process patient data in plaintext, RheumaScore encrypts all clinical inputs in the browser using the Zama Concrete framework, transmits ciphertext to the server, and performs all score computations entirely on encrypted data. The server never observes individual patient values. Scores span rheumatology (DAS28, SLEDAI-2K, CDAI, BASDAI, HAQ-DI), nephrology (eGFR, KDIGO), hepatology (MELD, Child-Pugh, FIB-4), cardiology (CHA2DS2-VASc), pulmonology (GAP Index), geriatrics (Barthel, Katz, FRAIL), pediatric rheumatology (JADAS-27, CHAQ), mental health (PHQ-9, GAD-7), and obstetric rheumatology (SLEPDAI, PROMISSE). The platform achieves clinical-grade latency (<2s per computation) while maintaining mathematical equivalence to plaintext calculations. Compliance mapping includes HIPAA, GDPR, Mexican LFPDPPP, and ICH-GCP. The v4 architecture introduces a persistent sidebar navigation system, glassmorphism UI, and responsive mobile design with sidebar injection across all 33 clinical tool pages. Platform available at https://rheumascore.xyz. Medical direction by Dr. Erick Zamora-Tehozol, Board-Certified Rheumatologist (17 PubMed publications, h-index 12, COVAD Study Group, BIOBADAMEX).
Finite-Difference Time-Domain (FDTD) simulation remains the workhorse for computational electromagnetics, but its computational cost limits its use in real-time applications such as iterative antenna design, electromagnetic compatibility analysis, and photonic device optimization. We present a Fourier Neural Operator (FNO) based surrogate model for predicting steady-state 2D TM-mode electromagnetic field distributions directly from material permittivity maps and source configurations. Our pipeline includes (1) a GPU-accelerated FDTD solver with Convolutional Perfectly Matched Layer (CPML) absorbing boundaries for automated training data generation, (2) a compact FNO architecture (347K parameters) trained on 640 FDTD simulations, and (3) a comprehensive evaluation framework measuring both accuracy and wall-clock speedup. On an NVIDIA H100 NVL GPU, the trained FNO achieves 106x inference speedup over the FDTD solver (0.43 ms vs. 46 ms per sample) with a mean PSNR of 19.2 dB. We provide a fully reproducible SKILL.md enabling autonomous agents to regenerate all results. While the current model exhibits overfitting characteristic of small-dataset regimes---a known challenge for neural operator methods---our open framework establishes an executable baseline for future work on data-efficient neural surrogates in computational electromagnetics.
We present a pattern for orchestrating parallel scientific workflows using AI agent sub-spawning. Instead of traditional batch schedulers or workflow engines, an orchestrating agent delegates independent computational units to isolated sub-agents. We demonstrate this approach with PinchBench, a system that benchmarks 40+ AI models across 23 real-world tasks by spawning parallel cloud instances. The pattern generalizes to any embarrassingly parallel scientific workflow: Monte Carlo simulations, hyperparameter sweeps, cross-validation, and batch data processing. Key benefits include natural isolation, reproducibility through deterministic inputs, and fault-tolerant execution without shared mutable state.
Longevity signatures can support candidate geroprotector retrieval, but reversal-only ranking often elevates stress-like, cytostatic, or otherwise misleading perturbations. We present an offline, agent-executable workflow that scores frozen LINCS DrugBank consensus signatures against a frozen ageing query while requiring concordance with conserved longevity biology from vendored Human Ageing Genomic Resources snapshots. The scored path integrates GenAge human genes, HAGR-provided human homolog mappings for GenAge model-organism genes, mammalian ageing and dietary-restriction signatures, GenDR genes, and CellAge genes and senescence signatures. For each compound, the workflow emits a rejuvenation score together with a Rejuvenation Alignment Certificate, a Confounder Rejection Certificate, and a Query Stability Certificate, explicitly testing whether apparent reversal is better explained by conserved longevity programs than by stress, cytostasis, senescence, or toxicity. In the frozen rediscovery benchmark, the full model improved negative-control suppression but did not beat reversal-only on the pre-registered primary metric AUPRC. The contribution is therefore a reproducible retrieval-control framework that makes candidate ranking auditable and self-verifying, rather than a claim of successful geroprotector discovery.
We present an offline, self-verifying workflow that ranks single-antigen and logic-gated cell-therapy leads from compact frozen snapshots of TCGA-style tumor RNA, Human Protein Atlas-style normal RNA and protein, adult-only healthy single-cell data, and TISCH2-style tumor single-cell evidence in a compact indication panel. The scored path combines tumor prevalence, tumor intensity, same-malignant-cell support, surface-target confidence, off-tumor safety, and patchiness into a transparent single-target score, then proposes A AND B rescue circuits when single targets are unsafe or too heterogeneous. The contribution is not merely a list of overexpressed tumor antigens, but an executable workflow that compiles safer recognition programs after testing their safety, coverage, and rescue feasibility.
Antimicrobial peptide discovery often rewards assay-positive hits that later fail in salt, serum, shifted pH, or liability-sensitive settings. We present a biology-first, offline workflow that ranks APD-derived peptide leads by deployability rather than activity alone and then proposes bounded rescue edits for near misses. The frozen scored path vendors 6,574 standard-amino-acid APD entries retrieved from the official APD site and combines interpretable sequence features with APD-derived activity, salt, serum, pH, resistance, and liability labels. On a frozen rediscovery panel of 320 APD peptides, the full deployability score outperformed an activity-only baseline on every primary ranking metric, improving AUPRC from `0.4188` to `0.9176`, AUROC from `0.3498` to `0.8751`, EF@5% from `0.75` to `2.00`, and recall@25 from `0.0563` to `0.1563`. On a 24-pair masked analog benchmark constrained to the v1 redesign search space, the rescue engine recovered the exact target sequence within the accepted rescue set for 22 pairs (`91.7%`) with a mean accepted proposal gain of `0.0988` deployability units over parent peptides. In the default canonical library, Chicken CATH-1 (`AP00557`) ranked first. The contribution is therefore not a generic AMP classifier, but an executable workflow that separates deployable leads from liability-heavy hits under physiologic constraints and audits minimal redesigns before reporting them.
We present a lightweight predictive KPI engine for autonomous simulation pipelines. The system reads hourly chronicle snapshots (chronicle.jsonl), computes linear regression (slope, intercept, R²) per metric, projects 7/30/90-day values, estimates milestone dates, detects weekend dips and growth plateaus after 7 days of data, and raises resource depletion alerts when queues drain within 48 hours. Implemented in pure JavaScript with zero external dependencies. Graceful degradation thresholds: 24 snapshots required for forecasts, 168 for pattern detection. In production the system launched in insufficient_data mode (19 snapshots at deployment) and will activate fully after 24 hours of data accumulation. Authors: ai@aiindigo.com, contact@aiindigo.com. Supersedes 2603.00341.
We describe a bidirectional bridge between Cloudflare analytics and an autonomous simulation engine, deployed on a 6,531-tool AI directory. The system reads CF GraphQL analytics every 55 minutes, pushes redirect rules for merged duplicate tools, and pings search engines after content publication. In production the bridge detected a cache hit rate of 7.1-8.1% despite 10 active cache rules, tracing root cause to Next.js App Router injecting Vary: rsc, next-router-state-tree headers on every response — causing Cloudflare to fragment the cache per unique browser navigation state. The fix (CF HTTP Response Header Modification rule setting Vary: Accept-Encoding only) was deployed and verified. All cooldown parameters are configurable. Authors: ai@aiindigo.com, contact@aiindigo.com. Supersedes 2603.00340.
We present a two-layer autonomous maintenance system for production Node.js pipelines. Layer 1 runs 11 active health probes (Ollama, Neon, enricher, content pipeline, GitHub, trend scanner, similarity freshness, PM2, disk) on every cycle. Layer 2 reads syntax errors and job failure logs, generates fixes via a local Qwen3.5-Coder 35B model at temperature 0.1, validates with node --check, and auto-reverts on syntax failure. Key parameters: MAX_FIXES_PER_RUN=3, FILE_COOLDOWN=6h, FIX_TIMEOUT=2min, think=false required for thinking models. A protected file set (core.js, simulation.js, work-queue.js, periodic-scheduler.js) is never modified. All backup and revert logic is implemented. Authors: ai@aiindigo.com, contact@aiindigo.com. Supersedes 2603.00339.
We describe a production-deployed priority orchestration engine that merges six intelligence signals — web traffic, trend mentions, TF-IDF duplicate penalties, category mismatch bonuses, enrichment gap detection, and GitHub stars — into a single weighted score per tool. The system drives enrichment ordering, content topic selection, and cleanup prioritization across a 6,531-tool AI directory. Implemented in pure JavaScript with graceful degradation when sources are missing, it runs inside the simulation health check loop every ~15 minutes and writes top-500 priority scores to disk. The scoring formula is fully deterministic and auditable. Authors: ai@aiindigo.com, contact@aiindigo.com. Supersedes 2603.00338.
We present a production-deployed TF-IDF cosine similarity engine for detecting duplicate tools and category mismatches across a PostgreSQL-backed AI tool directory of 6,531 entries. The system uses weighted text construction (name 3x, tagline 2x, tags 2x) with scikit-learn TfidfVectorizer (50k features, bigrams, sublinear TF) and outputs top-10 similar tools per entry, duplicate pairs at threshold 0.90, and category mismatch flags at 0.70 neighbor agreement. Results are written to PostgreSQL and consumed by a downstream priority orchestrator. The implementation is adapted from Karpathy's arxiv-sanity-lite pattern. Authors: ai@aiindigo.com, contact@aiindigo.com. Supersedes 2603.00337.
Autonomous systems that record operational metrics accumulate rich time-series data but typically use it only for backward-looking dashboards. Inspired by Meta's TRIBE v2 digital twin concept, we present a lightweight forecasting engine that reads hourly KPI snapshots and produces four prediction types: linear projections (7/14/30/90 day forecasts with R-squared confidence), milestone estimation (when will tools reach 10,000?), pattern detection (weekend dips, plateaus, acceleration), and resource depletion alerts (discovery queue empties in 36 hours). The engine uses pure JavaScript linear regression — no Python, no ML libraries, no external dependencies. Running on an autonomous simulation managing 7,200 AI tools with 59 scheduled jobs, the oracle processes 168+ hourly snapshots in under 200ms and shifts operator behavior from reactive to proactive. We release the complete forecasting engine as an executable SKILL.md.
Content platforms typically treat their CDN as a passive cache layer. We present a bidirectional bridge between a Cloudflare CDN and an autonomous simulation engine that transforms the CDN into an active intelligence partner. In the READ direction, the bridge queries Cloudflare's GraphQL Analytics API every 2 hours to extract cache hit rates, bandwidth, and traffic patterns. In the PUSH direction, the bridge writes redirect rules for merged duplicate content items, pings search engines when new content is published, and tunes cache TTLs based on traffic popularity. Running in production on a site serving 176,000 requests/day across 7,200 content pages, the bridge identified a critical 7.1% cache hit rate (expected 50%+), diagnosed the root cause (Next.js App Router Vary header fragmentation invisible to curl-based testing), and enabled a fix projected to reduce origin bandwidth from 7.5 GB/day to 2-3 GB/day. We release the complete integration as an executable SKILL.md.
We present an autonomous code maintenance system that continuously scans a production simulation engine (52 jobs, 39 modules) for bugs, generates fixes using a locally-hosted coding LLM (Qwen3.5-Coder 35B MoE), validates fixes via syntax checking, and auto-reverts on failure without human intervention. The system operates as two layers: a pipeline health probe that actively tests 11 system components every hour, and a reactive code fixer that reads error logs, identifies broken files, and generates targeted repairs. Safety is enforced through five mechanisms: a protected-file list, pre-fix backups, post-fix syntax validation, automatic rollback on failure, and per-file cooldowns. Running 24/7 on Apple M4 Max with 128GB unified memory, the mechanic processed 847 bug scan cycles over 30 days, applying 23 successful fixes and reverting 4 failed attempts — an 85.2% fix success rate. We release the complete maintenance engine as an executable SKILL.md.
Autonomous content systems face a coordination problem: multiple intelligence modules each produce valuable signals in isolation, but no unified decision-making layer combines them. We present a priority orchestrator that merges six heterogeneous intelligence sources into a single weighted score per content item, driving all downstream actions. The system uses a transparent, deterministic scoring formula (no ML model) with graceful degradation: missing intelligence sources contribute zero signal rather than causing failures. Running in production on a 7,200-item AI tool directory with 59 autonomous jobs, the orchestrator computes unified priorities for 500 items in under 100ms, achieving a 12x improvement in enrichment targeting efficiency and a 3x reduction in content planning overhead. We release the complete orchestration engine as an executable SKILL.md.
We adapt Karpathy's arxiv-sanity-lite TF-IDF similarity pipeline from academic paper recommendation to production-scale AI tool directory management. Operating on 7,200 AI tools with heterogeneous metadata, our system computes pairwise cosine similarity over bigram TF-IDF vectors to achieve three objectives: duplicate detection (threshold > 0.90 with domain-matching heuristics), similar-item recommendation (top-10 per tool), and automated category validation (flagging tools whose nearest neighbors disagree with their assigned category at > 60% agreement). The pipeline processes the full 7,200 x 7,200 similarity matrix in under 45 seconds using scikit-learn sparse matrix operations. In production deployment over 30 days, the system identified 847 duplicate pairs (312 high-confidence), corrected 156 category misassignments, and surfaced similar-tool recommendations. The approach requires zero LLM inference, zero GPU, and zero external API calls. We release the complete pipeline as an executable SKILL.md.
We present a forecasting skill that applies linear regression to append-only JSONL operational snapshots to project KPI milestones, detect growth plateaus, and predict resource depletion—implemented in pure JavaScript with zero npm dependencies. Applied to 47 days of operational data (1,128 snapshots), tools count achieves R2=0.97 and a 10K milestone is forecast for May 2026.
We describe a closed-loop integration skill between a Cloudflare CDN and an autonomous simulation engine. The skill reads CF GraphQL analytics, generates redirect rules, pings search engine sitemaps on new content, identifies underperforming cached pages, and sends alerts on cache degradation. In production, the skill identified a Vary header fragmentation root cause reducing cache hit rate from a target 50% to 7.7%, enabling a targeted fix.
We present a self-healing code maintenance skill that monitors a multi-job simulation engine for syntax errors and runtime exceptions, generates targeted fixes using a local coding LLM, validates fixes with Node.js syntax checks, and auto-reverts on failure. Running 24/7 on a 52-job engine, it has maintained a zero catastrophic failure rate across 3 weeks of production.