Structured data fără balast JSON
The invoice hiding in your braces
JSON won because it is boring in exactly the right way. Humans can read it. Machines can parse it. Every language has a library for it. If two systems need to exchange an object and nobody wants a standards meeting, JSON is usually where the conversation ends. Fine. There are worse compromises. Many of them have enterprise in the name.
The problem is not JSON as a web format. The problem is what happens when we push JSON into language-model workflows andpretend the cost is free. A model does not see a tidy object in the way an application parser sees one. It sees tokens. It reads the same keys again and again. It spends context on punctuation, repeated field names, wrappers, nested scaffolding, and shape reminders that were already known before the first record arrived.
That waste used to be mildly irritating. With AI systems, it becomes a product problem. Every repeated key competes with evidence, instructions, examples, citations, and actual user content. Every redundant structural token is a little tax on the useful work. The invoice does not say needless braces, because invoices lack poetry. It says tokens.
HEDL starts from a plain observation: when the schema is known, repeating the schema inside every record is silly. Declare the structure once. Encode records positionally. Keep the semantics exact. Convert back to the formats existing systems already expect. That is not anti-JSON ideology. It is a refusal to pay the model to reread the same road sign every ten metres.
This matters because structured AI work is not just chat. It is extraction, classification, tool calls, data transformation, review packets, evidence bundles, MCP calls, workflows, and agents passing objects to each other all day. The more serious the system becomes, the more structure it needs. If structure is expressed in the most verbose possible way, the system pays for its own discipline.
JSON is not the villain
It would be easy, and lazy, to write this as a JSON complaint. JSON has real strengths. It is ubiquitous, debuggable, easy to pipe through existing tools, and good enough for a huge amount of application work. The point is not that JSON is bad. The point is that JSON is often used in places where the receiving side already knows the shape, and there the repetition stops being clarity and starts being cargo.
Consider a structured extraction task. The schema says every answer has a name, source, value, confidence, and rationale. Now imagine sending hundreds of rows to a model or receiving hundreds of rows back from one. JSON repeats those field names for every object. The application parser does not mind. The model context does. The context window becomes a deliveryvan full of labels instead of goods.
HEDL treats the schema as a contract. It names the fields and types once. The records then carry values in order. That sounds obvious because it is. Many efficient formats have made similar tradeoffs for decades. The difference is that HEDL is aimed at LLM-facing structured workflows where human debuggability, conversion, and tool compatibility still matter. It is not a binary blob lobbed over a wall with a note saying good luck.
Implementarea HEDL include suport pentru biblioteci Rust, utilizare din linia de comandă, suprafețe de server MCP și proxy, WASM, FFI și legături, plus conversia în și din formate comune. Această combinație este importantă. Un format pentru fluxurile de lucru AI nu poate fi doar compact. Trebuie să intre și să iasă din lumea reală fără să devină un cult privat. API-urile existente încă vor JSON. Oamenii încă inspectează datele. Instrumentele încă au nevoie de călătorii dus-întors. Formatul trebuie să fie dens fără să devină antisocial.
Structura ca un contract
Cele mai multe eșecuri AI legate de date structurate nu sunt dramatice. Sunt meschine, ceea ce le face mai greu de respectat până când costă bani reali. Un câmp derivă. O valoare este plasată sub cheia greșită. Un model emite un obiect plauzibil cu un câmp opțional lipsă. Un parser acceptă o formă pe care ar fi trebuit să o respingă. Un instrument din aval primește aproape lucrul corect, cel mai periculos tip de lucru în software.
Abordarea schema-first a HEDL este utilă pentru că face structura explicită înainte ca înregistrările să înceapă să se miște. Schema nu este o sugestie vagă de prompt. Este lucrul care îi spune cititorului cum să interpreteze valorile. Înregistrarea este compactă pentru că nu trebuie să se narativeze în mod repetat. Instrumentele din jur pot încă valida, converti și livra date către sisteme care preferă JSON, YAML, XML, CSV sau alte forme convenționale.
Călătoriile dus-întors sunt testul dacă un format este util sau doar ingenios. Dacă JSON intră, HEDL se deplasează prin fluxul de lucru, iar JSON iese cu aceleași semantici, sistemul câștigă densitate fără a pierde compatibilitatea. Dacă sensul se pierde în tăcere, formatul a eșuat. Comportamentul corect sub presiune nu este să dai din umeri și să trimiți obiectul mai departe. Este să blochezi, să raportezi și să forțezi ambiguitatea la suprafață.
Aici HEDL se așază frumos lângă restul stivei Dweve. Ledger îi pasă ca evenimentele operaționale să rămână inspectabile. AION îi pasă ca dovezile de decizie să poată fi verificate. Trace îi pasă ca calculul să poată fi reluat. HEDL îi pasă ca datele structurate să poată fi reprezentate dens și restaurate exact. Aceste sarcini se ating, dar nu sunt aceeași sarcină. Din nou: mai puține cuvinte calde și vagi, mai multe granițe utile.
Benchmark-ul nu este decor
Afirmațiile despre performanță în jurul infrastructurii AI sunt adesea scrise ca poveștile pescarilor. Numărul crește de fiecare dată când este repovestit. HEDL are o afirmație concretă de benchmark: 571 de sarcini de extracție structurată pe șapte seturi de date, cu 56 de procente mai puține token-uri decât JSON și un câștig de acuratețe de 10,3 puncte procentuale față de JSON.
Aceste numere ar trebui citite ca o afirmație de benchmark, nu ca o lege universală a fizicii. Ele descriu o configurație de benchmark. Nu înseamnă că fiecare flux de lucru primește magic același rezultat. Dar explică de ce există formatul. Numărul de token-uri nu este o notă de subsol de implementare în sistemele LLM. Este parte din interfață. Dacă două reprezentări poartă același sens și una consumă mult mai mult context, cea mai grea nu este neutră.
The accuracy gain is especially interesting. It suggests the benefit is not only cheaper prompts. A cleaner representation can also make the task easier for the model. That should not be surprising. If the model spends less attention on repeated syntactic clutter, it has more room for values and relations. This is the same reason good forms beat messy forms in human work. The human may be smart, but do not hand them a tax form written by a printer having a difficult childhood.
There is a broader design lesson here. AI interfaces should not be judged only by whether the model can cope. Models can cope with many bad interfaces. People can also carry furniture up stairs with poor grip and no plan. That does not make it architecture. A good AI interface reduces avoidable work, exposes structure, preserves meaning, and fails loudly when the structure is wrong.
Why proxy surfaces matter
A format rarely wins by being pure. It wins by fitting the ugly middle. HEDL's MCP and proxysurfaces matter because most organisations cannot simply announce that everything now speaks a new representation. They have existing APIs, data stores, validation rules, dashboards, notebooks, and export formats. Replacing all of that to save tokens would be aheroic way to lose friends.
The proxy pattern is more practical. Let models and tools benefit from dense structured representation where it matters. Convert at the boundary. Validate before data leaves the controlled path. Keep downstream JSON compatibility. Let systems that expect JSON receive JSON, but stop forcing the model to haul the full JSON shape through every internal step.
This is also where governance enters, quietly and usefully. If the proxy validates structure, it can reject malformed objects before they become business facts. If it preserves a lossless round trip, it can prove that conversion did not change the meaning. If it keeps compatibility with existingsystems, it can be adopted without turning every integration into a migration programme. We are European. We have enough migration programmes. Some of them still have steering committees from 2014.
For agent systems, the proxy is even more important. Agents pass structured calls and results across boundaries. They call tools, receive outputs, update memory, produce artifacts, and hand state to other agents. A dense representation with validation keeps those handoffs less wasteful and less ambiguous. It does not make the agent wise. It makes the envelope less stupid. That is a respectable engineering outcome.
Where HEDL should not be used
Every useful tool has a place where it should not be used. HEDL is not a replacement for every JSON file on earth. If asmall config file is read once by a human and edited twice a year, JSON or TOML will survive the tragedy. If a public API needs maximum familiarity and the payloads are tiny, JSON is fine. If the schema is genuinely unknown and ad hoc, schema-once encoding is not the right starting assumption.
HEDL becomes interesting when structure is repeated, volumes are meaningful, model context is expensive, round trips matter, and tools need compatibility at the edges. That is why LLM workflows are such a good fit. They sit precisely at the intersection of structured intent and token economics. They also tend to grow from prototype to production faster than anyone planned, because apparently nobody has learned this lesson despite the entire history of software looking mildly offended in the corner.
The practical adoption path should therefore be narrow. Do not rewrite the organisation. Pick a structured extraction workflow. Pick an agent tool-call path. Pick an MCP proxy boundary. Measure token use, failure rate, validation outcomes, and round-trip fidelity. If the numbers hold, expand. If they do not, keep the boring thing. The goal is not to worship a format. The goal is to stop paying for avoidable structure.
The lesson
The lesson of HEDL is that structure is not free just because it is useful. In ordinary software, repeated keys are mostly an annoyance. In AI workflows, they are context, money, attention, and failure surface. If the schema is known, repeating it in every record is often the least imaginative option available.
HEDL makes a simple trade: declare structure once, encode records densely, preserve semantics, convert back when needed, and validate at the proxy boundary. It is not a replacement for JSON as the common language of the web. It is a better internal envelope for structured AI work where the model should be spending its context on meaning, not on reading the same field names until the heat death of the budget.
That is the useful standard for AI infrastructure. Not cleverness for its own sake. Not novelty tax.Not a format that requires everyone else to suffer. A good layer removes waste, keeps the contract explicit, and lets the rest of the system keep working. HEDL earns its place when the object becomes smaller without the meaning becoming softer.
JSON can stay. It has done nothing wrong. It can even have a cup of coffee. It just does not need to sit inside every model call carrying the same set of keys like a man moving house one spoon at a time.