Civic technology · applied AI · public systems
I’m La Shara Cordero, a court operations leader and applied AI product builder who believes in learning by doing. I design working prototypes that make evidence, decisions, and unknowns easier to inspect.
§ 01 · Selected work
These projects are the result of learning by doing—separating what a system observed from what it concluded, while keeping human authority visible.
Flagship · civic AI · readiness intelligence
The AI reads the record. It never assigns the score.
A cited public record readiness surface for California superior courts. A bounded agent locates and extracts evidence. A deterministic registry calculates the result. Every claim can be checked and every unknown remains declared.
GPT 5.6 · Tavily · Next.js · deterministic TypeScript engine · recomputable audit bundle · published methods
Empirical product research
Shows developers what retrieval agents experience when they read a website. Deterministic checks, a published methodology, and a fifty site benchmark make the second audience visible.
AWS Lambda · Bedrock · DynamoDB · Vercel · fifty site benchmark
Education · Personalized AI learning
A stateless, privacy-focused tool providing personalized learning paths through verified free resources. Formulates custom curricula based on learner goals and style.
Next.js · AWS Amplify · Amazon Nova · AWS Lambda · S3 · TypeScript CDK
Court service · policy alignment
Role-based AI readiness guidance for court staff. Evaluates specific court workflows against sensitivity guidelines to determine where AI can safely assist and where human authority must remain.
Claude Haiku · AWS Bedrock · AWS Amplify · server-side PDF engine
§ 02 · Operating philosophy
Trust is not a tone of voice layered over a product. It is the result of assigning evidence, calculation, uncertainty, and authority to the right parts of the system.
Consequential claims remain connected to their sources. Retrieval and inference are not treated as the same thing.
Rules, boundaries, failure behavior, and deterministic calculations belong in the architecture before a model is invited in.
AI can retrieve, extract, explain, and prepare. It should not quietly acquire the power to decide.
§ 03 · Selected writing
I write through the failures, costs, wrong assumptions, and product decisions that disappear from polished launch posts.
I wasn’t going to enter. 33 apps and an unexpected bill later, here’s the post-mortem.
Product judgment · AI buildingWhen the agents delivered exactly what the specification requested and the product still failed the intent.
Career · identity · civic technologyEntering the rooms you earned while other people are still deciding who they think you are.
§ 04 · About
The code is newer. The systems judgment is not.
I spent over ten years inside court operations and government before I began building software. I started this journey with a simple philosophy: learn by doing. Rather than analyzing AI from a distance, I began building tools in 2025 to test my questions through working systems. That experience shaped the questions I bring to technology: Who has authority? What evidence supports the claim? What happens when the data is incomplete? Who carries the consequence when an implementation fails?
I began building AI tools in 2025 to test those questions through working systems rather than presentations alone. Since then, I have shipped across civic technology, agent readiness, developer tools, education, and public service.
I build through a directed, review intensive AI workflow. I define the problem, architecture, constraints, acceptance criteria, and design. AI accelerates implementation. I inspect, test, and approve the result.
33 apps built in 31 days during Netlify’s Agent Runner build challenge.
Measures coding growth from shipped work.
Preserves reasoning across fast AI builds.
Local first research memory with transparent reasoning.
Plain language code learning for career switchers.
Repository insights without judgment.
The proof of concept that preceded Agentis Lux.
Deterministic policy controls for AI code changes.
Audits documentation claims against code.
Plain language jury information grounded in the court’s own public record.
Autonomous debugging with reusable principles.
Agent readiness review for AWS commits.
Intelligent open source project discovery.
A renter controlled application readiness copilot for affordable housing.
Document extraction tested against public court forms.
A finding that identified data quality as the blocker.
First pass data quality briefing for tabular data.
Cybersecurity awareness for court staff.
Tea leaf reading for code, steeped in evidence.
A challenge triage agent that hedges its judgment.
A proposed pair of homemade Meshtastic radios.
§ 05 · Contact
Open to public sector AI product roles, civic technology collaborations, responsible AI pilots, speaking, and applied research partnerships.
