RESEARCH TOPIC / AI-SYSTEMS
Models, retrieval, agents, and input-output pipelines.
GROUNDING MAP
Explore 16 research notes through a shared decision domain. Each article identifies its conclusion, sources, findings, and limitations.
Design evidence for AI-agent actions around a chain of approval, execution, and state change—not full-content retention. Capture disputed content selectively under protection, then test reconstructability and minimization as separate release gates.
Read article
Instead of reusing a human session, separate the principal from the agent and evaluate a delegation that binds resource, action, audience and lifetime at execution time.
Read article
After AI-enabled RPA was introduced, interviews suggested monthly research time fell about 90%. Later, only 10–20% of estimated freed time was explained as new work or extra output. This note shows how to measure the time actually freed and where it went.
Read article
After work has been redesigned, decide how remaining steps combine core systems, APIs, RPA, AI, and people—and what proves the operation can run without its builder.
Read article
Treat faster local tasks as only one signal; redesign bottlenecks, exceptions, expert handoffs, and the allocation of released capacity across the full workflow.
Read article
We mitigate the risk of malicious documents entering the top search results and guiding answers through write history, index monitoring, contradiction detection, post-generation verification, and isolation with re-indexing.
Read article
Do not trust multi-LLM discussions based on vote counts; instead, determine the added value by assessing the diversity of initial answers, conformity, problem drift, retention of correct answers, and the difference from simple voting.
Read article
Do not equate the productivity of generated code with safety; instead, treat vulnerabilities, user safety perception, static and dynamic testing, and independent review as gates for adopting high-impact code.
Read article
Instead of uniformly prohibiting the reuse of synthetic data, we design learning data operations that separate the replacement, accumulation, and selection of real data to preserve rare cases and diversity.
Read article
Monitoring only changes in input distribution does not reveal actual harm; design multi-layered monitoring and response procedures that connect data, predictions, decisions, and delayed outcomes.
Read article
Filtering suspicious text alone cannot protect AI that reads external data and executes tools; we organize multi-layered defense through attack evaluation, structured input, and official classification.
Read article
Being able to extract text via OCR is distinct from correctly linking layout, graphs, tables, and body text; we organize the unit of business verification based on research in document question answering.
Read article
Designing a system that sends all requests to a high-performance model, or one that fixes them to a low-cost model, is not necessarily optimal; drawing from cascade and router research, we consider routing under quality constraints.
Read article
Even with high accuracy in a single response, errors accumulate in tasks involving continuous planning, search, tool execution, and state updates; we consider the boundaries of reliable automation based on real-world environment benchmarks.
Read article
Providing evidence via search does not necessarily eliminate errors; this article outlines methods for verifying RAG in business operations by distinguishing between search omissions, inconsistencies with evidence, and oversights in long contexts.
Read article
Average effects of AI coding are not enough for investment decisions. Research from laboratories, enterprises, and mature open-source projects reveals the work, personnel, and measurement conditions that determine whether development speeds up.
Read article
