Loading…
Latest reads
Every post, summarised
Grounded summaries of engineering blogs, newest first. Each links to the original.
- 4,671 posts
- 20 companies
The Good Stuff
Paid picks we use ourselves. Links carry a referral code — a subscription through one earns us a commission at no extra cost to you.
Latest posts
Building Secure AI Agents with Microsoft Agent Framework and Auth0: Sending Email with Token Vault
An expense-reviewing AI agent required manual manager intervention to email employees about missing report data such as amounts, merchants, or justifications. To automate follow-ups safely, the agent uses Auth0 Token Vault to acquire and refresh Google OAuth tokens without storing credentials in the application database. The implementation configures Auth0 with offline access, My Account API permissions, and multi-resource refresh tokens to handle silent token retrieval across user sessions. Rather than exposing Gmail credentials to the underlying language model, the agent executes email actions via an internal backend endpoint that retrieves a short-lived access token, sends the email, and immediately discards the token.
Examining Human-Like Behaviors in LLMs: A Multi-Dimensional Analysis of Model Behaviors, User Factors, and System Prompts
Large language models frequently exhibit human-like behaviors such as expressing emotions, building relationships, and setting boundaries, yet empirical guidance on appropriate usage remains limited. To address this gap, researchers analyzed 21,000 multi-turn conversations across four models: gpt-4o, gpt-4.1-mini, claude-sonnet-4.6, and gemini-2.5-flash. The study combined LLM-as-a-judge techniques with human evaluation to measure behavior prevalence, perceived appropriateness, and prompt controllability across diverse user goals and profiles. Human evaluators judged LLM self-referential and relationship-building behaviors as less appropriate than identical human actions, whereas boundary-maintaining behaviors were rated as more appropriate for models. System prompting effectively steered these behaviors, though the authors emphasize that rigorous evaluation remains necessary to prevent unintended side effects.
The P-Completeness of Inverted Index Traversal: On the Complexity of Evaluating Boolean Query DAGs
Modern artificial intelligence agents increasingly rely on search infrastructure to run complex, neuro-symbolic reasoning workflows that compile into deeply nested, non-monotonic Boolean queries. Standard inverted index evaluation methods struggle with these query structures, facing either exponential query complexity under Document-at-a-Time models or universe-scale space penalties under Term-at-a-Time models during logical negation. To address these theoretical limitations, the author formalizes a DAG-based retrieval language named L_R and proves its query evaluation problem is strictly P-Complete. The paper introduces ComputePN, a deterministic and sparsity-aware algorithm that employs a Positive-Negative dual representation alongside native DAG memoization. This mechanism bounds evaluation time to O(|Q| · |U_active|), effectively evaluating P-Complete queries natively over the index while bypassing combinatorial tree expansion and universal scan overhead.
Databricks Document Intelligence: pushing the frontier for complex document extraction
Databricks introduces Precision Mode for its ai_extract document extraction API, targeting enterprise workloads that challenge existing LLM and rules-based systems. The mode addresses long documents with cross-references, large nested outputs such as thousands of line items, and schemas requiring reasoning across financial statements or applying discounts. It combines custom-trained, efficient extraction models with an agent harness that decomposes jobs semantically, runs smaller tasks in parallel, preserves intermediate results, and reconciles them into a final structured output. On benchmarks covering roughly 9,000 documents, including files up to 2,000 pages and schemas with more than 300 deeply nested fields, Precision Mode reached 94.7% accuracy, seven points above the strongest frontier-model chunk-and-merge baseline, GPT-5.6 Sol; the source says it is now available through ai_extract and the Information Extraction UI.
How Much Memory Does Your Agent Actually Need?
The post examines how much agentic memory different models can use effectively, evaluating ALTK-Evolve's self-distilled guidelines across eight models on AppWorld's 585 multi-step tasks. Memory is produced by extracting and consolidating lessons from successful and unsuccessful trajectories, then delivering either the full guideline set on every ReAct step or a fixed core plus task-relevant retrieval, without updating model weights. Results identify three patterns: strong models with headroom benefited from the full set, gpt-oss-120b gained 16.1 percentage points in task completion from curated retrieval, and GLM-5 showed no measurable gain; stricter scenario completion sometimes improved more. Curated retrieval gave gpt-oss-120b that gain with only 5% more tokens versus 51% for its full set, while prompt caching is presented as a way to reduce recurring input cost, supporting calibration to model capability rather than simply accumulating memory.
How AI Coding Agents Can Unlock Materials Simulation with NVIDIA ALCHEMI Toolkit
Atomistic simulation combines scientific judgment, compute-efficient implementation, and an accessible interface to the simulation stack, but the MLIP ecosystem lacks the mature interfaces available for classical force fields. NVIDIA ALCHEMI Toolkit addresses implementation with composable, PyTorch-native, GPU-accelerated building blocks and in-flight batching, while its agent skills and reference files supply API patterns to coding agents. The post benchmarks 45 generated pipelines across silicon equation of state, copper adsorption, and lithium self-diffusion, checking code features and running representative workloads on NVIDIA H200 GPUs. All 45 scripts used batched GPU execution, 38 completed screening, and all 15 production representatives completed; however, agents did not assess physical validity, and thermostat choices could suppress measured lithium diffusion by 3–5×, so independent validation against DFT, experiment, or another reference remains necessary.
Improving infrastructure efficiency for growing demand in the age of AI
Dropbox manages growing infrastructure demands from AI and standard workloads by maximizing the efficiency of its existing data centers rather than just building more capacity. Through a system-level approach spanning software, hardware, and physical facility design, the company dynamically manages power and balances workloads. These optimizations, combined with higher storage density and data-driven hardware lifecycle management, have significantly reduced energy use per unit of storage.
Run Massive-Scale UMAP in Minutes Using Multiple GPUs—Without Losing Accuracy
UMAP workflows on tens to hundreds of millions of vectors are constrained by the cost of constructing an all-neighbors k-nearest-neighbor graph, especially when repeated runs support exploration and parameter tuning. The NVIDIA cuML and cuVS 25.06 feature distributes this graph-construction stage across multiple GPUs while retaining the out-of-core design that partitions data into balanced clusters, overlaps vectors across nearby clusters, computes local graphs, and merges them into a global graph. knn_n_clusters and knn_overlap_factor expose the memory, runtime, and graph-quality trade-off: more clusters reduce per-GPU data, while more overlap can improve nearest-neighbor recall at higher computational and memory cost. On eight NVIDIA H100 GPUs, the reported evaluation found up to 74x end-to-end speedup over a projected CPU runtime for the 106M-vector MIRACL dataset, completing it in 8 minutes. The post states that performance continues to improve from one to eight GPUs while preserving comparable embedding quality across configurations.
How Sony LIV uses ClickHouse Cloud to deliver live streaming analytics at billion-row scale
Sony LIV’s legacy analytics environment combined batch pipelines, Elasticsearch, BigQuery, and other telemetry stores, creating slow, costly, fragmented analysis as streaming activity reached billions of events per day. During live sports, the platform needed sub-second queries, high ingestion throughput, cost-efficient long-term storage, and horizontal scaling for sudden traffic spikes. Sony LIV consolidated these workloads on ClickHouse Cloud: client, streaming, CDN, and advertising systems send events through Amazon Kinesis and ClickPipes into a ClickHouse cluster serving dashboards, product analytics, QoE, and SRE workflows. The source reports that queries previously taking tens of seconds to minutes now run in sub-second to low-single-digit seconds, improving operational responsiveness, engineering productivity, and the handling of major live-event traffic.
17,600 Actions: Agent Security Is a Systems Problem
Security incidents involving AI agents, such as the OpenAI and Hugging Face event where attackers executed 17,600 actions, demonstrate that system security cannot rely entirely on manual human review. Managing agent velocity requires dedicated system-level controls to properly constrain, observe, and govern their behaviors during execution. To secure autonomous development workflows, Docker Sandboxes allow AI agents to operate within GitHub Actions, run Testcontainers tests, adjust code, and automatically generate draft pull requests inside isolated environments. In addition, escalating software supply-chain threats and the increased volume of AI-generated code drive the adoption of Docker Hardened Images and Docker Extended Lifecycle Support. These updates incorporate software built from source into container images, extend security patch coverage past end-of-life milestones, and move organizational policy enforcement directly onto developer machines.
BGP Role model: tracking the adoption of RFC 9234
Border Gateway Protocol route leaks occur when routing announcements propagate beyond their intended customer-provider or peer relationships, causing traffic misdirection and performance degradation. RFC 9234 embeds relationship awareness directly into BGP by establishing negotiated BGP Roles and attaching an Only to Customer (OTC) transitive path attribute to prevent unauthorized route propagation. To assess real-world adoption, Cloudflare monitored OTC attribute transmission across peer networks and discovered that 33.1 percent of IPv4 and 17 percent of IPv6 paths were missing the OTC attribute. Investigation revealed that Tier-1 transit providers AS1299 and AS3257 were stripping the attribute due to legacy defensive BGP error-handling configurations. Following direct engagement, AS1299 updated its configurations to preserve OTC propagation, whereas AS3257 continued stripping it, highlighting the necessity of broader vendor and carrier support across the Internet.
When it comes to Governance, Retailers need a control plane for context
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
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
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
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
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
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
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
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
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.
Top topics
- Architecture834
- Performance816
- LLMs660
- Machine Learning622
- Open Source563
- AI Agents553
- AI470
- Developer Experience448
Weekly digest
The best engineering reads, once a week.