Topic hub
Retrieval
A New Runtime topic hub collecting signals, patterns, field notes, and public sources about retrieval.
Retrieval answer
A New Runtime topic hub collecting signals, patterns, field notes, and public sources about retrieval. Retrieval is tracked here as an evidence-linked topic, not as a static glossary entry. The page connects raw observations to pattern hypotheses, longer analysis, and public sources. Use it as the canonical landing page before drilling into individual records.
Field notes
What should readers understand next?
What Happened When machine-consumption.json Became New Runtime’s Leading Machine Route
A public methods note on turning an unusual crawler signal into a verified discovery graph, a privacy-safe measurement system, and three falsifiable experiments.
Raw signals
What changed recently?
Retrieval and long context do not create company memory
Finding a relevant fragment does not establish whether it is current, authorized, trustworthy, or applicable to the present task.
LinkedIn Builds Semantic Search for a Hiring Agent at Scale
Hiring Assistant uses retrieval and ranking infrastructure tuned for agent decisions rather than generic document search.
Reasoning can act as self-retrieval
Google's Thinking to Recall work studies how generated reasoning can recover knowledge that a direct answer fails to surface.
Google Makes RAG Search Again Before It Answers
Agentic RAG adds planning and iterative retrieval when the first result set is insufficient, replacing one-shot lookup with a loop.
GitHub / yichuan-w/LEANN: Routable Model Components
The archive captures GitHub / yichuan-w/LEANN as a dated public record from GitHub / yichuan-w/LEANN. It documents models becoming replaceable or specialized components inside a more durable runtime and is retained as supporting evidence for the routable model components trend.
CocoIndex Keeps Agent Context Fresh Without Full Reindexing
CocoIndex turns source changes into incremental dataflow updates for live agent context and code-aware retrieval.
Google Research / Building Better Ai Benchmarks How Many Raters: Verification Bandwidth
The archive captures Google Research / Building Better Ai Benchmarks How Many Raters as a dated public record from Google Research / Building Better Ai Benchmarks How Many Raters. It documents evaluation, review, and observability becoming the bottleneck after generation accelerates and is retained as pressure-testing evidence for the verification bandwidth trend.
The Only Skills that Matter in 2026
The archive captures The Only Skills that Matter in 2026 as a dated public record from X source / Saboo Shubham. It documents long-running work gaining explicit goals, state, stopping rules, and recovery and is retained as supporting evidence for the goal-scoped agent loops trend.
X source / Akshay Pachaar: Verification Bandwidth
The archive captures X source / Akshay Pachaar as a dated public record from X source / Akshay Pachaar. It documents evaluation, review, and observability becoming the bottleneck after generation accelerates and is retained as pressure-testing evidence for the verification bandwidth trend.
GitHub / tobi/qmd: Routable Model Components
The archive captures GitHub / tobi/qmd as a dated public record from GitHub / tobi/qmd. It documents models becoming replaceable or specialized components inside a more durable runtime and is retained as pressure-testing evidence for the routable model components trend.
Marktechpost / Microsoft Releases Vibevoice Asr Unified Speech To: Generative Media Infrastructure
The archive captures Marktechpost / Microsoft Releases Vibevoice Asr Unified Speech To as a dated public record from Marktechpost / Microsoft Releases Vibevoice Asr Unified Speech To. It documents image, video, audio, and multimodal generation becoming application infrastructure and is retained as branch-opening evidence for the generative media infrastructure trend.
Humanlayer / Writing Good Claude Md: Harnesses And Portable Skills
The archive captures Humanlayer / Writing Good Claude Md as a dated public record from Humanlayer / Writing Good Claude Md. It documents agent behavior moving from ad hoc prompts into reusable rules, skills, and harnesses and is retained as supporting evidence for the harnesses and portable skills trend.
Google Research / Titans Miras Helping Ai Have Long Term: Governed Context And Memory
The archive captures Google Research / Titans Miras Helping Ai Have Long Term as a dated public record from Google Research / Titans Miras Helping Ai Have Long Term. It documents context and memory becoming governed infrastructure with update and provenance loops and is retained as supporting evidence for the governed context and memory trend.
Medium / How We Built High Quality Q Assistant: Governed Context And Memory
The archive captures Medium / How We Built High Quality Q Assistant as a dated public record from Medium / How We Built High Quality Q Assistant. It documents context and memory becoming governed infrastructure with update and provenance loops and is retained as pressure-testing evidence for the governed context and memory trend.
Blog / Validating Llm As Judge Systems Under Rating: Harnesses And Portable Skills
The archive captures Blog / Validating Llm As Judge Systems Under Rating as a dated public record from Blog / Validating Llm As Judge Systems Under Rating. It documents agent behavior moving from ad hoc prompts into reusable rules, skills, and harnesses and is retained as pressure-testing evidence for the harnesses and portable skills trend.
Cursor / Debug Mode: Governed Context And Memory
The archive captures Cursor / Debug Mode as a dated public record from Cursor / Debug Mode. It documents context and memory becoming governed infrastructure with update and provenance loops and is retained as supporting evidence for the governed context and memory trend.
Philschmid / Context Engineering Part: Goal-Scoped Agent Loops
The archive captures Philschmid / Context Engineering Part as a dated public record from Philschmid / Context Engineering Part. It documents long-running work gaining explicit goals, state, stopping rules, and recovery and is retained as supporting evidence for the goal-scoped agent loops trend.
8 learnings from 1 year of agents - PostHog AI
The archive captures 8 learnings from 1 year of agents - PostHog AI as a dated public record from Posthog / Learnings From Year Of Agents Posthog Ai. It documents long-running work gaining explicit goals, state, stopping rules, and recovery and is retained as pressure-testing evidence for the goal-scoped agent loops trend.
OpenAI Developers / Agents Md: Governed Context And Memory
The archive captures OpenAI Developers / Agents Md as a dated public record from OpenAI Developers / Agents Md. It documents context and memory becoming governed infrastructure with update and provenance loops and is retained as supporting evidence for the governed context and memory trend.
Claude / Claude Best Practices: Governed Context And Memory
The archive captures Claude / Claude Best Practices as a dated public record from Claude / Claude Best Practices. It documents context and memory becoming governed infrastructure with update and provenance loops and is retained as supporting evidence for the governed context and memory trend.
Llamaindex / Announcing Llamasheets Turn Messy Spreadsheets Into Ai: Governed Context And Memory
The archive captures Llamaindex / Announcing Llamasheets Turn Messy Spreadsheets Into Ai as a dated public record from Llamaindex / Announcing Llamasheets Turn Messy Spreadsheets Into Ai. It documents context and memory becoming governed infrastructure with update and provenance loops and is retained as supporting evidence for the governed context and memory trend.
Neon: Governed Context And Memory
The archive captures Neon as a dated public record from Neon. It documents context and memory becoming governed infrastructure with update and provenance loops and is retained as supporting evidence for the governed context and memory trend.
Aiechoes / Building Biomedical Graphrag When: Governed Context And Memory
The archive captures Aiechoes / Building Biomedical Graphrag When as a dated public record from Aiechoes / Building Biomedical Graphrag When. It documents context and memory becoming governed infrastructure with update and provenance loops and is retained as pressure-testing evidence for the governed context and memory trend.
Hugging Face: Verification Bandwidth
The archive captures Hugging Face as a dated public record from Hugging Face. It documents evaluation, review, and observability becoming the bottleneck after generation accelerates and is retained as pressure-testing evidence for the verification bandwidth trend.