The talk details the architecture of inference engines, covering prefill/decode phases, the role of the scheduler, and advanced optimizations like KV caching and speculative decoding to maximize GPU throughput.
Read article
The Universal Verifier addresses the unreliability of LLM judges for agent testing. By using structured rubrics and ranking evidence, it significantly closes the gap between perceived and actual agent success rates.
Read article
The talk details the shift from manual trace review to automated, continuous improvement loops for AI agents. By introducing 'Signal,' the system detects patterns in evaluation failures and automatically suggests fixes, closing the software development loop.
Read article
Learn how to scale AI chatbots from 40 files to 80,000+ documents. This talk covers AI-assisted metadata tagging, sensitive data detection, and maintaining data quality (freshness, conflicts) to ensure reliable RAG context.
Read article
Deep dive into evaluating OCR and AI agents on complex documents. Learn how to perform root cause analysis when an agent fails, tracing the error back to upstream data issues like OCR inaccuracies or missing watermarks.
Read article
As AI agents level the implementation playing field, the differentiator becomes building the right thing. Learn to use Jobs to be Done and the Kano Model to guide product judgment and technical architecture.
Read article
As AI agents commoditize implementation, the most valuable skill for engineers is Product Engineering: the ability to define the 'right thing' to build. This requires connecting customer needs to technical constraints, focusing on the smallest useful slice of the system.
Read article
Matt Brockman walks through deliberate sandbox failures—from runaway processes to memory leaks—demonstrating how to manage resource quotas and maintain state in large-scale, isolated compute environments.
Read article
Evals are 'fuzzy unit tests' for non-deterministic AI systems. They provide ahead-of-time reliability, complementing runtime harnesses. Learn how to build an Eval suite, mitigate judge biases, and integrate it into a CI gate for production-grade safety.
Read article
Learn to operate a 'fleet of agents' instead of babysitting single sessions. We cover Goals, Loops, Hooks, and Git worktrees to build fully autonomous, verifiable development workflows.
Read article
Comparing agentic search vs. vector search for coding agents, this talk reveals that while both methods achieved equal accuracy, vector search cost four times more due to lack of connective context.
Read article
To manage AI spend, tag every resource and move beyond total cost. Focus on efficiency metrics like 'cost per thought,' 'reasoning ratio,' and 'cache hit rate' to truly understand AI ROI.
Read article
Agent memory is solved, but shared learning across agents is not. The solution requires an agent-native persistence layer (Meko) to promote private memories into governed, shared data packs.
Read article
OpenRouter usage shows token spend is up 80x year-over-year. The key to AI success is 'tokconomics': optimizing workflows using specialized models like Jev alongside LLMs to maximize value per token.
Read article
LangChain outlines the shift to 'owning your intelligence' by building domain-specific agents. The platform provides Managed Deep Agents, Jev decision models, and LangSmith Engine v2 for robust governance and production readiness.
Read article
DevOps requires using both IDEs and CLIs. The real challenge is 'context overload'—managing the friction across coding, testing, builds, and deployment pipelines.
Read article
Learn about meta-tooling: building AI agents that write, load, and use their own tools at runtime. Discover how to implement self-healing, self-modifying agents using the Strands Agents SDK.
Read article
AI coding agents are accelerating development but are causing massive codebase decay. Dan Adler argues that large-scale code visibility and infrastructure are the true bottlenecks, introducing Agentic Batch Changes for cross-repo updates.
Read article
Keyword search is dying. As shopping moves to the intent and delegation eras, product catalogs must be rebuilt for AI agents. Learn how hybrid search and structured data enrichment are key to success.
Read article
Learn how to build durable, multi-agent AI systems that handle human-in-the-loop processes. Discover why blocking calls fail and how Temporal's primitives ensure state persistence during long waits.
Read article