Agent

When format constraints hurt LLMs: the same structured-output techniques often lower scores on reasoning tasks and raise them on discrete classification—from agent pipelines to benchmark evaluation.

Synthetic data for RAG, agents, and offline evaluation—when to augment, how to trust the distribution, and pipelines from distilabel and Persona Hub to Hub SQL and quality filters.

Stateful agents and context compilation: how Letta (from MemGPT) treats the context window as a compiled runtime view—memory tiers, agentic RAG, tool-call unification, multi-agent blocks, and observability—with evidence boundaries called out.

Query Agent on a vector database: auditable retrieval, Ask vs Search modes, schema introspection, multi-collection routing, and what is verified in docs versus speaker claims.

From RAG to search agents: BEIR co-author Nandan Thakur on BrowseComp-Plus, synthetic data pipelines, GRPO economics, and why retrieval benchmarks, training cost, and harness design pull in different directions.

Use domain modeling to move Java AI agents from ‘it runs’ to ‘it’s controlled’—orchestration, contracts, and type-safe pipelines with Koog.

Enterprise RAG on financial research corpora: engineering trade-offs across vector stores, agents, and eval—ingestion throughput, retrieval granularity, entitlements, and agent latency.

Enterprise RAG and agents when vector databases meet four decades of analytics software—engineering tensions in regulated industries, SAS RAM, Weaviate integration, and production boundaries.

Enterprise RAG and agents: from stitched-together pipelines to an end-to-end optimizable system—RAG 2.0, active retrieval, preference learning (KTO/APO), and LMUnit-style evaluation, with evidence boundaries called out.

Enterprise AI on exabyte-scale unstructured content: permissions, layered retrieval, and agent boundaries—engineering lessons from Box × Weaviate on ACL-aware RAG, embedding economics, and production agents.

Data agents across Snowflake, MySQL, Mongo, and Salesforce—DAB benchmarks, DocETL, tribal knowledge, and agent-first databases, with verifiable claims separated from speaker opinion.

AI-Powered Search: When RAG, agents, and classic IR get rewired—retrieval quality vs. agent loops, long context vs. searchable history, leaderboard embeddings vs. domain corpora, with Doug Turnbull and Trey Grainger on what ships.

Stanford’s STaRK benchmark and AvaTaR contrastive optimization for retrieval agents on semi-structured knowledge bases—metrics, multi-vector limits, when agents lose to dense retrievers, and what to ship in production.

Agent-agnostic Java quality guardrails: use AGENTS.md and static analysis to encode standards in the repository.

Agent oversight stack: from static evaluation to trajectory-level observability—evaluation, observability, and supervision for multi-agent systems, with Percival, Lynx, and Glider, and evidence boundaries called out.