Official account of the DataFun community, dedicated to sharing big data and AI industry summit news and speaker talks, with regular downloadable resource packs.
The article analyzes Harness Engineering’s semantic foundation, showing how an ontology‑driven approach restructures agent constraints, context handling, and feedback loops to achieve safe, auditable, and business‑level controllable execution, illustrated with a Knora implementation case study.
The article explains that in long‑running autonomous agents, larger context windows, excessive tool sets, and unstructured memory cause slower, costlier, and error‑prone behavior, and it proposes six design principles—dense context, minimal toolkits, task‑driven skill growth, hierarchical memory, action‑validated experience, and efficiency‑focused evaluation—to achieve stable, self‑evolving agents.
The article analyzes the fundamental trade‑off between global competition in attention and efficiency when processing million‑token contexts, and presents three complementary techniques—AsymKV, Compression‑Aware Tuning (CAT), and Softmax Linear Attention (SLA)—that preserve or rebuild global competition while dramatically reducing memory and compute costs, achieving state‑of‑the‑art results on LongBench and various retrieval benchmarks.
The article analyzes Palantir's Foundry and AIP approach in a mortgage‑lending case, showing how unified business context, rule traceability, and ontology‑driven document and call processing turn AI from a standalone model into an end‑to‑end operational system.
The article critiques the uncontrolled “blind rail” AI coding loops that generate massive PRs, explains why control theory‑based feedback loops are essential, and details a concrete Effect‑TS migration case that demonstrates a repeatable, low‑risk engineering pattern for AI‑assisted code evolution.
The article analyzes the 2026‑07‑28 MCP specification update, detailing four production‑grade signals, QCC’s decade‑long shift from simple data retrieval to Agent‑Native services, a five‑layer capability matrix, and a trusted workflow for AI‑driven corporate due‑diligence tasks.
At a closed‑door OpenKG × DataFun session the authors argued that enterprises now lack a unified, computable, evolvable semantic layer—not model capability—and that ontology, re‑imagined as a semantic operating system, can bridge business, data and AI, though organizational and open‑source hurdles remain.
The article traces the evolution from traditional software factories to the “lights‑off” AI‑driven model, exposing a maintainability nightmare, explaining why current LLM‑based coding agents cannot learn good design, reviewing emerging benchmarks, and proposing a pragmatic four‑step process to re‑introduce planning and human oversight.
The article explains how Palantir’s Foundry and AIP combine data integration, ontology‑based business context, and rule management to turn large‑model AI into executable intelligence, illustrated by Freedom Mortgage’s 90‑day rollout of compliance, document, and call‑handling applications that link rules, documents and customer interactions into a unified, actionable system.
PlanRAG adapts decades‑old database query‑planning techniques to Retrieval‑Augmented Generation, turning complex, non‑linear questions into logical query trees that guide retrieval and generation, resulting in smarter search, reduced noise, lower cost, and up to 2.5× faster execution on exploratory reasoning tasks.
