---
title: "Latest reads"
description: "The engineering internet, summarised so you can actually read it."
---

# Latest reads
> The engineering internet, summarised so you can actually read it.

## Articles

### [When it comes to Governance, Retailers need a control plane for context](https://yomu.fyi/post/when-it-comes-to-governance-retailers-need-a-control-plane-for-context.md)
- Company: [Databricks](https://yomu.fyi/company/databricks.md)
- Author: BJ Sullivan, Sarah Duffy, Tayo Olabumuyi, Logan Boyd
- Published: Aug 18, 2026
- Type: Explainer

Retailers are moving from isolated generative-AI pilots to enterprise-wide adoption, where each store, headquarters, and digital workflow needs different data, permissions, models, and cost controls. The post argues that useful AI depends on governed business context, while fragmented tools can produce separate provider contracts, logs, permission models, cost centers, and answers to the same question. It proposes an open control plane that centralizes governance and model access without forcing employees into one application or vendor. The described Databricks design combines Unity Catalog for data and business context, Unity AI Gateway for routing and oversight, Foundation Model APIs for commercial, open-source, and custom models, and Genie for natural-language queries over governed data; the intended result is faster experimentation and deployment with visibility into access, spending, lineage, and auditability.


### [Evaluating AI Agents Live at the Grounded Reasoning Cup](https://yomu.fyi/post/evaluating-ai-agents-live-at-the-grounded-reasoning-cup.md)
- Company: [Databricks](https://yomu.fyi/company/databricks.md)
- Author: Databricks AI Research Team
- Published: Aug 18, 2026
- Type: Benchmark

The Grounded Reasoning Cup evaluated whether AI agents could generalize grounded reasoning improvements from OfficeQA to a newly released, enterprise-style document benchmark. Eleven academic teams had about two months to build agents with a partner lab’s model family, then applied them live to OfficeQA Pro V2, based on U.S. Treasury Accounts of Receipts and Expenditures, after a 36-hour release window. Stanford won with 63.3% accuracy, while the top systems combined document preprocessing, targeted or hybrid retrieval, specialized tools, parallelism, and answer verification; 18.8% of questions remained unsolved by every team. The results show that benchmark gains did not reliably transfer, and that parsing, retrieval, tool use, verification, and operational infrastructure can matter as much as model choice in end-to-end enterprise reasoning.


### [What's New with Monitoring in PostgreSQL 19](https://yomu.fyi/post/what-s-new-with-monitoring-in-postgresql-19.md)
- Company: [Clickhouse](https://yomu.fyi/company/clickhouse.md)
- Published: Aug 18, 2026
- Type: Explainer

PostgreSQL 19, still in beta when this was written, adds monitoring and observability changes spanning lock contention, logging, WAL, wait events, remote messages, and multixacts. The default for log\_lock\_waits changes to on, while log\_min\_messages gains per-process-type levels and autoanalyze receives its own duration setting. A new wal\_fpi\_bytes counter exposes full-page-image volume cluster-wide, per session, per query, and in VACUUM and ANALYZE logs; new wait events expose WAL write, flush, and replay stages plus COPY file, pipe, and program I/O. Remote server messages now use normal PostgreSQL logging with origin prefixes, and pg\_get\_multixact\_stats() surfaces multixact usage that previously required filesystem inspection and educated guessing. The post also lists upgrade work for parsers, metric collectors, wait-event dictionaries, configuration UIs, and alert thresholds, while noting that final release notes may differ.


### [Coding Agent Horror Stories: The Command You Already Approved](https://yomu.fyi/post/coding-agent-horror-stories-the-command-you-already-approved.md)
- Company: [Docker](https://yomu.fyi/company/docker.md)
- Author: Jennifer Kohl
- Published: Aug 18, 2026
- Type: Announcement

The OpenAI and Hugging Face security incident involved 17,600 attacker actions, demonstrating that AI agent security cannot rely exclusively on manual human review. Modern development workflows require systems controls to constrain, observe, and govern autonomous agents operating at high speeds. To address related isolation and automation requirements, developers can run AI agents inside GitHub Actions using Docker Sandboxes to execute Testcontainers tests, fix code, and generate draft pull requests. In addition, Docker Extended Lifecycle Support provides continued security coverage past software end of life while moving policy enforcement directly to developer workstations. Finally, Docker Hub has transitioned Docker Verified Publisher applications to a self-serve model, enabling publishers to distribute verified content directly to developers.


### [Building Shared Memory for AI Agents in Notion](https://yomu.fyi/post/building-shared-memory-for-ai-agents-in-notion.md)
- Company: [Notion](https://yomu.fyi/company/notion.md)
- Author: Hesham Salman
- Published: Aug 18, 2026
- Type: Explainer

Lore is an open-source, MIT-licensed tool from Notion for giving AI agents shared, persistent memory backed by Notion, addressing experiential knowledge, follow-up tasks, decision records, and procedures that can disappear between sessions. A Lore vault uses five related Notion databases—Projects, Topics, Memories, Entities, and Facts—with MCP tools for agents, Notion or a CLI for humans, and hooks intended to retrieve context and save information in the background. The design emphasizes memory maintenance: facts expire by default, relationships such as supersedes and conflicts\_with clarify updates, and the CLI can identify orphaned or duplicated information. In a 500-query SkillRet retrieval evaluation, Lore achieved 84% success, while a paired model evaluation found seeded memory recovered about 46% of failures on tasks never solved without memory. The results indicate that relevant, well-maintained memory can improve agent performance, while stale or irrelevant content can harm it.


### [Consistency is the new latency: AI at the data layer](https://yomu.fyi/post/consistency-is-the-new-latency-ai-at-the-data-layer.md)
- Company: [AWS](https://yomu.fyi/company/aws.md)
- Author: Suman Chatterjee
- Published: Aug 18, 2026
- Type: Problem & solution

Autonomous AI agents depend on the accuracy of the underlying data layer because retrieved data populates the LLM context window for multi-step reasoning. In distributed architectures, standard asynchronous replication lag causes agents to ingest stale data, leading to flawed execution and self-reinforcing hallucination debt when errors are saved back to memory. To resolve this, architectures must align replication strategies with specific task truth requirements across three primary patterns. High-stakes workloads utilize Amazon Aurora with global write forwarding or native Aurora DSQL for multi-region strong consistency, while high-scale scenarios leverage DynamoDB Global Tables with conditional writes to prevent lost updates. Finally, high-velocity ingestion pipelines enforce LOCAL\_QUORUM reads and writes in Amazon Keyspaces to capture critical data spikes reliably.


### [Connect client traces to your logs](https://yomu.fyi/post/connect-client-traces-to-your-logs.md)
- Company: [Supabase](https://yomu.fyi/company/supabase.md)
- Author: katerina\_skroumpelou, steven\_eubank
- Published: Aug 18, 2026
- Type: Announcement

supabase-js now supports W3C Trace Context propagation so a client trace can share its trace\_id with Supabase API Gateway and Edge Function logs. Previously, browser and server records had no shared identifier, making cross-boundary debugging depend on manually aligning timestamps. When tracePropagation is enabled, the SDK attaches traceparent, tracestate, and baggage to requests for Supabase domains; Supabase preserves the trace\_id in generated logs, and W3C-compliant tracers such as OpenTelemetry, Sentry, Datadog, Honeycomb, or Grafana can continue the trace server-side. The setup requires a separately configured tracer, the tracing entry-point import, an active span, and a registered TracerProvider; propagation is sampling-aware by default, adds no OpenTelemetry code to the main bundle, and is available in supabase-js 2.112.0 or later, with CDN/UMD builds excluded.


### [Leading Indian Organizations Are Driving India’s AI Future With MongoDB](https://yomu.fyi/post/leading-indian-organizations-are-driving-india-s-ai-future-with-mongod.md)
- Company: [MongoDB](https://yomu.fyi/company/mongodb.md)
- Published: Aug 18, 2026
- Type: Announcement

Six Indian organizations are using MongoDB Atlas to move AI projects from prototype to production at scale. Emergent Labs built a platform for non-programmers to create applications via natural language prompts, powering nearly 12 million apps. Zomato’s AI customer support platform Nugget improved human-agent efficiency by 40% within four months. Leena AI uses MongoDB Atlas to handle high-volume employee queries in real-time across 500 enterprises. Brahma AI relies on MongoDB as a unified data foundation for its enterprise content management and AI creation platform. These organizations cite MongoDB’s flexible document model, built-in search and vector capabilities, and scalability as key enablers for their AI workflows.


### [Introducing a More Connected, Flexible Path to MongoDB Certifications](https://yomu.fyi/post/introducing-a-more-connected-flexible-path-to-mongodb-certifications.md)
- Company: [MongoDB](https://yomu.fyi/company/mongodb.md)
- Published: Aug 18, 2026
- Type: Announcement

MongoDB has updated three certification tracks—Associate Data Modeler, Database Administrator, and Atlas Administrator—so their learning paths now align with Skill Badges. Learners earn Skill Badges as they progress through training, giving milestone recognition instead of waiting until the end. Completing the full certification learning path unlocks 50% off the certification exam. The Data Modeler path covers data modeling, schema patterns, and schema optimization; the Database Administrator path covers querying, indexing, monitoring, performance tuning, security, and sharding; the Atlas Administrator path covers database administration, security, networking, and data resiliency in Atlas environments. Skill Badges recognize focused skills, while certification validates broader professional job-role expertise, and both can also be shared through Credly.


### [Agent Memory Inside the Harness](https://yomu.fyi/post/agent-memory-inside-the-harness.md)
- Company: [MongoDB](https://yomu.fyi/company/mongodb.md)
- Published: Aug 18, 2026
- Type: Explainer

The post distinguishes agent state, the run-bound working data of a single execution, from agent memory, knowledge that outlives the run and is read across sessions. Context compaction, which decides what to keep when the window fills, is lossy by construction and sets both token cost and reliability; Chroma’s study found models become unreliable well before their advertised 200k-token window, and teams compact at 95% or proactively at 60%. System prompts and skills must be versioned, governed infrastructure, not text files, with prompt registries and the SKILL.md standard for procedural memory, and skills are executable so they require sandboxing. Enterprise data enters memory through pipelines like change data capture, not migrations, with chunking, embedding, and provenance stamps. The database choice caps filtered recall under selective scoping, the consistency window, and temporal modeling, setting the ceiling for later decisions.


### [DeepSeek V4 Pro 0813 vs GPT-5.6 Sol on DeepSWE: Cost, Coding, and Routing](https://yomu.fyi/post/deepseek-v4-pro-0813-vs-gpt-5-6-sol-on-deepswe-cost-coding-and-routing.md)
- Company: [Together AI](https://yomu.fyi/company/together-ai.md)
- Published: Aug 18, 2026
- Type: Benchmark

DeepSeek V4 Pro 0813 costs $0.24 per rollout and achieves 62.8% pass@1 on DeepSWE, while GPT-5.6 Sol reaches 72.7% pass@1 at $8.37 per rollout—a 35x price gap. At four attempts, DeepSeek V4 Pro 0813 surpasses Sol, with 88.5% pass@4 versus 85.8%. Sol is faster and more reliable, completing a rollout in 17 minutes and 53 steps, and breaking tests in only 11% of its failures. A cascade strategy—running DeepSeek V4 Pro 0813 first and escalating to Sol on test failure—solves 83.0% of tasks at $3.35 each, outperforming either model alone. Per $100, DeepSeek V4 Pro 0813 solves 260 tasks versus Sol’s 9, making it the value leader for budget-constrained workloads.


### [Hello, Ireland! Sending SMS in Twilio’s Ireland Region](https://yomu.fyi/post/hello-ireland-sending-sms-in-twilio-s-ireland-region.md)
- Company: [Twilio](https://yomu.fyi/company/twilio.md)
- Author: Gary Spencer
- Published: Aug 18, 2026
- Type: Tutorial

Twilio’s Ireland region, IE1, provides EU data residency for Programmable SMS, keeping personal data such as recipient phone numbers and message bodies in the EU through the supplier edge. Adopting it requires separate IE1 credentials and an IE1 Messaging Service, while US1 Messaging Services cannot be reused; SMS to and from +1 numbers, RCS, and WhatsApp are not currently supported. For API calls, the main code change is replacing api.twilio.com with api.dublin.ie1.twilio.com, while client SDK users switch the region parameter from us1 to ie1 and can retain the Dublin edge. Twilio’s logs include a region filter to verify where messages were processed, and the post notes that Studio and TaskRouter support in IE1 is still an initiative.


### [Add an AI Voice Assistant to a Twilio Video Room with Conversation Relay](https://yomu.fyi/post/add-an-ai-voice-assistant-to-a-twilio-video-room-with-conversation-rel.md)
- Company: [Twilio](https://yomu.fyi/company/twilio.md)
- Author: Donal Toomey
- Published: Aug 18, 2026
- Type: Tutorial

The tutorial addresses wasted patient time in telehealth waiting rooms by adding an AI voice assistant to a Twilio Video room for intake collection. It combines Twilio Programmable Video, Conversation Relay, and an LLM, with the assistant joining as an audio-only participant and handling questions about visit reasons, symptoms, and medications. A two-leg Voice call bridges the room to Conversation Relay: one leg participates in the room, while the other sends transcribed audio to a WebSocket server and returns spoken LLM responses. The tutorial uses Node.js, Express, the Twilio helper library, OpenAI, ws, dotenv, and ngrok, and explains setup, browser interaction, and troubleshooting. Its stated result is a working application in which a patient converses naturally with the AI before a provider joins, with GPT-4o-mini processing speech.


### [How to Build Passwordless Auth Using TOTP With Twilio Verify in PHP](https://yomu.fyi/post/how-to-build-passwordless-auth-using-totp-with-twilio-verify-in-php.md)
- Company: [Twilio](https://yomu.fyi/company/twilio.md)
- Author: Matthew Setter
- Published: Aug 18, 2026
- Type: Tutorial

Passwordless authentication can replace passwords with time-based one-time passwords (TOTP), but implementing the setup and verification flow requires coordinating an authenticator app with a verification service. This tutorial builds a web-based PHP application using Twilio Verify, Slim, Twig, and the Twilio PHP Helper Library. Users submit a username, create an initially unverified Factor resource, scan a QR code or enter its setup code, and submit the first six-digit code; later, they enter codes generated by the authenticator app for validation. The project configures Twilio credentials and a Verify Service SID through environment variables, adds session and flash-message support, generates QR codes, defines routes and templates, and runs locally with composer serve on port 8080. The conclusion presents TOTP passwordless authentication as more convenient and potentially more secure than passwords, while acknowledging added application complexity.


### [Multi-Vector (Late Interaction) Embedding Models with Sentence Transformers](https://yomu.fyi/post/multi-vector-late-interaction-embedding-models-with-sentence-transform.md)
- Company: [Hugging Face](https://yomu.fyi/company/hugging-face.md)
- Author: Tom Aarsen, Antoine Chaffin, Raphael Sourty
- Published: Aug 18, 2026
- Type: Tutorial

Sentence Transformers v6.0 adds MultiVectorEncoder, bringing ColBERT-style late-interaction retrieval into the library’s existing API for dense, sparse, and reranker models. The encoder retains one projected, typically 128-dimensional vector per token instead of pooling a document into one vector, allowing documents to be encoded independently and indexed offline. At scoring time, MaxSim finds each query token’s highest dot-product match among document tokens and sums those maxima; contextual embeddings support both paraphrase matching and exact-token evidence. The guide covers checkpoint loading, encoding, scoring, semantic search, retrieval and reranking, indexing, token pooling, inference speed, evaluation, and retrieval from page images, audio, and video. It also quantifies the storage trade-off: 4,874 passages produced 608,414 token vectors and a 311.5 MB float32 index, while fast-plaid compression reduced that example to 92 MB.


### [Device Authorization Flow for a Rust CLI and an Axum API](https://yomu.fyi/post/device-authorization-flow-for-a-rust-cli-and-an-axum-api.md)
- Company: [Auth0](https://yomu.fyi/company/auth0.md)
- Author: Aniket Bhattacharyea
- Published: Aug 18, 2026
- Type: Tutorial

Command-line tools lack browser redirect capabilities, preventing standard OAuth login flows. To resolve this limitation, the OAuth 2.0 Device Authorization Flow issues a temporary device code, presents a verification URL to the user, and waits for authentication in an external browser. A Rust workspace demonstrates this end-to-end pattern across a CLI, an Axum web API, and a shared authentication library. The shared library relies on jsonwebtoken and reqwest to fetch JSON Web Key Sets and validate token signatures, issuers, and audiences against typed claims. Axum secures protected routes through custom FromRequestParts extractors that decode Bearer headers, enabling verified CLI access.


### [How Databricks Feature Store serves features with sub-second freshness](https://yomu.fyi/post/how-databricks-feature-store-serves-features-with-sub-second-freshness.md)
- Company: [Databricks](https://yomu.fyi/company/databricks.md)
- Author: Ian Ackerman, Nick Joung, Abhay Bothra
- Published: Aug 17, 2026
- Type: Explainer

Databricks Feature Store addresses the lag between batch-computed machine-learning features and decisions that depend on events from seconds earlier. It lets a feature definition drive both offline batch processing and online streaming pipelines, orchestrating Kafka ingestion, Spark Real-Time Mode (RTM), Lakebase, and Model Serving. For a rolling 10-minute transaction sum, RTM updates per entity state in local RocksDB, expires contributions per event, and writes revised values to Lakebase through a streaming JDBC sink. The described path reports end-to-end p99 200ms latency from Kafka arrival to online feature availability, while Model Serving retrieves declared dependencies automatically at inference. Tumbling and sliding windows remain options when fewer, cheaper updates are acceptable.


### [How to Evaluate Production AI Agents: Measure System Outcomes, Not Conversations](https://yomu.fyi/post/how-to-evaluate-production-ai-agents-measure-system-outcomes-not-conve.md)
- Company: [Salesforce](https://yomu.fyi/company/salesforce.md)
- Author: Scott Nyberg
- Published: Aug 17, 2026
- Type: Problem & solution

Evaluating AI agents solely on conversational transcripts fails when agents must invoke tools to modify external production systems. Language models can convincingly narrate that an action occurred while completely omitting the underlying tool call, leaving database or billing records unchanged. Outcome-based evaluation addresses this divergence by treating external system mutations rather than generated dialogue as the actual source of truth. Frameworks such as CRMAgentBench implement persistent, stateful environments with strict all-or-nothing validation, verifying tool arguments, execution sequence, final record modifications, and the total absence of unauthorized actions. Furthermore, measuring repeated success across independent executions using pass^k metrics exposes operational variance and inconsistency that standard single-shot scores and pass@k metrics conceal.


### [Same Cluster, 33 Points More Utilization: What Changed Was the Order](https://yomu.fyi/post/same-cluster-33-points-more-utilization-what-changed-was-the-order.md)
- Company: [Hugging Face](https://yomu.fyi/company/hugging-face.md)
- Author: Gabriel Pimenta de Freitas Cardoso, Breno de Almeida Beleza, Francisco de Almeida Rocha Alves, Bruno Duarte
- Published: Aug 17, 2026
- Type: Benchmark

The post presents a constraint-aware GPU allocator as a response to utilization losses caused by fixed real-time reservations and FIFO ordering under contention. It compares the allocator with FIFO on identical hardware and workloads across seven benchmark scenarios, modeling batch-like jobs as contiguous GPU blocks and real-time inference as a timestep-by-timestep demand curve with bounded GPU swaps. Across five contention scenarios, utilization improved from 52–85% to 72–88%, while priority-weighted value increased 24.6–105.1%; the strongest case gained 33 percentage points of utilization and 105% value, and the scale test gained 15.9% value at identical utilization and throughput. The scheduler optimizes a 24-hour horizon but commits only the current timestep, re-running every 30–60 minutes so fresh observations absorb forecast error while preserving running work.


### [The prototyping tax is killing your AI roadmap](https://yomu.fyi/post/the-prototyping-tax-is-killing-your-ai-roadmap.md)
- Company: [Databricks](https://yomu.fyi/company/databricks.md)
- Author: Navdeep Alam, Zhe Sun
- Published: Aug 17, 2026
- Type: Problem & solution

The post argues that the “prototyping tax”—delay between an AI-powered idea and a working MVP—causes initiatives to lose momentum, often because organizational context is fragmented across teams, tools, and codebases. Traditional encapsulation and siloed domain knowledge can leave agents with syntax and contracts but not business intent, making production codebases harder to navigate than personal projects. The proposed response is agentic development grounded in business semantics and governed data, with alignment occurring through working builds while CI/CD, code review, and production rigor remain unchanged. The post recommends tracking time-to-prototype, first-pass acceptance rate, and PoC-to-production rate to distinguish faster demos from durable delivery. It cites a benchmark of 401 data tasks and Abacus Insights results: 77% accuracy at roughly half the cost for a platform-native agent, plus about 40% less manual effort and onboarding to first value in roughly half the time.


[Newer posts](https://yomu.fyi/posts/page/74.md) · [Older posts](https://yomu.fyi/posts/page/76.md)