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
Agent Bricks: The governed enterprise agent platform
Agent Bricks is presented as Databricks’ enterprise platform for building, deploying, and governing agents that operate on business data under real identities, permissions, and operational constraints. The platform combines multi-model and framework support, execution, routing, fallback, cost optimization, and unified governance through Unity Catalog and AI Gateway, including on-behalf-of token passing and observability across data, models, MCPs, and APIs. Its context layer uses metadata such as schemas, business definitions, lineage, permissions, and data-quality signals, while Genie Spaces, Document Intelligence, Knowledge Assistant, and Agent Mode address structured and unstructured business information. The announcement includes general availability for Document Intelligence, Custom Agents on Apps, and Supervisor Agent, plus AI Gateway guardrails, managed OAuth MCP Connectors, web search, and MLflow’s CLEARS evaluation framework; the post reports 70% higher accuracy than standard RAG and a 30% improvement in multi-step workflows.
The hardest percentages
Complex customer-support queries are relatively infrequent but consume disproportionate handling time and shape customers’ memories of service, especially when they require action across systems. The post distinguishes informational, personalized, and action-led queries, then positions Fin Procedures as a way to automate complex cases through configurable multi-step processes using natural-language SOPs, branching logic, data connectors, and AI-powered simulations. Since managed-availability launch, Procedures has handled more than 1.5 million conversations across hundreds of apps, with volume doubling month over month; a randomized 5% holdout found CSAT 28.93% higher when Procedures ran. The product is available to all 8,000+ Fin customers and adds review, failure reporting, rollback, connector monitoring, email simulation, and Agent in the Loop checkpoints for human approval or missing integrations.
Agentic coding with ClickHouse. One person, one data stack, one full-stack application
A Solutions Architect at ClickHouse built ClickShop, a full-stack retail analytics platform, within a few days using Cursor to demonstrate production-level capabilities beyond static slides. The platform pairs ClickHouse for sub-second analytical queries across billions of rows with PostgreSQL for transactional workflows, using ClickPipes for real-time change data capture synchronization. LibreChat orchestrates 18 persona-tailored AI agents, while dual observability layers—ClickStack for OpenTelemetry infrastructure metrics and Langfuse for LLM prompt and cost tracking—store their telemetry directly in ClickHouse. Developing with an AI-assisted IDE was accelerated by open-source documentation and community skills, though it required continuous human review to handle unintended code refactoring and token consumption.
8 AI and data trends shaping financial services in 2026
The post argues that financial-services AI adoption is widespread, but execution—not model capability or strategy—is determining who captures value in 2026. It attributes stalled pilots to fragmented legacy infrastructure, inconsistent data, weak lineage, and insufficient control for governed, real-time workflows such as fraud detection, pricing, and personalization. Firms advancing further treat data as a managed asset, embed governance in data and model pipelines, and align data, analytics, and AI teams around shared definitions, workflows, and metrics. The proposed remedy is a unified lakehouse environment combining storage, compute, governance, lifecycle management, orchestration, streaming, and AI workflows, with Unity Catalog providing centralized access control, lineage, and auditing. The conclusion is that by the end of 2026, firms that embed AI into operational decisioning at scale will pull ahead of organizations still running pilots.
Mintlify boosts NPS 30% and saves 60% with real-time analytics on ClickHouse Cloud
Documentation platform Mintlify experienced major dashboard performance degradation and rate limiting under PostHog as multi-tenant analytics traffic grew rapidly. Because PostHog lacked incremental materialized views, queries scanned full raw datasets and took tens of seconds to load. Mintlify migrated its customer-facing analytics infrastructure to ClickHouse Cloud, ingesting events through Amazon MSK and ClickPipes into a single events table backing incremental materialized views. The team executed the transition over two weeks by dual-writing events and replicating the existing PostHog schema to preserve API surface compatibility. The migration reduced dashboard query latency to sub-one-second, decreased related support bug reports to zero, lifted NPS by an estimated 30%, and lowered analytics infrastructure costs by approximately 60%.
Speeding up GPU kernels by 38% with a multi-agent system
The post reports a three-week experiment in which a multi-agent system optimized 235 CUDA kernel problems generated from workloads spanning more than 124 production open-source models. Using SOL-ExecBench on 27 NVIDIA Blackwell 200 GPUs, the system used a planner to distribute and rebalance work, while autonomous workers benchmarked, debugged, and refined kernels without developer intervention. It ran separate CUDA C with inline PTX and CuTe DSL runs, reaching assembly-level optimization and learning a documented higher-level API. Against a single-agent optimized PyTorch baseline, it outperformed 149 of 235 problems, achieving a 1.38x geometric mean ratio, while 45 solutions exceeded 2x. The highlighted cases included an 84% geomean gain over a human FlashInfer baseline for paged-prefill attention, a 39% gain for NVFP4 MoE linear, and a GEMM reaching 86% of a tuned cuBLAS baseline; median SOL was 0.56, leaving room for improvement.
Building real-time product search on Databricks
Real-time product search for an online marketplace must retrieve, filter, rank, and respond in milliseconds while balancing latency, relevance, revenue, and click-through rate. The Databricks architecture divides the pipeline into ingestion, retrieval, and refinement, using Lakeflow pipelines and AI Functions for source processing, AI Search for embeddings and hybrid retrieval, and Lakebase for sub-10ms operational signals. It recommends validating p95/p99 latency, throughput, retrieval quality, and engagement metrics, with MLflow supporting systematic evaluation and caching helping meet strict latency requirements. As an example, FOX Sports used AI Search for thousands of QPS and achieved a 2x improvement in query success rate, combining streaming ingestion, two-phase retrieval, model serving, caching, and trending searches.
We're Transferring the Stripe Sync Engine to Stripe
The Stripe Sync Engine repository is moving from supabase/stripe-sync-engine to stripe/sync-engine after growing from an open-source tool for syncing Stripe data into a Stripe schema in Postgres. The transfer follows collaboration that added cursor-based incremental sync, JSONB storage with generated columns, multi-account support for Stripe Connect platforms, event ordering in a new CLI, and automatic incremental backfilling using Supabase Cron and Queue. The latest release adds coupon synchronization, branching support, immediate syncing on installation, one-click upgrades, SSL enforcement, and tighter installation controls, along with clearer errors and dashboard visibility for Edge Function source code. The project remains open source under Apache 2.0, existing installations continue to work, and the Supabase dashboard integration is unchanged. With Stripe data in Postgres, users can join it with application data for subscription checks, feature gating, MRR, and churn analysis.
AI Email Editor
Resend announces an AI-extended email editor designed to help users create emails that retain their brand voice while catching mistakes and reducing workflow friction. Users can provide a URL, and the AI extracts the brand, voice, and tone to generate a ready-to-send draft from existing content such as a blog post, changelog, or product page. During composition, selected blocks can be rewritten, rephrased, or improved, while pre-send checks cover deliverability, content compatibility, subject and preview, broken links, and typos. The editor also supports agents through the Resend MCP server, with access to the visual editor, real-time collaboration, cursor support, and presence indicators; the announcement says all features are live in the Broadcast and Template editors.
Build Better AI Agents: 5 Developer Tips from the Agent Bake-Off
The Google Cloud AI Agent Bake-Off is presented as a test of building autonomous agents under severe time constraints for e-commerce, banking modernization, and startup go-to-market problems. Its five patterns recommend decomposing monolithic prompts into specialized sub-agents under a supervisor, designing modularly because model capabilities can quickly replace custom harnesses, and treating multimodality as native. It also advocates open protocols—including MCP, A2A, UCP, AP2, A2UI, and AG-UI—for agent and tool connections instead of bespoke wrappers. Finally, it separates probabilistic reasoning from execution: strict JSON schemas such as Pydantic validate LLM outputs before deterministic Python functions or SQL perform calculations and writes. The stated conclusion is that reliable production agents depend on rigorous software architecture rather than elaborate prompts or flashy single-shot demos.
From swarms to product: Turning customer signals into scalable features
Intercom’s Fin teams use cross-functional swarms to identify customer needs while helping customers increase automation and understand the product. In these high-touch engagements, engineers, data scientists, and a product manager analyze conversations, APIs, Procedures, and workflows, using fast feedback to test configuration changes and estimate achievable automation; one manual taxonomy analysis took more than half a day and predicted a 70% rate that the customer achieved. Cockpit then encodes swarm patterns into repeatable workflows, letting customer success managers and Sales assess automation potential, diagnose issues, and suggest next actions across accounts without repeated data-science involvement. It also tests whether ideas generalize before product development. Patterns that prove broadly useful, robust, and scalable can move into product features such as the automation taxonomy in Insights and CX Score, which measures conversation quality; unlike Cockpit, product features must work for every customer without configuration.
Managing context in long-run agentic applications
Long-running multi-agent systems struggle with context management because accumulating raw message histories degrades inference quality, increases latency, and exceeds context window limits. In a collaborative security investigation platform, passing unrestricted history can also introduce confirmation bias across specialized agents. To maintain coherence across unbounded rounds of investigation, the system eliminates raw message history carryover between invocations. Instead, it coordinates agents through three structured context channels: a Director's Journal for orchestration memory, a Critic's Review that scores findings to filter hallucinations, and a Critic's Timeline of validated chronological events. This architecture provides agents with tailored context without overwhelming their inference capacity.
Lovable + Databricks: Build Data-Driven Apps at the Speed of Thought
Databricks users outside data teams often depend on requests to access business data because they may not write SQL or have a Databricks license. The official Lovable connector lets teams connect Lovable to a Databricks environment and build custom internal applications with plain English. Lovable's AI-powered agent examines accessible data and builds and deploys an application, while Databricks remains the source of truth and data stays within its security perimeter. Data is queried from Databricks at runtime, avoiding ETL, data replication, and sync jobs. Examples include live revenue and pipeline dashboards, spreadsheet-replacing operational tools, internal Slack chatbots, and other business applications that teams can build without engineering or data-team support.
Automating Receipt Collection: Apple Intelligence for On-Device Inference
Ramp built automatic receipt detection for its iOS app to reduce the effort of finding receipt photos while keeping private images on device. An initial design used PhotoKit, Vision OCR, background processing, local storage, and exact checks for merchant, amount, and date, but formatting differences, aliases, and OCR errors produced many false negatives. FoundationModels enabled a local structured-output LLM, yet a single prompt performed poorly in evals because the small 4096-token model hallucinated and took shortcuts. Splitting the merchant, date, and amount questions and requesting rationale improved evaluation results, but the alpha release reached 66% precision and about 18% recall. Version 3.0 combined one LLM merchant-name check with deterministic iOS 26 data detectors for dates and monetary values; it cut processing time, more than doubled recall, and raised precision to 87%.
Using AI agents to build Stripe-Salesforce integrations faster
An experiment using Claude Code to build a Stripe App for Salesforce Flow exposed context gaps: the generated integration misnamed fields, targeted a nonexistent custom field, and omitted AsyncAfterCommit, causing a “Callout from triggers not supported” deployment error. The proposed remedy is a repository of grounding context files that present invocable signatures, request models, platform constraints, LWC patterns, and validated examples in concise, machine-readable form. Core files are about 35K tokens, while the full reference catalog is about 230K tokens and can be loaded on demand. With the context loaded, the agent selected the v02_CreateCustomers invocable directly and generated a helper Apex class for nested Checkout Session inputs, along with callout-safe Flow structure and other safeguards. The author reports minutes instead of hours and fewer iterations in personal usage, while noting that org-specific details still require human verification.
Re-imagining ML Serving Infra: My Winter Internship at Ramp
Ramp’s ML Platform team needed to separate flexible model development in ml-pipelines from the Intelligence Platform’s 99.9%+ uptime and low-latency requirements. The internship project, Bring-Your-Own-Model-Weight Serving (mw-serve), built a dedicated serving layer that pulls model weights from MLflow and a training-environment base image from ECR, then runs each model in an isolated instance. To protect uptime, it added deployment safeguards, pre-traffic liveness checks, and monitors, while latency work instrumented client TCP/TLS connections and server processing. The investigation traced extreme tail latency to connection churn, which improved with longer keepalives and startup warmups, and to garbage-collection pauses associated with memory drops; tuning thresholds and freezing objects removed more outliers. By the final day, one Intelligence Platform model was serving production traffic through mw-serve, with additional models in shadow testing.
Introducing clickhousectl: the CLI for ClickHouse local and cloud (beta)
ClickHouse released the beta version of clickhousectl, an official command-line interface designed to unify local operations and cloud infrastructure management for both humans and AI agents. The tool acts as a version manager that stores reusable binaries globally in ~/.clickhouse/versions/ while offering optional project directory scaffolding for SQL files. Developers and agents can run multiple isolated local server instances concurrently with automatic free-port detection and dedicated data directories. For ClickHouse Cloud, the CLI provides complete management coverage with structured JSON output, using read-only OAuth or scoped API key authentication to safeguard modifying operations. Additionally, the tool can install ClickHouse Agent Skills directly into supported coding agents to facilitate automated local and cloud interactions.
Enabling Multi-Region Data Systems at Notion
Notion’s data residency work keeps customer data processed and stored in the region where it was generated, supporting EU requirements across Search, analytics, scheduled events, and AI. To make this possible, Notion modularized infrastructure around isolated private networks and workspace IDs, then deployed regional data lakes, Kafka clusters, Spark jobs, Elasticsearch, and vector databases. Debezium captures Postgres changes into regional Kafka, while Airflow remains a centralized orchestration layer that routes jobs to regional EMR clusters; event logging similarly routes traffic by workspace and sanitizes data before Snowflake. Centralized mapping tables, shared region helpers, Terraform, and localized sanitization let teams retain a unified Snowflake environment without exporting customer data. The work took months, and Notion says it is applying these patterns to Japan and South Korea while aiming to provision future regional data stacks within days rather than months.
The cure for "execution tax" | Notion
Brainlabs CEO Dan Gilbert describes “execution tax” as the gap between a decision and its outcome, where meeting action items are recorded, chased, or lost. He argues that AI has improved engineering productivity while leaving strategists, account managers, and operators with fragmented context and a wide gap between thinking and doing. Brainlabs chose Notion as a company-wide context layer and built “Get Stuff Done,” a factory of Notion Custom Agents that captures action items, assigns owners, and executes suitable work. Its automation uses Notion Custom Agents for native tasks, Notion Workers for external integrations, company-specific Skills and selected LLMs for complex tasks, and human-in-the-loop workflows when judgment remains necessary; Gilbert says some decisions now become completed work in minutes rather than weeks.
AI Agents Know About Supabase. They Don't Always Use It Right.
Supabase is releasing Supabase Agent Skills, an open-source instruction set for AI coding agents working with Supabase through Claude Code, Codex, GitHub Copilot, Cursor, and compatible Agent Skills implementations. The skill addresses recurring errors such as omitted RLS policies, hallucinated CLI commands, views missing security_invoker = true, and reliance on outdated training data by requiring documentation checks and embedding critical security guidance in SKILL.md. It also guides CLI and MCP workflows and recommends direct schema changes on local or staging databases, followed by database advisors and a migration after the schema stabilizes. Early evaluations across six scenarios found MCP + Skill scores of 67% for Claude Opus 4.6, 71% for Claude Sonnet 4.6, 88% for Codex GPT-5.4, and 71% for GPT-5.4 Mini, though the sample was small.
Top topics
- Architecture834
- Performance816
- LLMs660
- Machine Learning622
- Open Source563
- AI Agents553
- AI470
- Developer Experience448
Weekly digest
The best engineering reads, once a week.