# schema design

Schema design is the process of defining and organizing the structure, meaning, and constraints of data or metadata for applications and information systems.

This is one page of public article previews, not the complete archive. Follow Next page to continue. Summaries are not the original full articles.

## SGLayout: Schema-Guided Closed-Loop Refinement for LLM-Driven Parameterized Layout Generation

DevFeed: [SGLayout: Schema-Guided Closed-Loop Refinement for LLM-Driven Parameterized Layout Generation](<https://devfeed.tech/articles/sglayout-schema-guided-closed-loop-refinement-for-llm-driven-parameterized-layout-generation-145510.md>)

Original publisher: [Read original article](<https://arxiv.org/abs/2611.25410>)

Author: Siyang Chen, Yuan Pu, Yuhan Qin, Zhaotan Lin, Siyuan Liang, Zhuolun He, Lining Zhang, Bei Yu

Published: 2026-11-20T05:00:00Z

Content type: article

Language: en

Sources: [arXiv: Artificial Intelligence](<https://devfeed.tech/sources/arxiv-artificial-intelligence.md>)

Topics: [Large Language Model](<https://devfeed.tech/topics/llm.md>), [Artificial Intelligence](<https://devfeed.tech/topics/ai.md>), [schema design](<https://devfeed.tech/topics/schema-design.md>)

Tags: [benchmark](<https://devfeed.tech/tags/benchmark.md>), [code-execution](<https://devfeed.tech/tags/code-execution.md>), [compliance](<https://devfeed.tech/tags/compliance.md>), [convergence](<https://devfeed.tech/tags/convergence.md>), [cs-ai](<https://devfeed.tech/tags/cs-ai.md>), [cs-ar](<https://devfeed.tech/tags/cs-ar.md>), [drc](<https://devfeed.tech/tags/drc.md>), [evaluation](<https://devfeed.tech/tags/evaluation.md>), [generation](<https://devfeed.tech/tags/generation.md>), [layout](<https://devfeed.tech/tags/layout.md>), [llm](<https://devfeed.tech/tags/llm.md>), [repair](<https://devfeed.tech/tags/repair.md>), [schema](<https://devfeed.tech/tags/schema.md>), [tasks](<https://devfeed.tech/tags/tasks.md>)

### AI overview

SGLayout uses a structured schema to link code instances to geometric attributes, then maps layout violations back to precise code targets for repair. It checks intent through quantitative structural checks and qualitative vision-language assessment, and checks rule compliance with DRC; this loop repeats until layout convergence. On 112 GDSFactory tasks, it achieved a 76.79% pass rate, versus 50.89% for the strongest baseline.

### Source excerpt

arXiv:2611.25410v1 Announce Type: cross Abstract: Large Language Models (LLMs) have shown strong potential in parameterized layout generation via tool-augmented code synthesis. However, LLMs lack spatial awareness, making one-shot generation unreliable. While layout quality can be evaluated with established techniques, a critical gap remains: geometric-domain evaluation outcomes cannot be directly translated into actionable code-level fixes, trapping iterative refinement in blind refactoring. We propose SGLayout, a self-refining framework that closes this gap via a schema-guided mechanism. Upon code execution, a structured schema captures the correspondence between each code-level instance and its geometric attributes, establishing a bidirectional link between code space and geometry space. Emulating engineer review practices, SGLayout evaluates layouts along two complementary dimensions: intent compliance through quantitative structural checking and qualitative vision-language assessment, and rule compliance through DRC. All identified violations are then back-projected through the schema onto precise code targets, enabling surgical repair. This closed-loop process iterates until layout convergence. On a curated benchmark of 112 parameterized layout generation tasks using GDSFactory, SGLayout achieves a 76.79% pass rate, compared with 50.89% for the strongest baseline.

## Logical Design Tuning via Workload-aware E/R-to-Relational Mapping

DevFeed: [Logical Design Tuning via Workload-aware E/R-to-Relational Mapping](<https://devfeed.tech/articles/logical-design-tuning-via-workload-aware-e-r-to-relational-mapping-142287.md>)

Original publisher: [Read original article](<https://arxiv.org/abs/2611.23632>)

Author: Hasara Kalumin, Amol Deshpande

Published: 2026-11-19T05:00:00Z

Content type: article

Language: en

Sources: [arXiv: Databases](<https://devfeed.tech/sources/arxiv-databases.md>)

Topics: [data-modeling](<https://devfeed.tech/topics/data-modeling.md>), [schema design](<https://devfeed.tech/topics/schema-design.md>), [SQL](<https://devfeed.tech/topics/sql.md>), [rdbms](<https://devfeed.tech/topics/rdbms.md>)

Tags: [applications](<https://devfeed.tech/tags/applications.md>), [approach](<https://devfeed.tech/tags/approach.md>), [arxiv](<https://devfeed.tech/tags/arxiv.md>), [automatically](<https://devfeed.tech/tags/automatically.md>), [based](<https://devfeed.tech/tags/based.md>), [challenge](<https://devfeed.tech/tags/challenge.md>), [cost](<https://devfeed.tech/tags/cost.md>), [cs-db](<https://devfeed.tech/tags/cs-db.md>), [data](<https://devfeed.tech/tags/data.md>), [design](<https://devfeed.tech/tags/design.md>), [designer](<https://devfeed.tech/tags/designer.md>), [execution](<https://devfeed.tech/tags/execution.md>), [execution-plan](<https://devfeed.tech/tags/execution-plan.md>), [existing](<https://devfeed.tech/tags/existing.md>), [experiments](<https://devfeed.tech/tags/experiments.md>), [fixed](<https://devfeed.tech/tags/fixed.md>), [flexibility](<https://devfeed.tech/tags/flexibility.md>), [framework](<https://devfeed.tech/tags/framework.md>), [inheritance](<https://devfeed.tech/tags/inheritance.md>), [logical](<https://devfeed.tech/tags/logical.md>), [mapping](<https://devfeed.tech/tags/mapping.md>)

### AI overview

The paper presents a cost-based framework that chooses a relational schema for an E/R model using a representative workload. It optimizes choices for inheritance and entity and relationship representations, then compiles user E/R queries to SQL so existing relational optimizers can choose physical plans. Experiments on real-world-inspired schemas report that fixed and heuristic mappings vary widely in performance across workloads, while the proposed method achieves competitive performance and avoids pathological cases. The supplied text does not provide quantitative results or implementation details.

### Source excerpt

arXiv:2611.23632v1 Announce Type: new Abstract: Conceptual data models, like the E/R model, can provide a more stable and intuitive user-facing interface and better logical independence for applications, compared to the relational model which is forced to closely mirror the physical representation. However, this flexibility introduces a challenge as well as an opportunity: a single conceptual schema admits many semantically equivalent relational schemas, whose performance can differ substantially across workloads. Traditional mapping methods use a set of predefined transformation rules or designer-selected mapping strategies, rather than optimizing the relational realization with respect to the expected workload. In this paper, we present a cost-based framework for workload-aware conceptual-to-relational mapping. Given an E/R schema and a representative workload, our framework automatically selects an efficient relational schema by optimizing mapping decisions, including inheritance, entity and relationship representations. User-specified E/R queries are compiled into SQL over the selected relational realization, allowing existing relational query optimizers to determine the physical execution plan. Experiments on real-world-inspired schemas show that mapping choices strongly affect performance; fixed or heuristic strategies exhibit large variability across workloads, whereas our approach consistently achieves competitive performance avoiding pathological cases.

## Tracing the Messy Middle: A Runtime Transaction Schema for AI Coding Agents

DevFeed: [Tracing the Messy Middle: A Runtime Transaction Schema for AI Coding Agents](<https://devfeed.tech/articles/tracing-the-messy-middle-a-runtime-transaction-schema-for-ai-coding-agents-142123.md>)

Original publisher: [Read original article](<https://arxiv.org/abs/2611.23234>)

Author: Yuelin Hou, Haorui Li, Lu Chen, Zhen Chen

Published: 2026-11-19T05:00:00Z

Content type: article

Language: en

Sources: [arXiv: Software Engineering](<https://devfeed.tech/sources/arxiv-software-engineering.md>)

Topics: [ai observability](<https://devfeed.tech/topics/ai-observability.md>), [tracing](<https://devfeed.tech/topics/tracing.md>), [schema design](<https://devfeed.tech/topics/schema-design.md>)

Tags: [ai-coding-agents](<https://devfeed.tech/tags/ai-coding-agents.md>), [asynchronous](<https://devfeed.tech/tags/asynchronous.md>), [atm](<https://devfeed.tech/tags/atm.md>), [causality](<https://devfeed.tech/tags/causality.md>), [coaching](<https://devfeed.tech/tags/coaching.md>), [cost](<https://devfeed.tech/tags/cost.md>), [cs-se](<https://devfeed.tech/tags/cs-se.md>), [fallback](<https://devfeed.tech/tags/fallback.md>), [infrastructure](<https://devfeed.tech/tags/infrastructure.md>), [local-first](<https://devfeed.tech/tags/local-first.md>), [observability](<https://devfeed.tech/tags/observability.md>), [optimization](<https://devfeed.tech/tags/optimization.md>), [productivity](<https://devfeed.tech/tags/productivity.md>), [reconciliation](<https://devfeed.tech/tags/reconciliation.md>), [retries](<https://devfeed.tech/tags/retries.md>), [routing-policy](<https://devfeed.tech/tags/routing-policy.md>), [runtime](<https://devfeed.tech/tags/runtime.md>), [schema](<https://devfeed.tech/tags/schema.md>), [sessions](<https://devfeed.tech/tags/sessions.md>), [tracing](<https://devfeed.tech/tags/tracing.md>), [transaction](<https://devfeed.tech/tags/transaction.md>)

### AI overview

The paper proposes recording AI coding agents' runtime activity as structured transactions to expose retries, fallbacks, routing choices, and abandoned sessions that final artifacts miss. Such records could support behavior-based engineering coaching, workflow improvements at failure points, and routing decisions based on total task cost rather than per-request price. The authors describe a runtime transaction schema and initial feasibility with Agent Token Manager (Atm), a local-first prototype that reconciles gateway records with transcript evidence without sending prompt content to external collectors. Scaling this approach still faces challenges: reconciling traces without shared request IDs, linking outcomes across asynchronous systems, and establishing whether interventions cause improvements.

### Source excerpt

arXiv:2611.23234v1 Announce Type: new Abstract: AI coding agents are increasingly integrated into software development, yet the field lacks a systematic feedback loop to improve their behavior in practice. Artifact datasets capture final outputs such as code patches, commits, and benchmark outcomes, but omit the messy middle of the development lifecycle: the failed retries, fallback strategies, routing decisions, and abandoned sessions that determine operational cost, reliability, and productivity. We propose an observability framework that captures these runtime behaviors as structured transaction records, enabling engineering coaching grounded in behavioral evidence, workflow optimization at the stages where tasks break down, and routing policy iteration measured by total task cost rather than per-request price. We define the runtime transaction schema this architecture requires and demonstrate initial feasibility through Agent Token Manager (Atm), a local-first prototype that reconciles gateway records and transcript evidence without exposing prompt content to external collectors. Finally, we identify three open research problems that must be solved to scale these feedback mechanisms: trace reconciliation without shared request identifiers, outcome linking across asynchronous systems, and intervention causality. Treating the linkage between sessions and artifacts as a fundamental infrastructure requirement provides a structured foundation for understanding and optimizing agent behavior.

## Nutrient Data Extraction API: JSON Matching Your Schema With Per-Field Citations and Confidence

DevFeed: [Nutrient Data Extraction API: JSON Matching Your Schema With Per-Field Citations and Confidence](<https://devfeed.tech/articles/nutrient-data-extraction-api-json-matching-your-schema-with-per-field-citations-and-confidence-142244.md>)

Original publisher: [Read original article](<https://www.marktechpost.com/2026/11/18/nutrient-data-extraction-api-citations-confidence/>)

Author: Asif Razzaq

Published: 2026-11-19T03:23:50Z

Content type: article

Language: en

Sources: [MarkTechPost](<https://devfeed.tech/sources/marktechpost.md>)

Topics: [document ai](<https://devfeed.tech/topics/document-ai.md>), [API](<https://devfeed.tech/topics/api.md>), [JSON](<https://devfeed.tech/topics/json.md>), [schema design](<https://devfeed.tech/topics/schema-design.md>)

Tags: [agentic-ai](<https://devfeed.tech/tags/agentic-ai.md>), [ai-shorts](<https://devfeed.tech/tags/ai-shorts.md>), [api](<https://devfeed.tech/tags/api.md>), [applications](<https://devfeed.tech/tags/applications.md>), [artificial-intelligence](<https://devfeed.tech/tags/artificial-intelligence.md>), [computer-vision](<https://devfeed.tech/tags/computer-vision.md>), [confidence](<https://devfeed.tech/tags/confidence.md>), [data-extraction](<https://devfeed.tech/tags/data-extraction.md>), [editors-pick](<https://devfeed.tech/tags/editors-pick.md>), [embedding-model](<https://devfeed.tech/tags/embedding-model.md>), [enterprise-ai](<https://devfeed.tech/tags/enterprise-ai.md>), [for-devs](<https://devfeed.tech/tags/for-devs.md>), [generative-ai](<https://devfeed.tech/tags/generative-ai.md>), [json](<https://devfeed.tech/tags/json.md>), [language-model](<https://devfeed.tech/tags/language-model.md>), [new-releases](<https://devfeed.tech/tags/new-releases.md>), [ocr](<https://devfeed.tech/tags/ocr.md>), [promote](<https://devfeed.tech/tags/promote.md>), [schema](<https://devfeed.tech/tags/schema.md>), [sponsored](<https://devfeed.tech/tags/sponsored.md>), [staff](<https://devfeed.tech/tags/staff.md>), [studio](<https://devfeed.tech/tags/studio.md>), [technology](<https://devfeed.tech/tags/technology.md>), [test](<https://devfeed.tech/tags/test.md>), [uncategorized](<https://devfeed.tech/tags/uncategorized.md>), [vision-language-model](<https://devfeed.tech/tags/vision-language-model.md>)

### AI overview

Nutrient's Extraction API maps PDFs, scans, images, and Office files to a supplied JSON schema, attaching page and region citations, match labels, and confidence when available. Studio lets teams draft schemas, inspect results on fresh documents, save versioned processors, and evaluate them against up to 25 reviewed documents. Parsing modes include structure, understand, and agentic; Auto routes pages among them, while omitted mode defaults to understand. Confidence combines optional signals and can be missing; even a grounded value may answer the wrong field, so the article's example checks match labels before confidence and still calls for type and business-rule validation. The service is available in Nutrient's cloud, through an SDK on customer servers, or on Apple silicon; fully offline production requires the SDK. Nutrient reports an 86.2 WholeDoc Bench score for agentic mode, but says the benchmark measures parsing rather than extraction accuracy, its main test set is private, and cross-page tables and charts remain difficult.

### Source excerpt

Nutrient Data Extraction API parses PDFs, scans and Office files into JSON matching your schema. Fields carry page, region and match-label citations, and Studio lets teams test before writing code. The post Nutrient Data Extraction API: JSON Matching Your Schema With Per-Field Citations and Confidence appeared first on MarkTechPost.

## Data Contracts

DevFeed: [Data Contracts](<https://devfeed.tech/articles/data-contracts-142435.md>)

Original publisher: [Read original article](<https://martinfowler.com/articles/data-contracts.html>)

Author: Martin Fowler (martin@martinfowler.com)

Published: 2026-11-18T14:02:00Z

Content type: article

Language: en

Sources: [Martin Fowler](<https://devfeed.tech/sources/martin-fowler.md>)

Topics: [data](<https://devfeed.tech/topics/data.md>), [schema design](<https://devfeed.tech/topics/schema-design.md>), [Data Quality](<https://devfeed.tech/topics/data-quality.md>), [semantic-layer](<https://devfeed.tech/topics/semantic-layer.md>), [schema-evolution](<https://devfeed.tech/topics/schema-evolution.md>), [CI/CD](<https://devfeed.tech/topics/cicd.md>), [Test automation](<https://devfeed.tech/topics/test-automation.md>)

Tags: [agents](<https://devfeed.tech/tags/agents.md>), [ai](<https://devfeed.tech/tags/ai.md>), [ai-agents](<https://devfeed.tech/tags/ai-agents.md>), [contracts](<https://devfeed.tech/tags/contracts.md>), [data](<https://devfeed.tech/tags/data.md>), [data-contracts](<https://devfeed.tech/tags/data-contracts.md>), [data-products](<https://devfeed.tech/tags/data-products.md>), [datasets](<https://devfeed.tech/tags/datasets.md>), [enterprises](<https://devfeed.tech/tags/enterprises.md>), [guarantees](<https://devfeed.tech/tags/guarantees.md>), [interfaces](<https://devfeed.tech/tags/interfaces.md>), [metadata](<https://devfeed.tech/tags/metadata.md>), [practices](<https://devfeed.tech/tags/practices.md>), [robustness](<https://devfeed.tech/tags/robustness.md>), [services](<https://devfeed.tech/tags/services.md>)

### AI overview

Data contracts make a provider's dataset promises explicit and machine-readable, covering schema and meaning, quality checks, service levels, usage terms, ownership, and access details. The article presents ODCS as a YAML standard for these contracts and recommends validating promises automatically in CI/CD and against production data. Versioning helps detect breaking changes and phase in replacements; contracts can also connect to data products, ontologies, and marketplaces, giving consumers and AI agents context for finding, joining, and using data. They require ongoing effort and accountable ownership, so the article recommends starting with cross-team data interfaces where quality problems, broken pipelines, or miscommunication are costly.

### Source excerpt

Data contracts are a way to describe the contents and guarantees of datasets. Simon Harrer and Arif Wider describe in detail what they are and how to use them. They apply practices from API design to data by treating them as data-providing services - such as data products - whose interfaces we want to define as clearly as possible. This approach significantly increases the robustness of large-scale data landscapes, and gives both people and AI agents the explicit, trustworthy metadata they need to work with data autonomously, which is why more and more enterprises are adopting them. more...

## Star Schema vs. OBT for Data Warehouse Performance | Blog | Fivetran

DevFeed: [Star Schema vs. OBT for Data Warehouse Performance | Blog | Fivetran](<https://devfeed.tech/articles/star-schema-vs-obt-for-data-warehouse-performance-blog-fivetran-140258.md>)

Original publisher: [Read original article](<https://wf.fivetran.com/blog/star-schema-vs-obt>)

Author: Michael Kaminsky

Published: 2026-11-18T04:42:41Z

Content type: comparison

Language: en

Sources: [Fivetran Blog](<https://devfeed.tech/sources/fivetran-blog.md>)

Topics: [schema design](<https://devfeed.tech/topics/schema-design.md>), [Amazon Redshift](<https://devfeed.tech/topics/amazon-redshift.md>), [database-optimization](<https://devfeed.tech/topics/database-optimization.md>), [etl](<https://devfeed.tech/topics/etl.md>), [data](<https://devfeed.tech/topics/data.md>)

Tags: [analysis](<https://devfeed.tech/tags/analysis.md>), [analysts](<https://devfeed.tech/tags/analysts.md>), [architecture](<https://devfeed.tech/tags/architecture.md>), [benchmark](<https://devfeed.tech/tags/benchmark.md>), [bi](<https://devfeed.tech/tags/bi.md>), [bigquery](<https://devfeed.tech/tags/bigquery.md>), [blog](<https://devfeed.tech/tags/blog.md>), [cache](<https://devfeed.tech/tags/cache.md>), [caching](<https://devfeed.tech/tags/caching.md>), [customer](<https://devfeed.tech/tags/customer.md>), [customers](<https://devfeed.tech/tags/customers.md>), [data](<https://devfeed.tech/tags/data.md>), [data-mining](<https://devfeed.tech/tags/data-mining.md>), [data-warehouse](<https://devfeed.tech/tags/data-warehouse.md>), [fivetran](<https://devfeed.tech/tags/fivetran.md>), [performance](<https://devfeed.tech/tags/performance.md>), [schema](<https://devfeed.tech/tags/schema.md>), [star](<https://devfeed.tech/tags/star.md>), [vs](<https://devfeed.tech/tags/vs.md>), [warehouse](<https://devfeed.tech/tags/warehouse.md>)

### AI overview

In BI-style tests using TPC-DS 100 data, a denormalized one big table (OBT) generally returned queries faster than a star schema across Redshift, Snowflake, and BigQuery, with reported gains of roughly 25-50%. Results varied by warehouse: Redshift favored OBT in nine of ten queries; Snowflake showed mixed results, with star schema faster on some simpler queries; BigQuery averaged a 49% improvement for OBT and favored it in every tested category. The benchmark covers selected BI queries within each warehouse, not comparisons between warehouses or arbitrary ad hoc workloads. OBT avoids query-time joins, but takes more disk space: on the tested Redshift setup, materializing it raised usage from just over 30 GB to over 90 GB, and a larger join exceeded available space. The article also cites star schema's clearer organization and easier navigation for analysts.

### Source excerpt

Which data warehouse schema offers better performance? Let's find out.

## Why Your Customer Data Platform Should Be the Data Warehouse | Blog | Fivetran

DevFeed: [Why Your Customer Data Platform Should Be the Data Warehouse | Blog | Fivetran](<https://devfeed.tech/articles/why-your-customer-data-platform-should-be-the-data-warehouse-blog-fivetran-140207.md>)

Original publisher: [Read original article](<https://wf.fivetran.com/blog/customer-data-platform-data-warehouse>)

Author: Tejas Manohar

Published: 2026-11-18T03:38:23Z

Content type: opinion

Language: en

Sources: [Fivetran Blog](<https://devfeed.tech/sources/fivetran-blog.md>)

Topics: [Data Management](<https://devfeed.tech/topics/data-management.md>), [etl](<https://devfeed.tech/topics/etl.md>), [schema design](<https://devfeed.tech/topics/schema-design.md>), [vendor lock-in](<https://devfeed.tech/topics/vendor-lock-in.md>), [Amazon Redshift](<https://devfeed.tech/topics/amazon-redshift.md>)

Tags: [2](<https://devfeed.tech/tags/2.md>), [2019](<https://devfeed.tech/tags/2019.md>), [3](<https://devfeed.tech/tags/3.md>), [about](<https://devfeed.tech/tags/about.md>), [accessible](<https://devfeed.tech/tags/accessible.md>), [account](<https://devfeed.tech/tags/account.md>), [blog](<https://devfeed.tech/tags/blog.md>), [consider](<https://devfeed.tech/tags/consider.md>), [customer](<https://devfeed.tech/tags/customer.md>), [customer-data](<https://devfeed.tech/tags/customer-data.md>), [customer-data-platform](<https://devfeed.tech/tags/customer-data-platform.md>), [data](<https://devfeed.tech/tags/data.md>), [data-platform](<https://devfeed.tech/tags/data-platform.md>), [data-platforms](<https://devfeed.tech/tags/data-platforms.md>), [data-warehouse](<https://devfeed.tech/tags/data-warehouse.md>), [fivetran](<https://devfeed.tech/tags/fivetran.md>), [instead](<https://devfeed.tech/tags/instead.md>), [platform](<https://devfeed.tech/tags/platform.md>), [platforms](<https://devfeed.tech/tags/platforms.md>), [warehouse](<https://devfeed.tech/tags/warehouse.md>)

### AI overview

The article argues that a data warehouse can serve as a company's customer data platform by keeping customer information and trusted definitions centralized, modeling flexible relational data in SQL, and syncing warehouse data to business tools. It says general-purpose CDPs can impose rigid data models, limit access and portability, and separate marketing workflows from data-team oversight. The proposed warehouse approach uses tools such as Hightouch for SQL-based syncs and audience building, with data teams modeling data and marketers creating segments. The article sees vertical CDPs as useful for specialized needs, and off-the-shelf CDPs as reasonable when SQL expertise or a modern data stack is lacking, or when near-real-time capabilities are essential. It cautions that some CDPs' real-time functions may still be constrained by warehouse technology.

### Source excerpt

Off-the-shelf customer data platforms have serious shortcomings. Consider data warehouses instead.

## Why You Need Automated Schema Migration | Blog | Fivetran

DevFeed: [Why You Need Automated Schema Migration | Blog | Fivetran](<https://devfeed.tech/articles/why-you-need-automated-schema-migration-blog-fivetran-140195.md>)

Original publisher: [Read original article](<https://wf.fivetran.com/blog/automated-schema-migration>)

Author: Charles Wang

Published: 2026-11-18T03:07:10Z

Content type: article

Language: en

Sources: [Fivetran Blog](<https://devfeed.tech/sources/fivetran-blog.md>)

Topics: [schema design](<https://devfeed.tech/topics/schema-design.md>), [elt](<https://devfeed.tech/topics/elt.md>), [etl](<https://devfeed.tech/topics/etl.md>)

Tags: [automated](<https://devfeed.tech/tags/automated.md>), [data-integration](<https://devfeed.tech/tags/data-integration.md>), [data-pipeline](<https://devfeed.tech/tags/data-pipeline.md>), [downtime](<https://devfeed.tech/tags/downtime.md>), [fivetran](<https://devfeed.tech/tags/fivetran.md>), [migration](<https://devfeed.tech/tags/migration.md>), [schema](<https://devfeed.tech/tags/schema.md>)

### AI overview

Upstream SaaS schema changes can break traditional ETL scripts, interrupting loads and leaving analysts with stale data. The article contrasts raw ELT, which stores data without adapting to its schema, with outsourced automated ELT that understands source models and maintains pipelines. Fivetran says it propagates changes incrementally: it adds new columns and backfills when applicable; soft-deletes removed columns and sets future records to NULL while retaining history; handles datatype changes by retaining the old column and creating one able to accommodate both types; starts syncing new tables; and leaves deleted source tables in the warehouse. These practices aim to preserve data and avoid downtime, though datatype handling may require users to create views.

### Source excerpt

Schema changes can completely disrupt a data pipeline. Automated data integration offers a solution.

## How Fivetran Built its Klaviyo Connector | Blog | Fivetran

DevFeed: [How Fivetran Built its Klaviyo Connector | Blog | Fivetran](<https://devfeed.tech/articles/how-fivetran-built-its-klaviyo-connector-blog-fivetran-140217.md>)

Original publisher: [Read original article](<https://wf.fivetran.com/blog/fivetran-built-klaviyo-connector>)

Author: Charles Wang

Published: 2026-11-18T02:45:50Z

Content type: article

Language: en

Sources: [Fivetran Blog](<https://devfeed.tech/sources/fivetran-blog.md>)

Topics: [schema design](<https://devfeed.tech/topics/schema-design.md>), [implementation](<https://devfeed.tech/topics/implementation.md>), [Documentation](<https://devfeed.tech/topics/documentation.md>), [software development triangle](<https://devfeed.tech/topics/software-development-triangle.md>)

Tags: [api](<https://devfeed.tech/tags/api.md>), [api-documentation](<https://devfeed.tech/tags/api-documentation.md>), [api-key](<https://devfeed.tech/tags/api-key.md>), [app](<https://devfeed.tech/tags/app.md>), [automation](<https://devfeed.tech/tags/automation.md>), [beta](<https://devfeed.tech/tags/beta.md>), [blog](<https://devfeed.tech/tags/blog.md>), [bug-fixes](<https://devfeed.tech/tags/bug-fixes.md>), [build](<https://devfeed.tech/tags/build.md>), [challenges](<https://devfeed.tech/tags/challenges.md>), [customer](<https://devfeed.tech/tags/customer.md>), [customer-relationship-management](<https://devfeed.tech/tags/customer-relationship-management.md>), [data](<https://devfeed.tech/tags/data.md>), [data-engineering](<https://devfeed.tech/tags/data-engineering.md>), [data-engineering-workflow](<https://devfeed.tech/tags/data-engineering-workflow.md>), [data-integrity](<https://devfeed.tech/tags/data-integrity.md>), [designing](<https://devfeed.tech/tags/designing.md>), [fivetran](<https://devfeed.tech/tags/fivetran.md>), [schema](<https://devfeed.tech/tags/schema.md>), [schema-design](<https://devfeed.tech/tags/schema-design.md>)

### AI overview

Building Fivetran's Klaviyo connector took one engineer at least six weeks, with periodic help from an engineering manager, reviewer, and product lead. Work began with Campaigns, Lists, and Templates: the team tested endpoint ingestion, designed a normalized ERD, and integrated the code into Fivetran's framework. Metrics and Events were added with little trouble, but the high-level data model referenced a Flow table missing from public API documentation. Klaviyo provided private instructions for an undocumented Flow endpoint, and the teams secured a key to distinguish Flow-related from Campaign-related metrics and events. Flow Messages and Flow Recipients remained inaccessible. The connector entered public beta in early March 2018 and became stable in April; later maintenance included documentation and schema revisions, data integrity and bug fixes, and infrastructure updates. The article's main lesson is that connector design depends on reconciling documentation, supplied data models, and accessible API data, which may conflict.

### Source excerpt

The process of building a connector is inextricably linked with schema design.

## Govern and discover records with common metadata in AWS Agent Registry

DevFeed: [Govern and discover records with common metadata in AWS Agent Registry](<https://devfeed.tech/articles/govern-and-discover-records-with-common-metadata-in-aws-agent-registry-138534.md>)

Original publisher: [Read original article](<https://aws.amazon.com/blogs/machine-learning/govern-and-discover-records-with-common-metadata-in-aws-agent-registry/>)

Author: Sana Iqbal

Published: 2026-11-17T20:31:04Z

Content type: article

Language: en

Sources: [Artificial Intelligence](<https://devfeed.tech/sources/artificial-intelligence.md>)

Topics: [schema design](<https://devfeed.tech/topics/schema-design.md>), [AWS IAM](<https://devfeed.tech/topics/aws-iam.md>), [CI/CD](<https://devfeed.tech/topics/cicd.md>), [Multi Agent Systems](<https://devfeed.tech/topics/multi-agent-systems.md>)

Tags: [administrator](<https://devfeed.tech/tags/administrator.md>), [advanced-300](<https://devfeed.tech/tags/advanced-300.md>), [agent](<https://devfeed.tech/tags/agent.md>), [amazon-bedrock-agentcore](<https://devfeed.tech/tags/amazon-bedrock-agentcore.md>), [aws](<https://devfeed.tech/tags/aws.md>), [custom](<https://devfeed.tech/tags/custom.md>), [define](<https://devfeed.tech/tags/define.md>), [definition](<https://devfeed.tech/tags/definition.md>), [discovery](<https://devfeed.tech/tags/discovery.md>), [enrichment](<https://devfeed.tech/tags/enrichment.md>), [fields](<https://devfeed.tech/tags/fields.md>), [mcp](<https://devfeed.tech/tags/mcp.md>), [mcp-server](<https://devfeed.tech/tags/mcp-server.md>), [metadata](<https://devfeed.tech/tags/metadata.md>), [one](<https://devfeed.tech/tags/one.md>), [post](<https://devfeed.tech/tags/post.md>), [records](<https://devfeed.tech/tags/records.md>), [registry](<https://devfeed.tech/tags/registry.md>), [resources](<https://devfeed.tech/tags/resources.md>), [schema](<https://devfeed.tech/tags/schema.md>), [schemas](<https://devfeed.tech/tags/schemas.md>), [technical-how-to](<https://devfeed.tech/tags/technical-how-to.md>), [with](<https://devfeed.tech/tags/with.md>)

### AI overview

AWS Agent Registry custom metadata schemas give records shared, administrator-defined fields and allowed values, with validation on creation and updates. Records created without metadata can be saved as NON_COMPLIANT drafts but cannot be submitted for approval until required values are supplied; invalid or incomplete metadata is rejected. COMPLIANT indicates schema compliance, not approval. In the walkthrough, automation enriches an MCP record with scan and inventory data, then a custom Lambda approval function checks compliance, scan status, CMDB ID, and data classification. Approved records can be found through metadata filters or the registry's MCP endpoint; matching unapproved records stay out of discovery results. Schema changes are additive, and existing records are not rewritten: they may become NON_COMPLIANT while retaining approval until updated. The excerpt recommends choosing shared fields and values carefully and keeping secrets and sensitive findings out of broadly readable metadata.

### Source excerpt

Custom metadata schemas in AWS Agent Registry let an administrator define typed, validated fields that every agent, MCP server, and skill must carry. This post follows an MCP record from schema definition through registration, enrichment, approval, and discovery, so teams govern and find resources with one shared set of facts.

## Naming is hard, semantics are hard(er): Inside Sentry Conventions

DevFeed: [Naming is hard, semantics are hard(er): Inside Sentry Conventions](<https://devfeed.tech/articles/naming-is-hard-semantics-are-hard-er-inside-sentry-conventions-136409.md>)

Original publisher: [Read original article](<https://blog.sentry.io/sentry-conventions/>)

Author: Lukas Stracke

Published: 2026-11-16T11:00:00Z

Content type: article

Language: en

Sources: [Sentry](<https://devfeed.tech/sources/sentry-blog.md>)

Topics: [schema design](<https://devfeed.tech/topics/schema-design.md>), [observability pipelines](<https://devfeed.tech/topics/observability-pipelines.md>), [programming-tips](<https://devfeed.tech/topics/programming-tips.md>), [Test-driven development](<https://devfeed.tech/topics/tdd.md>)

Tags: [ai](<https://devfeed.tech/tags/ai.md>), [alert](<https://devfeed.tech/tags/alert.md>), [align](<https://devfeed.tech/tags/align.md>), [alignment](<https://devfeed.tech/tags/alignment.md>), [has](<https://devfeed.tech/tags/has.md>), [inside](<https://devfeed.tech/tags/inside.md>), [meaning](<https://devfeed.tech/tags/meaning.md>), [pipeline](<https://devfeed.tech/tags/pipeline.md>), [product](<https://devfeed.tech/tags/product.md>), [sdks](<https://devfeed.tech/tags/sdks.md>), [semantics](<https://devfeed.tech/tags/semantics.md>), [sentry](<https://devfeed.tech/tags/sentry.md>)

### AI overview

Sentry Conventions provide a shared specification, based on and extending OpenTelemetry conventions, to align attribute names and meanings across SDKs, ingestion, querying, and product features. They define attribute types, scrubbing and deprecation rules, well-known values, span operations and naming, and metrics. JavaScript SDKs use the packages for attribute names and span operations; Relay applies scrubbing and infers missing span descriptions or names; Snuba and the backend coalesce deprecated and current attributes so queries work with either name. The product uses conventions for attribute descriptions, types, and deprecation-safe features. Sentry says it grew coverage from about 300 attributes to more than 900, while noting it is not complete. Its lessons include agreeing on specs before shipping, testing conventions, and treating migrations as worthwhile but painful.

### Source excerpt

How Sentry Conventions keep attribute names and their meaning aligned across our SDKs, our ingestion pipeline, and the Sentry product.

## The Information Problem

DevFeed: [The Information Problem](<https://devfeed.tech/articles/the-information-problem-136358.md>)

Original publisher: [Read original article](<https://philipptheserver.com/posts/the-information-problem/>)

Author: Philipp Lehmann (philipp.lehmann@gruppe.ai)

Published: 2026-11-16T07:00:00Z

Content type: article

Language: en

Sources: [Philipp Lehmann](<https://devfeed.tech/sources/philipp-lehmann.md>)

Topics: [Data Management](<https://devfeed.tech/topics/data-management.md>), [knowledge-management](<https://devfeed.tech/topics/knowledge-management.md>), [data-processing](<https://devfeed.tech/topics/data-processing.md>), [schema design](<https://devfeed.tech/topics/schema-design.md>), [consistency](<https://devfeed.tech/topics/consistency.md>), [Documentation](<https://devfeed.tech/topics/documentation.md>), [Test-driven development](<https://devfeed.tech/topics/tdd.md>), [CI/CD](<https://devfeed.tech/topics/cicd.md>), [Electrical engineering and computer science (EECS)](<https://devfeed.tech/topics/electrical-engineering-and-computer-science-eecs.md>)

Tags: [22](<https://devfeed.tech/tags/22.md>), [about](<https://devfeed.tech/tags/about.md>), [acceptance](<https://devfeed.tech/tags/acceptance.md>), [act](<https://devfeed.tech/tags/act.md>), [actions](<https://devfeed.tech/tags/actions.md>), [adversarial](<https://devfeed.tech/tags/adversarial.md>), [after](<https://devfeed.tech/tags/after.md>), [agent](<https://devfeed.tech/tags/agent.md>), [agents](<https://devfeed.tech/tags/agents.md>), [ai](<https://devfeed.tech/tags/ai.md>), [all](<https://devfeed.tech/tags/all.md>), [api](<https://devfeed.tech/tags/api.md>), [application](<https://devfeed.tech/tags/application.md>), [architecture](<https://devfeed.tech/tags/architecture.md>), [argument](<https://devfeed.tech/tags/argument.md>), [cpp](<https://devfeed.tech/tags/cpp.md>), [documentation](<https://devfeed.tech/tags/documentation.md>), [information](<https://devfeed.tech/tags/information.md>), [methodology](<https://devfeed.tech/tags/methodology.md>), [moving](<https://devfeed.tech/tags/moving.md>), [needs](<https://devfeed.tech/tags/needs.md>), [revisions](<https://devfeed.tech/tags/revisions.md>), [testing](<https://devfeed.tech/tags/testing.md>), [traces](<https://devfeed.tech/tags/traces.md>), [world](<https://devfeed.tech/tags/world.md>)

### AI overview

Nisaba treats information as revisable claims about a changing world, with explicit limits on what records can establish. Its core is a responsibility loop: observe sources, create attributed and versioned assertions with declared dependencies, answer declared questions under eligibility conditions, deliver to accountable recipients, and observe outcomes. Revisions track world validity, record history, observation time, and current admissibility; this preserves what the system believed before a correction and distinguishes world changes from new knowledge or overdue review. Deterministic source transactions, parsers, rules, and human judgments form the baseline; AI is optional. Sixteen adversarial traces test failures such as treating missing allergy data as "no allergies," confusing an ACK with accepted responsibility, or a timer with proof of removal. The source describes a conditional specification with a working C++23 implementation, not a deployment. It explicitly excludes built-in AI, UI, and authentication, and states that identical observations cannot certify which of two unobserved worlds is real.

### Source excerpt

Nisaba treats information as stale claims about a moving world: bitemporal revisions, adversarial traces, and a closed loop that needs no AI.

## ScrapeGraphAI-100k: Dataset for Schema-Constrained LLM Generation

DevFeed: [ScrapeGraphAI-100k: Dataset for Schema-Constrained LLM Generation](<https://devfeed.tech/articles/scrapegraphai-100k-dataset-for-schema-constrained-llm-generation-134960.md>)

Original publisher: [Read original article](<https://arxiv.org/abs/2602.15189>)

Author: William Brach, Francesco Zuppichini, Marco Vinciguerra, Lorenzo Padoan

Published: 2026-11-16T05:00:00Z

Content type: article

Language: en

Sources: [arXiv: Artificial Intelligence](<https://devfeed.tech/sources/arxiv-artificial-intelligence.md>)

Topics: [Large Language Model](<https://devfeed.tech/topics/llm.md>), [LLM Techniques](<https://devfeed.tech/topics/llm-techniques.md>), [Fine-tuning](<https://devfeed.tech/topics/fine-tuning.md>), [schema design](<https://devfeed.tech/topics/schema-design.md>), [managing large-scale text data in AI](<https://devfeed.tech/topics/managing-large-scale-text-data-in-ai.md>), [open-llm-leaderboard](<https://devfeed.tech/topics/open-llm-leaderboard.md>)

Tags: [2025](<https://devfeed.tech/tags/2025.md>), [benchmarking](<https://devfeed.tech/tags/benchmarking.md>), [case-study](<https://devfeed.tech/tags/case-study.md>), [complexity](<https://devfeed.tech/tags/complexity.md>), [compliance](<https://devfeed.tech/tags/compliance.md>), [cs-ai](<https://devfeed.tech/tags/cs-ai.md>), [cs-cl](<https://devfeed.tech/tags/cs-cl.md>), [cs-ir](<https://devfeed.tech/tags/cs-ir.md>), [dataset](<https://devfeed.tech/tags/dataset.md>), [distillation](<https://devfeed.tech/tags/distillation.md>), [distribution](<https://devfeed.tech/tags/distribution.md>), [diversity](<https://devfeed.tech/tags/diversity.md>), [english](<https://devfeed.tech/tags/english.md>), [failure](<https://devfeed.tech/tags/failure.md>), [generation](<https://devfeed.tech/tags/generation.md>), [gpt](<https://devfeed.tech/tags/gpt.md>), [grounding](<https://devfeed.tech/tags/grounding.md>), [huggingface](<https://devfeed.tech/tags/huggingface.md>), [json](<https://devfeed.tech/tags/json.md>), [json-schema](<https://devfeed.tech/tags/json-schema.md>), [knowledge-base](<https://devfeed.tech/tags/knowledge-base.md>), [llm](<https://devfeed.tech/tags/llm.md>), [schema](<https://devfeed.tech/tags/schema.md>)

### AI overview

ScrapeGraphAI-100k contains 93,695 schema-constrained extraction events collected through opt-out ScrapeGraphAI telemetry in Q2-Q3 2025 and deduplicated and balanced by schema from 9 million raw events. Its 25,453 schemas cover 15 named languages, though English accounts for 89% of detected content. Each example pairs Markdown-converted page content with a prompt, schema, LLM response, and structural conformance labels. The authors report sharp failure thresholds as schema complexity increases. In a case study, a 1.7B fine-tuned student closely tracks its GPT-5-nano teacher's output distribution but trails a 30B-A3B reference (3.3B active parameters) on schema compliance; they describe this result as preliminary evidence for training and benchmarking on real practitioner workloads.

### Source excerpt

arXiv:2602.15189v3 Announce Type: replace-cross Abstract: Producing output that conforms to a specified JSON schema underlies tool use, structured extraction, and knowledge base construction in modern large language models. Despite this centrality, public datasets for the task remain small, synthetic, or text-only, and rarely pair real page content with the prompts and schemas used in practice. We introduce ScrapeGraphAI-100k, 93,695 schema-constrained extraction events collected via opt-out ScrapeGraphAI telemetry in Q2--Q3 2025, deduplicated and balanced by schema from 9M raw events. The corpus spans 25,453 unique schemas, across 15 named languages, with English covering 89% of detected content. Each instance pairs Markdown-converted page content with a prompt, schema, LLM response, and per-example jsonschema-rs structural conformance labels. We characterize structural diversity across the corpus and identify sharp failure thresholds as schema complexity grows. As a case study, a 1.7B student fine-tuned on this data closely tracks the output distribution of its GPT-5-nano teacher, though it still trails a 30B-A3B reference (3.3B active parameters) on schema compliance. We offer this distillation result as preliminary evidence that grounding schema-constrained generation in real practitioner workloads at scale enables training and benchmarking that prior synthetic or text-only corpora could not support. ScrapeGraphAI-100k is publicly available on HuggingFace.

## Preventing API Contract Drift in TypeScript Applications

DevFeed: [Preventing API Contract Drift in TypeScript Applications](<https://devfeed.tech/articles/preventing-api-contract-drift-in-typescript-applications-134432.md>)

Original publisher: [Read original article](<https://www.sitepoint.com/preventing-api-contract-drift-in-typescript-applications/>)

Author: Saifullah Adenwalla

Published: 2026-11-13T13:48:49Z

Content type: tutorial

Language: en

Sources: [SitePoint](<https://devfeed.tech/sources/sitepoint.md>)

Topics: [API](<https://devfeed.tech/topics/api.md>), [TypeScript](<https://devfeed.tech/topics/typescript.md>), [schema design](<https://devfeed.tech/topics/schema-design.md>), [Swagger](<https://devfeed.tech/topics/swagger.md>), [mock api](<https://devfeed.tech/topics/mock-api.md>), [CI/CD](<https://devfeed.tech/topics/cicd.md>), [Test-driven development](<https://devfeed.tech/topics/tdd.md>)

Tags: [accessibility](<https://devfeed.tech/tags/accessibility.md>), [agile-development](<https://devfeed.tech/tags/agile-development.md>), [api](<https://devfeed.tech/tags/api.md>), [api-design](<https://devfeed.tech/tags/api-design.md>), [api-documentation](<https://devfeed.tech/tags/api-documentation.md>), [api-integration](<https://devfeed.tech/tags/api-integration.md>), [apis](<https://devfeed.tech/tags/apis.md>), [ci-cd](<https://devfeed.tech/tags/ci-cd.md>), [code-generation](<https://devfeed.tech/tags/code-generation.md>), [contract-testing](<https://devfeed.tech/tags/contract-testing.md>), [contracts](<https://devfeed.tech/tags/contracts.md>), [data-structure](<https://devfeed.tech/tags/data-structure.md>), [data-types](<https://devfeed.tech/tags/data-types.md>), [javascript](<https://devfeed.tech/tags/javascript.md>), [typescript](<https://devfeed.tech/tags/typescript.md>), [ui-design](<https://devfeed.tech/tags/ui-design.md>)

### AI overview

TypeScript interfaces do not verify JSON received over HTTP, so a frontend can compile while silently receiving data that no longer matches its expectations. The excerpt recommends validating responses at the application boundary with Zod schemas, treating fetched data as unknown and using parse or safeParse; deriving types from schemas avoids maintaining duplicate definitions. It distinguishes this runtime check from OpenAPI, which documents a shared service contract, and Orval, which generates TypeScript clients and types from that specification but does not itself validate runtime responses. MSW can provide controlled success and failure responses for frontend development and tests without a live backend; Pact verifies consumer expectations against provider behavior. The excerpt also recommends automating contract validation and tests in CI/CD and assigning API ownership as teams grow. It presents these as complementary options to adopt according to architecture, rather than requiring every tool.

### Source excerpt

null Continue reading Preventing API Contract Drift in TypeScript Applications on SitePoint.

## Schema Drift vs. Semantic Drift in Data Pipelines

DevFeed: [Schema Drift vs. Semantic Drift in Data Pipelines](<https://devfeed.tech/articles/schema-drift-vs-semantic-drift-in-data-pipelines-133351.md>)

Original publisher: [Read original article](<https://www.freecodecamp.org/news/schema-drift-vs-semantic-drift-in-data-pipelines/>)

Author: Yemi Ojedapo

Published: 2026-11-13T11:23:18Z

Content type: article

Language: en

Sources: [Free Code Camp](<https://devfeed.tech/sources/freecodecamp-programming-tutorials-python-javascript-git-more.md>)

Topics: [Data pipelines](<https://devfeed.tech/topics/data-pipelines.md>), [data observability](<https://devfeed.tech/topics/data-observability.md>), [Pydantic](<https://devfeed.tech/topics/pydantic.md>), [schema design](<https://devfeed.tech/topics/schema-design.md>), [Data analysis](<https://devfeed.tech/topics/data-analysis.md>), [reproducibility](<https://devfeed.tech/topics/reproducibility.md>)

Tags: [data](<https://devfeed.tech/tags/data.md>), [data-engineering](<https://devfeed.tech/tags/data-engineering.md>), [data-pipelines](<https://devfeed.tech/tags/data-pipelines.md>), [drift](<https://devfeed.tech/tags/drift.md>), [pipelines](<https://devfeed.tech/tags/pipelines.md>), [pydantic](<https://devfeed.tech/tags/pydantic.md>), [python](<https://devfeed.tech/tags/python.md>), [schema](<https://devfeed.tech/tags/schema.md>), [schema-drift](<https://devfeed.tech/tags/schema-drift.md>), [semantic](<https://devfeed.tech/tags/semantic.md>), [semantic-drift](<https://devfeed.tech/tags/semantic-drift.md>)

### AI overview

In a synthetic pipeline lab with nine drift scenarios, schema checks caught all five structural changes, but missed semantic shifts that preserved field names and types. Such shifts let the pipeline run while changing results: timezone loss moved items to the wrong day, nulls replaced with empty strings reduced the unequipped count from 205 to 0, and tenfold durability scaling inflated the average. Across the four detectors, strict Pydantic validation caught the most cases (7/9), followed by schema diff (6), loose validation (4), and statistical profiling (2). Each had blind spots: strict rules need domain constraints, while statistical thresholds can raise false alarms and vary by field. Combining detectors improved coverage, but none establishes meaning without producer-consumer agreement on units, timezone conventions, valid values, and null semantics. The experiment used synthetic independent data and one fixed baseline, so its measured false-alarm rates may not generalize to real pipelines.

### Source excerpt

When a column is removed from a source database or dataset, the next pipeline run usually fails, making the problem easy to detect. But when a field keeps the same name and data type but its meaning c

## ANCHOR: Schema-Agnostic Threat Knowledge Graph Construction via Hybrid Ontology Discovery

DevFeed: [ANCHOR: Schema-Agnostic Threat Knowledge Graph Construction via Hybrid Ontology Discovery](<https://devfeed.tech/articles/anchor-schema-agnostic-threat-knowledge-graph-construction-via-hybrid-ontology-discovery-133254.md>)

Original publisher: [Read original article](<https://arxiv.org/abs/2606.01208>)

Author: Seonwoo Kim, Jinwoo Kim, Daegyu Kang, Daeseong Kim, Insup Lee

Published: 2026-11-13T05:00:00Z

Content type: article

Language: en

Sources: [arXiv: Cryptography and Security](<https://devfeed.tech/sources/arxiv-cryptography-and-security.md>)

Topics: [Threat Hunting & Intel](<https://devfeed.tech/topics/threat-hunting-intel.md>), [база знаний](<https://devfeed.tech/topics/tag-c51cc4bf76e5.md>), [graph-database](<https://devfeed.tech/topics/graph-database.md>), [Structured-data](<https://devfeed.tech/topics/structured-data.md>), [schema design](<https://devfeed.tech/topics/schema-design.md>), [llm-reasoning](<https://devfeed.tech/topics/llm-reasoning.md>)

Tags: [adversary](<https://devfeed.tech/tags/adversary.md>), [analysis](<https://devfeed.tech/tags/analysis.md>), [anchor](<https://devfeed.tech/tags/anchor.md>), [apis](<https://devfeed.tech/tags/apis.md>), [arxiv](<https://devfeed.tech/tags/arxiv.md>), [attack](<https://devfeed.tech/tags/attack.md>), [based](<https://devfeed.tech/tags/based.md>), [bridges](<https://devfeed.tech/tags/bridges.md>), [challenges](<https://devfeed.tech/tags/challenges.md>), [combined](<https://devfeed.tech/tags/combined.md>), [compliance](<https://devfeed.tech/tags/compliance.md>), [construction](<https://devfeed.tech/tags/construction.md>), [cs-cr](<https://devfeed.tech/tags/cs-cr.md>), [cyber](<https://devfeed.tech/tags/cyber.md>), [cyber-threat-intelligence](<https://devfeed.tech/tags/cyber-threat-intelligence.md>), [discovery](<https://devfeed.tech/tags/discovery.md>), [graph](<https://devfeed.tech/tags/graph.md>), [hybrid](<https://devfeed.tech/tags/hybrid.md>), [knowledge-graph](<https://devfeed.tech/tags/knowledge-graph.md>), [ontology](<https://devfeed.tech/tags/ontology.md>), [schema](<https://devfeed.tech/tags/schema.md>)

### AI overview

ANCHOR constructs cyber threat intelligence knowledge graphs across changing ontology schemas. It combines hybrid ontology discovery, which searches and navigates large schemas, with SHACL validation to enforce schema-compliant type assignments. The approach is intended to avoid manual pipeline reconfiguration and the scaling limits of inserting large ontologies into prompts. Experiments on UCO, STIX, and MALOnt reportedly show better ontology typing and schema compliance than existing baselines. With a local LLM, ANCHOR closely matches enterprise LLM typing performance, supporting privacy-preserving analysis of sensitive incident data. The supplied abstract does not include experiment details or quantify these gains.

### Source excerpt

arXiv:2606.01208v2 Announce Type: replace Abstract: Cyber threat intelligence (CTI) reports now serve as essential resources for capturing adversary tactics, techniques, and procedures observed in modern attack campaigns. While traditional CTI platforms reduce this intelligence to isolated indicators through fixed schemas such as STIX, ontology-based representations preserve the semantic relationships needed for structured threat analysis. However, existing approaches for ontology-aligned CTI extraction face three challenges: (i) schema-specific pipelines that require manual reconfiguration whenever the schema changes, (ii) prompt-based schema inclusion that fails to scale on large ontologies such as UCO, and (iii) reliance on enterprise LLM APIs that conflicts with privacy constraints when integrating sensitive internal incident data. In this paper, we present ANCHOR, a schema-agnostic CTI knowledge graph construction system that bridges LLMs and formal ontology schemas. At the core of ANCHOR is hybrid ontology discovery, a search-and-navigate mechanism that dynamically explores large-scale ontology schemas, combined with SHACL-based validation to enforce schema-compliant type assignments. Experimental results on the UCO, STIX, and MALOnt schemas show that ANCHOR outperforms existing baselines in ontology typing and schema compliance. In addition, ANCHOR with a local LLM closely matches enterprise LLM typing performance, enabling privacy-preserving CTI analysis with high fidelity.

## \[Experiment, Analysis, and Benchmark\] How well do LLMs comprehend and design relational database schemata?

DevFeed: [\[Experiment, Analysis, and Benchmark\] How well do LLMs comprehend and design relational database schemata?](<https://devfeed.tech/articles/experiment-analysis-and-benchmark-how-well-do-llms-comprehend-and-design-relational-database-schemata-132704.md>)

Original publisher: [Read original article](<https://arxiv.org/abs/2611.17044>)

Author: Sriom Chakrabarti, Sean Bin Yang, Arijit Khan, Sebastian Link

Published: 2026-11-13T05:00:00Z

Content type: article

Language: en

Sources: [arXiv: Databases](<https://devfeed.tech/sources/arxiv-databases.md>)

Topics: [schema design](<https://devfeed.tech/topics/schema-design.md>), [Large Language Model](<https://devfeed.tech/topics/llm.md>), [rdbms](<https://devfeed.tech/topics/rdbms.md>), [Database](<https://devfeed.tech/topics/database.md>), [text2sql](<https://devfeed.tech/topics/text2sql.md>)

Tags: [analysis](<https://devfeed.tech/tags/analysis.md>), [arxiv](<https://devfeed.tech/tags/arxiv.md>), [benchmark](<https://devfeed.tech/tags/benchmark.md>), [constraint](<https://devfeed.tech/tags/constraint.md>), [constructor](<https://devfeed.tech/tags/constructor.md>), [cs-db](<https://devfeed.tech/tags/cs-db.md>), [data-type](<https://devfeed.tech/tags/data-type.md>), [data-types](<https://devfeed.tech/tags/data-types.md>), [database](<https://devfeed.tech/tags/database.md>), [design](<https://devfeed.tech/tags/design.md>), [domain](<https://devfeed.tech/tags/domain.md>), [experiment](<https://devfeed.tech/tags/experiment.md>), [gpt](<https://devfeed.tech/tags/gpt.md>), [gpt-5-4](<https://devfeed.tech/tags/gpt-5-4.md>), [influence](<https://devfeed.tech/tags/influence.md>), [integrity](<https://devfeed.tech/tags/integrity.md>), [keys](<https://devfeed.tech/tags/keys.md>), [large-language-models-llms](<https://devfeed.tech/tags/large-language-models-llms.md>), [llms](<https://devfeed.tech/tags/llms.md>), [natural-language](<https://devfeed.tech/tags/natural-language.md>), [recovery](<https://devfeed.tech/tags/recovery.md>)

### AI overview

SchemaBridge evaluates six open-weight and proprietary LLMs on designing relational schemas from requirements, describing existing schemas, and preserving structure through a description round trip. Across 902 schemata, human-written requirements under-specify structure: no model exceeds 0.27 referential-integrity F1. Asking for complete descriptions raises GPT-5.4-mini's referential F1 on SchemaBench from 0.228 to 0.909, while BLEU, ROUGE-L, and BERTScore decrease. Round-trip fidelity depends on both the schema constructor and describer. Structural cues help recover keys and relationships, but data types and nullability are poorly retained together through verbalization.

### Source excerpt

arXiv:2611.17044v1 Announce Type: new Abstract: Large Language Models (LLMs) are increasingly used for database tasks, yet most work, such as Text2SQL, assumes that the relational schema already exists. We ask whether LLMs can design a schema from natural language requirements (Text2Schema), verbalize an existing schema (Schema2Text), and preserve its structure through a Schema-to-Text-to-Schema round trip. We present SchemaBridge, a benchmark of 902 schemata from three collections, stratified by size and constraint complexity, that scores fidelity separately for tables, attributes, domain (data types and nullability), entity, and referential integrity. Evaluating six open-weight and proprietary LLMs, we find that: (i) human-written requirements under-specify schemata, with no model exceeding 0.27 referential integrity F1; (ii) LLM-generated descriptions carry far more structure when explicitly asked to be complete, raising GPT-5.4-mini's referential F1 on SchemaBench from 0.228 to 0.909, even as BLEU, ROUGE-L, and BERTScore decrease; (iii) controlled experiments show that both constructor and describer choices influence round-trip fidelity under fixed settings; and (iv) masked schema experiments show that structural cues support recovery of keys and relationships, while joint data-type and nullability information is poorly retained through verbalization. Code and data are available at https://github.com/iamsriom/SchemaBridge

## CoordX Types: A Trustless, Swappable Type System for Shared Records

DevFeed: [CoordX Types: A Trustless, Swappable Type System for Shared Records](<https://devfeed.tech/articles/coordx-types-a-trustless-swappable-type-system-for-shared-records-133318.md>)

Original publisher: [Read original article](<https://arxiv.org/abs/2611.16128>)

Author: David Hyland-Wood, Rob Ewin

Published: 2026-11-13T05:00:00Z

Content type: article

Language: en

Sources: [arXiv: Cryptography and Security](<https://devfeed.tech/sources/arxiv-cryptography-and-security.md>)

Topics: [Programming Language Type Systems](<https://devfeed.tech/topics/programming-language-type-systems.md>), [schema design](<https://devfeed.tech/topics/schema-design.md>), [trust](<https://devfeed.tech/topics/trust.md>), [data type](<https://devfeed.tech/topics/data-type.md>)

Tags: [cs-cr](<https://devfeed.tech/tags/cs-cr.md>), [interpreter](<https://devfeed.tech/tags/interpreter.md>), [protocol](<https://devfeed.tech/tags/protocol.md>), [records](<https://devfeed.tech/tags/records.md>), [regular](<https://devfeed.tech/tags/regular.md>), [schemas](<https://devfeed.tech/tags/schemas.md>), [security](<https://devfeed.tech/tags/security.md>), [structure](<https://devfeed.tech/tags/structure.md>), [trust](<https://devfeed.tech/tags/trust.md>), [type-system](<https://devfeed.tech/tags/type-system.md>)

### AI overview

CoordX Types adds meaning to protocol-verified shared-record entries by specifying which entries count, how to interpret their positions, and what parties may or must do. Each type is a signed object fixed by its digest; parties evaluate it independently, without relying on a server, registry, or another party's software. Types identify the interpreter they require, allowing interpreters with different capabilities and designs to coexist in one record. The schema language constrains payloads to regular languages and entry structures to regular tree languages; its rules and computed values are total primitive-recursive functions, so evaluation always halts. The abstract says the paper compares the system with KQML, FIPA-ACL, and CBCL and relates it to language-theoretic security.

### Source excerpt

arXiv:2611.16128v1 Announce Type: new Abstract: The CoordX Protocol carries signed and encrypted entries between parties. It proves who wrote each entry and who had permission to write it. It does not say what an entry means. That task belongs above the protocol layer. This paper describes the CoordX type system, the layer that gives entries a meaning. A type is a short document that says how to read one part of a shared record: which entries count, what each position means, what a party may do there, and what a party must do next. The type system has two key properties. It is trustless: a type is an ordinary signed object fixed by its digest, and every party evaluates it for itself over entries that the CoordX Protocol has already verified. No party has to trust a server, a registry or another party's software. It is swappable: a type names the interpreter it is written for, so many interpreters, of different capabilities and designs, can be used side by side in one record. We describe how to write type schemas, and we define the expressive power of the schema language. Payloads form a regular language. Entry structure forms a regular tree language. Every rule and every computed value is a total function in the primitive recursive class, so evaluation always halts. We compare this with KQML, FIPA-ACL and CBCL, and we relate it to language-theoretic security.

## Operational Ontology on Snowflake: From Business Meaning to Governed AI Action

DevFeed: [Operational Ontology on Snowflake: From Business Meaning to Governed AI Action](<https://devfeed.tech/articles/operational-ontology-on-snowflake-from-business-meaning-to-governed-ai-action-131048.md>)

Original publisher: [Read original article](<https://medium.com/snowflake/operational-ontology-on-snowflake-from-business-meaning-to-governed-ai-action-6f3ef270d3f2?source=rss----34b6daafc07---4>)

Author: Tianxia Jia

Published: 2026-11-12T21:36:38Z

Content type: article

Language: en

Sources: [Snowflake Builders](<https://devfeed.tech/sources/snowflake-builders.md>)

Topics: [AI Integration Strategies](<https://devfeed.tech/topics/ai-integration-strategies.md>), [knowledge-engineering](<https://devfeed.tech/topics/knowledge-engineering.md>), [business logic](<https://devfeed.tech/topics/business-logic.md>), [semantic-layer](<https://devfeed.tech/topics/semantic-layer.md>), [Artificial Intelligence](<https://devfeed.tech/topics/ai.md>), [Authorization](<https://devfeed.tech/topics/authorization.md>), [function calling](<https://devfeed.tech/topics/function-calling.md>), [schema design](<https://devfeed.tech/topics/schema-design.md>), [AI-Ready Data](<https://devfeed.tech/topics/ai-ready-data.md>)

Tags: [acting](<https://devfeed.tech/tags/acting.md>), [actions](<https://devfeed.tech/tags/actions.md>), [agent](<https://devfeed.tech/tags/agent.md>), [agents](<https://devfeed.tech/tags/agents.md>), [ai](<https://devfeed.tech/tags/ai.md>), [ai-agent](<https://devfeed.tech/tags/ai-agent.md>), [ai-agents](<https://devfeed.tech/tags/ai-agents.md>), [ai-reasoning](<https://devfeed.tech/tags/ai-reasoning.md>), [also](<https://devfeed.tech/tags/also.md>), [architecture](<https://devfeed.tech/tags/architecture.md>), [article](<https://devfeed.tech/tags/article.md>), [authorization](<https://devfeed.tech/tags/authorization.md>), [best](<https://devfeed.tech/tags/best.md>), [bottleneck](<https://devfeed.tech/tags/bottleneck.md>), [business](<https://devfeed.tech/tags/business.md>), [governed-ai](<https://devfeed.tech/tags/governed-ai.md>), [meaning](<https://devfeed.tech/tags/meaning.md>), [ontology](<https://devfeed.tech/tags/ontology.md>), [operational](<https://devfeed.tech/tags/operational.md>), [snowflake](<https://devfeed.tech/tags/snowflake.md>)

### AI overview

The proposed Snowflake Operational Ontology architecture links governed business definitions to live operational state, domain rules, decision services, AI reasoning, and controlled execution. Its lifecycle is Observe -> Understand -> Evaluate -> Decide -> Execute -> Verify: Cortex Agents investigate and explain options, while specialized services validate or simulate plans; an authorized human approves actions before procedures dispatch them to external systems. Versioned snapshots, isolated simulation results, idempotency, and observed outcomes support traceability and verification. The article stresses that a system's acknowledgement does not prove an action completed. Snowflake Business Ontology governs concepts and relationships but does not execute rules or actions. Standard tables are the default for history and events; hybrid tables can serve selected indexed transactional workloads, with regional availability and quotas, but do not support streams. Applications therefore need another supported event source or dispatcher for hybrid-table state changes. The examples are illustrative synthetic reference implementations, not production integrations.

### Source excerpt

A reference architecture for AI agents to reason over operational state, simulate decisions, execute governed actions, and verify real-world outcomes. From Enterprise Knowledge to Operational Decisions At 1:30 PM, packing station PB-04 goes offline in a distribution center. Orders begin accumulating, and a carrier scheduled to depart at 5:00 PM may leave before its shipments are ready. An AI agent connected to warehouse data can identify the failed station, trace affected orders, and explain the shipping risk. But the warehouse manager needs to decide what to do. Can qualified workers move to another station? Can orders be rerouted? Which recovery plan has the best chance of meeting the deadline without creating another bottleneck? Answering these questions requires current operational state, resource capabilities, business constraints, and a way to evaluate proposed changes. Acting on a decision also requires authorization and confirmation that the intended changes occurred. In the earlier Ontology on Snowflake series, I explored how ontology definitions, enterprise data, semantic models, and AI reasoning establish a shared understanding of business information. Snowflake now has a product of Business Ontology for governed business definiton (Public Preview soon). This article builds on that foundation by introducing a Snowflake Operational Ontology Reference Architecture. It connects governed business meaning to operational state, constraints, simulation, AI reasoning, and controlled actions. The goal is to establish a reusable pattern. A warehouse, supply chain network, and data center require different operational models, but they can share architectural contracts and a common decision lifecycle. 1. What Makes an Ontology Operational? An ontology defines the concepts, relationships, and semantics of a domain. In our warehouse example, the ontology defines Packing Station, Worker, Order, and Carrier Commitment, along with relationships such as workers operating s

## dltHub brings data and meaning into ClickHouse

DevFeed: [dltHub brings data and meaning into ClickHouse](<https://devfeed.tech/articles/dlthub-brings-data-and-meaning-into-clickhouse-131083.md>)

Original publisher: [Read original article](<https://dlthub.com/blog/dlthub-clickhouse-ontology-agents>)

Author: Adrian Brudaru

Published: 2026-11-12T00:00:00Z

Content type: article

Language: en

Sources: [DLT Hub](<https://devfeed.tech/sources/dlt-hub.md>)

Topics: [semantic-layer](<https://devfeed.tech/topics/semantic-layer.md>), [etl](<https://devfeed.tech/topics/etl.md>), [AI-Ready Data](<https://devfeed.tech/topics/ai-ready-data.md>), [schema design](<https://devfeed.tech/topics/schema-design.md>)

Tags: [agent](<https://devfeed.tech/tags/agent.md>), [ai-harness](<https://devfeed.tech/tags/ai-harness.md>), [business](<https://devfeed.tech/tags/business.md>), [ci](<https://devfeed.tech/tags/ci.md>), [claude-code](<https://devfeed.tech/tags/claude-code.md>), [clickhouse](<https://devfeed.tech/tags/clickhouse.md>), [cloud](<https://devfeed.tech/tags/cloud.md>), [coding](<https://devfeed.tech/tags/coding.md>), [coding-agents](<https://devfeed.tech/tags/coding-agents.md>), [column](<https://devfeed.tech/tags/column.md>), [comment](<https://devfeed.tech/tags/comment.md>), [commit](<https://devfeed.tech/tags/commit.md>), [concepts](<https://devfeed.tech/tags/concepts.md>), [counts](<https://devfeed.tech/tags/counts.md>), [data](<https://devfeed.tech/tags/data.md>), [has](<https://devfeed.tech/tags/has.md>), [meaning](<https://devfeed.tech/tags/meaning.md>), [preview](<https://devfeed.tech/tags/preview.md>), [private](<https://devfeed.tech/tags/private.md>), [product](<https://devfeed.tech/tags/product.md>), [table](<https://devfeed.tech/tags/table.md>), [updates](<https://devfeed.tech/tags/updates.md>)

### AI overview

dltHub's Private Preview writes business definitions into ClickHouse table and column comments so ClickHouse Agent can consult them before generating SQL. The workflow uses an agent to build and deploy data pipelines, elicit and document business concepts with human owners, and create an ontology and canonical data model; pipeline runs can update the comments as data changes. The excerpt's GitHub dataset example distinguishes commits, pull requests, issue labels, and shared issues/pull requests endpoints, giving the agent context beyond table names. The article argues that raw-data access can leave agents guessing and that definitions stored in a separate governance tool can drift from the warehouse. dltHub says keeping definitions alongside data lets agents use the same context; this is the company's approach, not comparative evaluation evidence. Private Preview access is described as open to dltHub and ClickHouse customers.

### Source excerpt

Private Preview: dltHub writes your business definitions into ClickHouse table and column comments, so ClickHouse Agent gives trusted answers.

## DermaVQA-DAS: Dermatology Assessment Schema (DAS) & Datasets for Closed-Ended Question Answering & Segmentation in Patient-Generated Dermatology Images

DevFeed: [DermaVQA-DAS: Dermatology Assessment Schema (DAS) & Datasets for Closed-Ended Question Answering & Segmentation in Patient-Generated Dermatology Images](<https://devfeed.tech/articles/dermavqa-das-dermatology-assessment-schema-das-datasets-for-closed-ended-question-answering-segmentation-in-patient-generated-dermatology-images-128076.md>)

Original publisher: [Read original article](<https://arxiv.org/abs/2512.24340>)

Author: Wen-wai Yim, Yujuan Fu, Asma Ben Abacha, Meliha Yetisgen, Noel Codella, Roberto Andres Novoa, Josep Malvehy

Published: 2026-11-11T05:00:00Z

Content type: article

Language: en

Sources: [arXiv: Artificial Intelligence](<https://devfeed.tech/sources/arxiv-artificial-intelligence.md>)

Topics: [image recognition](<https://devfeed.tech/topics/image-recognition.md>), [Dataset development](<https://devfeed.tech/topics/dataset-development.md>), [ai evaluation](<https://devfeed.tech/topics/ai-evaluation.md>), [schema design](<https://devfeed.tech/topics/schema-design.md>), [AI Chat](<https://devfeed.tech/topics/ai-chat.md>), [Image](<https://devfeed.tech/topics/image.md>), [Enhancing AI model performance](<https://devfeed.tech/topics/enhancing-ai-model-performance.md>)

Tags: [assessment](<https://devfeed.tech/tags/assessment.md>), [benchmark](<https://devfeed.tech/tags/benchmark.md>), [benchmarks](<https://devfeed.tech/tags/benchmarks.md>), [cs-ai](<https://devfeed.tech/tags/cs-ai.md>), [cs-cl](<https://devfeed.tech/tags/cs-cl.md>), [cs-cv](<https://devfeed.tech/tags/cs-cv.md>), [datasets](<https://devfeed.tech/tags/datasets.md>), [design](<https://devfeed.tech/tags/design.md>), [english](<https://devfeed.tech/tags/english.md>), [evaluation](<https://devfeed.tech/tags/evaluation.md>), [features](<https://devfeed.tech/tags/features.md>), [framework](<https://devfeed.tech/tags/framework.md>), [future](<https://devfeed.tech/tags/future.md>), [gemini](<https://devfeed.tech/tags/gemini.md>), [gpt](<https://devfeed.tech/tags/gpt.md>), [gpt-4](<https://devfeed.tech/tags/gpt-4.md>), [image-analysis](<https://devfeed.tech/tags/image-analysis.md>), [jaccard](<https://devfeed.tech/tags/jaccard.md>), [language](<https://devfeed.tech/tags/language.md>), [leveraging](<https://devfeed.tech/tags/leveraging.md>), [max](<https://devfeed.tech/tags/max.md>), [question](<https://devfeed.tech/tags/question.md>), [schema](<https://devfeed.tech/tags/schema.md>)

### AI overview

DermaVQA-DAS extends DermaVQA with expert-annotated datasets for closed-ended question answering and lesion segmentation on patient-generated dermatology images. Its Dermatology Assessment Schema provides 36 high-level and 27 fine-grained questions, with multiple-choice options in English and Chinese. In the reported benchmarks, QA accuracy ranged from 0.729 to 0.798; o3 scored highest at 0.798, narrowly ahead of GPT-4.1 at 0.796. Segmentation results depended on prompt design and aggregation: the default prompt led under Mean-of-Max and Mean-of-Mean, while a prompt using both the patient query title and content led under majority-vote microscore, with BiomedParse achieving Jaccard 0.395 and Dice 0.566.

### Source excerpt

arXiv:2512.24340v2 Announce Type: replace-cross Abstract: Recent advances in dermatological image analysis have been driven by large-scale annotated datasets; however, most existing benchmarks focus on dermatoscopic images and lack patient-authored queries and clinical context, limiting their applicability to patient-centered care. To address this gap, we introduce DermaVQA-DAS, an extension of the DermaVQA dataset that supports two complementary tasks: closed-ended question answering (QA) and dermatological lesion segmentation. Central to this work is the Dermatology Assessment Schema (DAS), a novel expert-developed framework that systematically captures clinically meaningful dermatological features in a structured and standardized form. DAS comprises 36 high-level and 27 fine-grained assessment questions, with multiple-choice options in English and Chinese. Leveraging DAS, we provide expert-annotated datasets for both closed QA and segmentation and benchmark state-of-the-art multimodal models. For segmentation, we evaluate multiple prompting strategies and show that prompt design impacts performance: the default prompt achieves the best results under Mean-of-Max and Mean-of-Mean evaluation aggregation schemes, while an augmented prompt incorporating both patient query title and content yields the highest performance under majority-vote-based microscore evaluation, achieving a Jaccard index of 0.395 and a Dice score of 0.566 with BiomedParse. For closed-ended QA, overall performance is strong across models, with average accuracies ranging from 0.729 to 0.798; o3 achieves the best overall accuracy (0.798), closely followed by GPT-4.1 (0.796), while Gemini-1.5-Pro shows competitive performance within the Gemini family (0.783). We publicly release DermaVQA-DAS, the DAS schema, and evaluation protocols to support and accelerate future research in patient-centered dermatological vision-language modeling (https://osf.io/72rp3).

## PuppyGraph adds AI schema builder and MCP support to help ease enterprise agent adoption

DevFeed: [PuppyGraph adds AI schema builder and MCP support to help ease enterprise agent adoption](<https://devfeed.tech/articles/puppygraph-adds-ai-schema-builder-and-mcp-support-to-help-ease-enterprise-agent-adoption-126610.md>)

Original publisher: [Read original article](<https://www.infoworld.com/article/4246810/puppygraph-adds-ai-schema-builder-and-mcp-support-to-help-ease-enterprise-agent-adoption.html>)

Author: Anirban Ghoshal

Published: 2026-11-10T14:00:00Z

Content type: news

Language: en

Sources: [InfoWorld](<https://devfeed.tech/sources/infoworld.md>)

Topics: [graph-database](<https://devfeed.tech/topics/graph-database.md>), [schema design](<https://devfeed.tech/topics/schema-design.md>), [AI Integration Strategies](<https://devfeed.tech/topics/ai-integration-strategies.md>), [AI Infrastructure](<https://devfeed.tech/topics/ai-infrastructure.md>), [SQL](<https://devfeed.tech/topics/sql.md>), [Apache Iceberg](<https://devfeed.tech/topics/apache-iceberg.md>)

Tags: [agent](<https://devfeed.tech/tags/agent.md>), [agent-adoption](<https://devfeed.tech/tags/agent-adoption.md>), [ai](<https://devfeed.tech/tags/ai.md>), [ai-agents](<https://devfeed.tech/tags/ai-agents.md>), [ai-assisted](<https://devfeed.tech/tags/ai-assisted.md>), [artificial-intelligence](<https://devfeed.tech/tags/artificial-intelligence.md>), [artificial-intelligence-data-management](<https://devfeed.tech/tags/artificial-intelligence-data-management.md>), [automatically](<https://devfeed.tech/tags/automatically.md>), [builder](<https://devfeed.tech/tags/builder.md>), [data-management](<https://devfeed.tech/tags/data-management.md>), [distributed](<https://devfeed.tech/tags/distributed.md>), [engine](<https://devfeed.tech/tags/engine.md>), [enterprise](<https://devfeed.tech/tags/enterprise.md>), [enterprise-data](<https://devfeed.tech/tags/enterprise-data.md>), [graph](<https://devfeed.tech/tags/graph.md>), [graph-database](<https://devfeed.tech/tags/graph-database.md>), [graph-query-engine](<https://devfeed.tech/tags/graph-query-engine.md>), [integrations](<https://devfeed.tech/tags/integrations.md>), [language-en](<https://devfeed.tech/tags/language-en.md>), [large-datasets](<https://devfeed.tech/tags/large-datasets.md>), [latency](<https://devfeed.tech/tags/latency.md>), [mcp](<https://devfeed.tech/tags/mcp.md>), [puppygraph](<https://devfeed.tech/tags/puppygraph.md>), [schema](<https://devfeed.tech/tags/schema.md>), [storytype-news](<https://devfeed.tech/tags/storytype-news.md>)

### AI overview

PuppyGraph 1.0 adds an AI-assisted schema builder and MCP integrations to expose enterprise data through a distributed graph query engine. The builder maps existing tables into graph entities, relationships, and properties for developers to review; agents can use that schema instead of discovering tables and composing joins dynamically. The engine validates agent-generated queries against defined relationships and returns correction feedback, while splitting complex graph queries across compute nodes. PuppyGraph queries relational databases, warehouses, and lakehouses without copying data into a separate graph database, and also supports SQL. Trade-offs remain: developers must design and govern the graph model, results depend on source schema and data quality, and graph workloads can raise compute costs on underlying platforms. Analysts describe it as suited to analytical queries rather than low-latency graph writes or frequent transactional updates, and advise considering the vendor's maturity and support capacity.

### Source excerpt

PuppyGraph on Tuesday said it was adding an AI-assisted graph schema builder and MCP integrations to PuppyGraph 1.0, the new version of its distributed graph query engine for enterprise data. The update is designed to help developers reduce the complexity, latency, and costs associated with letting AI agents query interconnected data across thousands of database tables and multiple platforms. The AI-assisted schema builder automatically maps existing tables into graph entities, relationships, and properties, allowing developers to review and approve the resulting schema rather than manually defining how disparate datasets connect, the Santa Clara-headquartered startup said in a statement. These schemas can be used by agents deployed to query enterprise data, giving them a predefined map of how information across different tables and systems is connected, rather than requiring them to identify relevant tables and construct complex SQL joins dynamically, in turn simplifying query generation and reducing errors and retries, it added. To improve query accuracy, PuppyGraph's query engine also validates agent-generated queries against the graph schema, rejecting undefined relationships and returning feedback that agents can use to correct errors. Further, the execution engine splits complex graph queries into smaller operations that run simultaneously across multiple compute nodes, rather than sequentially on a single machine, helping accelerate queries that traverse multiple relationships across large datasets, the company said. These additions build on PuppyGraph's existing graph query engine, released in 2024, that lets enterprises query relational databases, data warehouses and lakehouses as a unified graph without moving or duplicating data into a separate graph database. The engine maps existing tables into a native Labeled Property Graph (LPG) model, representing data entities as nodes, their relationships as edges, and their attributes as properties, before execut

## Agents Propose, Code Verifies, Humans Decide: Verified Agentic Ingestion of Heterogeneous Scientific Tables into Relational Databases

DevFeed: [Agents Propose, Code Verifies, Humans Decide: Verified Agentic Ingestion of Heterogeneous Scientific Tables into Relational Databases](<https://devfeed.tech/articles/agents-propose-code-verifies-humans-decide-verified-agentic-ingestion-of-heterogeneous-scientific-tables-into-relational-databases-125668.md>)

Original publisher: [Read original article](<https://arxiv.org/abs/2611.11045>)

Author: Bharatha Rankothge, Suzanne Hodgkins, Virginia Rich, Michael Kirby

Published: 2026-11-10T05:00:00Z

Content type: article

Language: en

Sources: [arXiv: Artificial Intelligence](<https://devfeed.tech/sources/arxiv-artificial-intelligence.md>), [arXiv: Databases](<https://devfeed.tech/sources/arxiv-databases.md>)

Topics: [rdbms](<https://devfeed.tech/topics/rdbms.md>), [schema design](<https://devfeed.tech/topics/schema-design.md>), [SQL](<https://devfeed.tech/topics/sql.md>)

Tags: [agent](<https://devfeed.tech/tags/agent.md>), [agentic](<https://devfeed.tech/tags/agentic.md>), [agents](<https://devfeed.tech/tags/agents.md>), [ai](<https://devfeed.tech/tags/ai.md>), [ai-assisted](<https://devfeed.tech/tags/ai-assisted.md>), [audit](<https://devfeed.tech/tags/audit.md>), [audit-log](<https://devfeed.tech/tags/audit-log.md>), [audit-trail](<https://devfeed.tech/tags/audit-trail.md>), [automate](<https://devfeed.tech/tags/automate.md>), [biomedical](<https://devfeed.tech/tags/biomedical.md>), [code](<https://devfeed.tech/tags/code.md>), [coding](<https://devfeed.tech/tags/coding.md>), [coding-agent](<https://devfeed.tech/tags/coding-agent.md>), [cs-ai](<https://devfeed.tech/tags/cs-ai.md>), [cs-db](<https://devfeed.tech/tags/cs-db.md>), [data](<https://devfeed.tech/tags/data.md>), [database](<https://devfeed.tech/tags/database.md>), [databases](<https://devfeed.tech/tags/databases.md>), [dataset](<https://devfeed.tech/tags/dataset.md>), [datasets](<https://devfeed.tech/tags/datasets.md>), [q-bio-qm](<https://devfeed.tech/tags/q-bio-qm.md>), [relational-databases](<https://devfeed.tech/tags/relational-databases.md>), [tables](<https://devfeed.tech/tags/tables.md>)

### AI overview

The pipeline assigns LLM agents to propose typed schemas from compact, citable file evidence, while deterministic checks and human review govern ingestion. A verifier with 39 check types checks schema structure and meaning; code generates PostgreSQL DDL, reshapes data, quarantines unplaceable rows, records provenance, and reconciles staged rows against the database. Across four public biomedical datasets, including one held out from development, all 9 of 20 failed first proposals were caught: automated loops repaired eight and a reviewer corrected the ninth. All 45.1 million values loaded with no reconciliation gap. Structure discovery used 4-7 LLM calls, data preparation at most one more, and cost under $0.50 per dataset. In a separate test, all nine planted errors were quarantined with reasons or logged. These results are limited to the reported datasets and tests.

### Source excerpt

arXiv:2611.11045v1 Announce Type: new Abstract: Public scientific datasets rarely arrive analysis-ready. They arrive as messy folders of wide matrices, long tables, spreadsheets, and per-cohort files whose keys and encodings differ, and every reanalysis must reconnect them first. A coding agent can automate this, but its mistakes can look plausible, and without an audit trail, a mistake that corrupts data can go uncaught. We present an AI-assisted ingestion pipeline built on one rule: LLM agents propose, deterministic code verifies, and humans decide. Narrow agents see compact, citable evidence about the files, never the data, and return typed proposals. A verifier with 39 check types tests each proposal against that evidence in two loops, one for the schema's structure and one for its meaning, and a human reviewer approves the schema and the load. Code compiles PostgreSQL DDL, reshapes the data, quarantines rows it cannot place, records provenance, and reconciles every staged row against the database. On four public biomedical datasets, one held out from development, 9 of 20 first proposals failed a check and every failure was caught: the loops repaired eight, and a one-line reviewer edit fixed the ninth. All 45.1 million values loaded with zero reconciliation gap. Discovering a dataset's structure took 4-7 LLM calls and preparing its data at most one more, costing under $0.50 per dataset. In a separate test, each of nine planted data errors was quarantined with a reason or recorded in an audit log.

## OGDA: Ontology-Grounded Data Agents for Reliable Analysis over Heterogeneous Data Lakes

DevFeed: [OGDA: Ontology-Grounded Data Agents for Reliable Analysis over Heterogeneous Data Lakes](<https://devfeed.tech/articles/ogda-ontology-grounded-data-agents-for-reliable-analysis-over-heterogeneous-data-lakes-126231.md>)

Original publisher: [Read original article](<https://arxiv.org/abs/2611.12114>)

Author: Boyi Zhang, Hong Ting Tsang, Yisen Gao, Qiao Xiao, LI Yufei, Haoyu Huang, Zhongwei Xie, Jiaxin Bai, Yangqiu Song

Published: 2026-11-10T05:00:00Z

Content type: article

Language: en

Sources: [arXiv: Artificial Intelligence](<https://devfeed.tech/sources/arxiv-artificial-intelligence.md>)

Topics: [Data analysis](<https://devfeed.tech/topics/data-analysis.md>), [data lake](<https://devfeed.tech/topics/data-lake.md>), [Large Language Model](<https://devfeed.tech/topics/llm.md>), [llm-reasoning](<https://devfeed.tech/topics/llm-reasoning.md>), [schema design](<https://devfeed.tech/topics/schema-design.md>), [Data pipelines](<https://devfeed.tech/topics/data-pipelines.md>), [Multi Agent Systems](<https://devfeed.tech/topics/multi-agent-systems.md>)

Tags: [abstract](<https://devfeed.tech/tags/abstract.md>), [agent](<https://devfeed.tech/tags/agent.md>), [agentic](<https://devfeed.tech/tags/agentic.md>), [agents](<https://devfeed.tech/tags/agents.md>), [analysis](<https://devfeed.tech/tags/analysis.md>), [context-window](<https://devfeed.tech/tags/context-window.md>), [cs-ai](<https://devfeed.tech/tags/cs-ai.md>), [cs-cl](<https://devfeed.tech/tags/cs-cl.md>), [data](<https://devfeed.tech/tags/data.md>), [data-agents](<https://devfeed.tech/tags/data-agents.md>), [data-analysis](<https://devfeed.tech/tags/data-analysis.md>), [data-lake](<https://devfeed.tech/tags/data-lake.md>), [data-lakes](<https://devfeed.tech/tags/data-lakes.md>), [data-processing](<https://devfeed.tech/tags/data-processing.md>), [errors](<https://devfeed.tech/tags/errors.md>), [execution](<https://devfeed.tech/tags/execution.md>), [exploration](<https://devfeed.tech/tags/exploration.md>), [explore](<https://devfeed.tech/tags/explore.md>), [extend](<https://devfeed.tech/tags/extend.md>), [files](<https://devfeed.tech/tags/files.md>), [graph](<https://devfeed.tech/tags/graph.md>), [ontology](<https://devfeed.tech/tags/ontology.md>)

### AI overview

OGDA uses a compact ontology to help LLM agents analyze heterogeneous data lakes while limiting costly exploration and incorrect file selection. A proposer agent infers schemas, concepts, and relations from raw sources; a verifier checks each proposal against the data. During analysis, a task graph constrains processing actions and can be extended only after the agent observes the data's semantic meaning. Across KramaBench and DiscoveryBench with three LLM backbones, OGDA outperformed the strongest baselines by up to 10.82 points. The evidence is limited to the abstract and does not specify the evaluation setup or broader limitations.

### Source excerpt

arXiv:2611.12114v1 Announce Type: new Abstract: Full-pipeline data analysis over real-world data lakes requires LLM agents to locate and integrate information across large collections of tables with different schemas. Existing data agents follow task-specific exploration, which exhausts the context window in massive lakes. As the context fills, the agent's reasoning degrades, leading it to locate and process incorrect data files. These errors propagate into the final answer. To overcome these limitations, we introduce Ontology-Grounded Data Agent (OGDA), which utilizes a compact ontology to reduce exploration overhead and constrain data processing. OGDA constructs the ontology through agentic hypothesis testing. At each step, a proposer agent induces schemas, concepts, and relations from raw sources, and a verifier checks each proposal against the underlying data. During task execution, the ontology serves as a representation of the data lake for the agent to explore. Every data-processing action is constrained by a task graph, which the agent can extend only after observing the semantic meaning of the data. Across KramaBench and DiscoveryBench with three LLM backbones, OGDA outperforms the strongest baselines by up to 10.82 points. These results suggest that explicitly modeling the data lake is a key step toward reliable end-to-end data agents.

[Next page](<https://devfeed.tech/topics/schema-design.md?cursor=WyIyMDI2LTExLTEwVDA1OjAwOjAwKzAwOjAwIiwgIjMwMjMxZDc4LTU4MGMtNGYwNy05NjE0LWFmODYzNGZkNmUzNyJd>)