Skip to content
View earlgreyhot1701D's full-sized avatar

Block or report earlgreyhot1701D

Block user

Prevent this user from interacting with your repositories and sending you notifications. Learn more about blocking users.

You must be logged in to block users.

Content in all repositories owned by your account will be closed.
Maximum 250 characters. Please don’t include any personal information such as legal names or email addresses. This note will only be visible to you.
Report abuse

Contact GitHub support about this user’s behavior. Learn more about reporting abuse.

Report abuse
earlgreyhot1701D/README.md

L. CORDERO: Court operator who builds. Auditable AI for courts and the people they serve.

01 Captain's Log (About)

I run courtroom operations at Santa Barbara Superior Court: courtroom clerks, court reporters, and court interpreters. Ten years inside California courts taught me how systems serve people, and exactly where they fall short.

In July 2025 I started building AI tools from the inside of the institution, not at it. I direct, AI generates, I validate. Nothing ships until it holds up. I also speak to court leaders about AI adoption (NACM 2026, Los Angeles Superior Court).

Off duty: Supernote devotee, Lakers lifer, and certain that earl grey hot is the correct order.

🛰️ Open to: roles where civic experience meets AI building. Prototyping, AI enablement, public-sector AI, or a job that didn't exist a year ago. AI-assisted building gave me wings. I want to use them where institutions and the people they serve need a translator.

🎓 Credentials: AWS Certified AI Practitioner · AWS AI/ML Scholar, Agent Engineer Nanodegree (2026) · Certified Court Manager (CCM) · MPA, Claremont Lincoln University · Paralegal Certificate, UCSB · BA Liberal Studies, CSU Long Beach

02 Primary Mission (Featured Project)

Primary mission: Verity Lex, live. Everyone is selling AI to government. Who has checked whether government is ready to buy? Scores a California superior court's AI readiness from its own public record, against Rule of Court 10.430, Gov. Code 68150, and Rule of Court 10.500. An agentic scan gathers evidence. A deterministic rule engine assigns the score. The AI reads the record. It never assigns the score.

🟢 Live · Methods · Demo video · Repo

03 Second in Command (Featured Project)

Second in command: Agentis Lux, live. Your website has a second audience now: AI agents. Shows what retrieval agents experience when they read your site. Paste a URL or an OpenAPI spec, get one report across six categories for frontend and API. Findings, not fixes. Full CI, smoke-tested deploys, SSRF hardening on every redirect hop.

🟢 Live · Demo video · Repo: perseus-clew

04 In Drydock (In Progress)

In drydock: Dead Keys. A typing game, back from the dead. In 2000, almost half of US high school grads took a typing class. By 2019 it was 2.5%. Dead Keys rebuilds the 1980s typing games I grew up on as a trainer that notices which keys you miss and drills them. It picks up where Office Keys left off.

🟡 Repo · PRD · Office Keys, its predecessor

In drydock: Iris Clew. Every comment deserves a reply. Iris makes sure none slip. An agent that keeps track of comments across my dev.to posts and helps reshape each piece for X, daily.dev, and AWS Builder. It asks me for what only I know and learns from my decisions. I still write every reply myself.

🟡 Follow the build on dev.to · Running on Shako · Repo coming soon

05 Active Fleet (Projects)

Ghost Rovers, Kids' Space Console: 12 machines are still on the Moon and Mars. Only 1 still answers. A 1969 Mission Control console where kids radio what NASA left behind. Observator Clew, Estate Watch: Creating is becoming nearly free. Maintaining never did. Watches my GitHub estate and learns when not to bother me. Mk II of Daybreak. Two Sisters Tinctures, Built for My Sister: My little sister is my skincare product whisperer. So I built her a shelf that sorts morning and evening order and flags what shouldn't layer. Clew Directive, AI Learning Paths: Four questions. A personalized path from verified free resources. A PDF you keep forever. No signup, no data stored. README Clew 2, README Audit: READMEs drift. Paste a repo, get a claim ledger: every checkable README line, what the code says, and who decided. Janus Clew, Growth Tracking: You shipped three projects in three months. You're better, but can you prove it? Janus measures it. Evidence, not vibes. Memoria Clew, Research Memory: Bookmarks don't remember why you saved something. Memoria does, and resurfaces it when it matters again. Metis Clew, Code Explainer: What the code does, how it works, and why it was built that way. Validated with career switchers.

Full fleet roster (click to expand)
Vessel Mission Status
Lumen Clew Code health scanner. Awareness, not shame 🟢 Live
Ariadne Clew Turns messy LLM chat sessions into preserved reasoning 🔵
Heimdall Tests whether an AI gateway's access controls actually hold. Evidence for a sponsored dev.to piece 🔵
Daybreak Always-on AWS agent that tracked everything I ship. Mk I of Observator 🔵
Hermes Clew Agent readiness scanner, the proof of concept that became Agentis Lux 🔵
Anton Clew Policy CLI that classifies AI file changes as DENY, NEEDS_APPROVAL, or ALLOW 🔵
README Clew The first version of README Clew 2. I run it on mine. It found things 🔵
TicketGlass Transparency for IT support tickets 🔵
Athena Clew Autonomous debugging agent on Gemini 3 🔵
Argus Clew Agent-readiness review on every AWS commit 🔵
Clew Quest Open source project discovery matched to your learning goals 🔵
Vigil Crest Telegram correspondent that watches the DEV challenge feed 🔵
Clew Forge Lightweight framework for shipping fast without losing clarity 🔵
Propina USD/MXN tip calculator. One prompt, eight minutes, live 🟢 Live
4 GB and a Dream How far can a 4 GB Chromebook go? Four builds, nothing installed, every commit pushed from the chat 🟢 Live
Necesito 🍵 My wife was sick on vacation, so I built her a bilingual papel picado page. One tap texts me what she needs. Its story made DEV's Top 7 🟢 Live
Steep 🫖 Tea leaf reading for your repo. DEV April Fools 2026, Best Use of Google AI 🔵
Office Keys Gamified typing practice for workforce digital literacy 🔵
Sprint-Kit PM skills for middle schoolers. Zero data collection 🔵
Proof of Scoville 🌶️ On-chain salsa tracker. Yes, really. No regrets 🔵
Bench Power: Lakers 🏀 Data storytelling on bench impact 🔵

🟢 Live · 🔵 Docked (repo, run it yourself) · 🟡 In drydock

06 Away Missions (Civic and Legal AI)

Themis Lex, Court Staff Readiness: Plain-English AI readiness check for California court staff, as a PDF you can hand your supervisor. Porch Light, Civic Agent: Watches city meeting agendas for one resident. English and Spanish, a receipt on every claim. Drafts a comment only a human can send.

More away missions (click to expand)
Mission What it does
Permission to Approach the Firewall Cybersecurity awareness program for court staff
12 Angry Rows 11 years of jury utilization data, benchmarked against NCSC standards
Write of Access AWS Textract on public court forms, with honest notes on what it can't do
Hung Jury The blocker was data quality, not Python. Sometimes the finding is the deliverable
Panoptes Scout First-pass data quality briefing agent for tabular datasets

07 Commendations (Awards and Talks)

Commendations: DoraHacks AWS Global Vibe Hackathon (2025): Winner · Draper U scholarship (Janus Clew); AI Vibe Coding Hackathon (2026): Featherless 1st + ElevenLabs Best · 4th of 250; DEV WeCoded Challenge (2026): Winner; DEV April Fools Challenge (2026): Best Use of Google AI (Steep); DEV Top 7 Featured Posts (2026): A Builder in CDMX: Flu Edition (Nov 17); AWS 10,000 AIdeas (2026): Semi-Finalist (Clew Directive); CCC AI Summer Camp, Cal Poly DxHub/AWS (2025): 2nd of 14 · 1 of 100 from 1,300; NACM 2026 Midyear Conference (2026): Building Bridges: Enabling Staff Innovation; Los Angeles Superior Court (2026): Invited: AI adoption for court staff

08 Transmissions from DEV (Writing)

DEV post: Ghost Rovers: I Called 12 Machines NASA Left Behind. One Picked Up.

DEV post: One Month After the Hackathon: Why My 4-Service App Stopped Working (and What @mansio Caught in the Verifiers)

DEV post: Four Applications and One Ask. Guess Which One Scared Me.

💎 7 Community Gems. Gems are DEV's human-curated picks. Trusted curators hand out a limited number each day to spotlight work they think deserves a wider audience. No algorithm, just people with taste.

💎 Picked as a gem Date
Ghost Rovers: I Called 12 Machines NASA Left Behind. One Picked Up. Nov 2026
AI Took Me to Three Stages. I Still Don't Like Public Speaking. Oct 2026
My Agents Never Get Tired. I Do: On Satisficing Sep 2026
Block Zero: Oh, no! Claude, Kiro and I over-engineered the throwaway. Sep 2026
💬 Plus 3 gems for comments, because the conversation counts too

2026 WeCoded Winner April Fools Best Use of Google AI Top 7 JavaScript: top author of the week Community Gems: 4 milestone Community Gems: 2 milestone 24 Week Community Wellness Streak
WeCoded Winner · Best Use of Google AI · Top 7 · JavaScript Author of the Week · 💎 Community Gems · 24-Week Streak

09 Ship's Sensors (GitHub Stats)

Ship's sensors: 80 public repos, 66 DEV posts, 1318 DEV reactions, 2082 contributions this year

Star chart: one star per day of GitHub contributions over the last year, 2082 in total

10 Standing Orders (How I Work)

I don't write code from scratch. I give creative direction and validation: AI tools generate, I compare outputs, pick what works, and stitch it into something that holds up.

  1. Occam's Razor. Solve one problem completely before adding the next.
  2. Single Responsibility. Every component does one thing well.
  3. Deterministic structure, AI flavor. Code decides. The model describes.
  4. Name the limits. What a tool can't do goes in the docs, not under the rug.
  5. Operational Thinking. Ten years in courts means I know implementations have consequences.

11 Hailing Frequencies Open (Contact)

CLEWLABS.ORG (portfolio) DEV.TO (writing) LINKEDIN (connect) FORUM FILES (substack) EMAIL (hail me)

End transmission. AI assisted. Human approved. Powered by NLP.

This page redraws itself daily from the DEV and GitHub APIs. Last sensor sweep: 2026-11-20.

Pinned Loading

  1. Ariadne-Clew Ariadne-Clew Public

    Ariadne Clew is a context engine and reasoning agent for LLM-native builders. It transforms raw chat logs into structured memory artifacts, preserving aha moments, MVP changes, scope creep, README …

    Python 2

  2. Clew-Directive Clew-Directive Public

    AI education is overwhelming — thousands of courses, most behind paywalls, few personalized. Clew Directive cuts through it. 4 questions, a personalized learning path from verified free resources, …

    Python 1

  3. perseus-clew perseus-clew Public

    AgentisLux shows you what retrieval agents (ChatGPT, Perplexity, AI overviews) see when they read your site's raw HTML. For your second audience. Live at agentislux.io.

    JavaScript

  4. themis-lex themis-lex Public

    Themis Lex is a plain-English AI readiness check for California court staff. Tell it your role and workflow, get back what AI can help with and what it must never touch, as a PDF you can hand to yo…

    TypeScript