---
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

### [MCP Marketplace brings real-time intelligence to agentic applications](https://yomu.fyi/post/mcp-marketplace-brings-real-time-intelligence-to-agentic-applications.md)
- Company: [Databricks](https://yomu.fyi/company/databricks.md)
- Author: Roman Ostrovski, Harish Gaur, Antoine Amend
- Published: May 8, 2026
- Type: Announcement

The MCP Marketplace connects agentic applications with real-time external intelligence alongside enterprise data. The problem appears in use cases such as loan approval, where historical internal records omit market conditions, updated credit signals, property changes, and competitor activity, making manual research a bottleneck. Databricks Marketplace provides governed access to MCP servers from You.com, Moody’s, and Cotality, while Unity Catalog authenticates connections and tracks access and lineage; Lakebase stores state, decisions, and audit trails across multi-step workflows. Examples show agents combining internal data with web research, credit ratings and sector outlooks, or property-resolution and mortgage signals before surfacing decisions for human review, including a commercial-loan flow with recorded sources, timestamps, and approver.


### [How we turned support into a revenue engine at Intercom](https://yomu.fyi/post/how-we-turned-support-into-a-revenue-engine-at-intercom.md)
- Company: [Intercom](https://yomu.fyi/company/intercom.md)
- Author: Franka Martinovic
- Published: May 8, 2026
- Type: Problem & solution

After Fin improved resolution rates and efficiency at Intercom, support gained capacity and began testing a consultative role focused on customer value and company goals. The team generated campaign ideas through a support town hall, then assigned a small volunteer group to proactively help self-serve customers with Fin trials, optimization, and adoption. Volunteers were trained to probe customer context rather than only resolve immediate issues, while sales and success teams provided guidance on timing and outreach. Over six months, engaged accounts grew roughly twice as fast in usage and expansion as accounts contacted without a response; the team also tracked resolutions, automation, and influenced expansion ARR. The initiative expanded into cross-functional partnerships and a ~16-person volunteer group, positioning support as a contributor to adoption, retention, and expansion revenue.


### [Pushing the Frontier for Data Agents with Genie](https://yomu.fyi/post/pushing-the-frontier-for-data-agents-with-genie.md)
- Company: [Databricks](https://yomu.fyi/company/databricks.md)
- Author: The Databricks AI Research Team
- Published: May 8, 2026
- Type: Benchmark

Genie is Databricks’ data agent for complex questions across structured enterprise assets—tables, dashboards, and notebooks—and unstructured sources including workspace files, Google Drive, and Sharepoint. Unlike coding agents operating in static environments, it must discover relevant assets at enterprise scale, determine authoritative knowledge from potentially contradictory sources, and handle questions without verifiable tests or guaranteed answers. It combines specialized knowledge search using semantic context and metadata, parallel thinking across sampled trajectories, and Multi-LLM orchestration with optimized prompts for distinct sub-agents. On an internal benchmark of real-world data-analysis tasks, these techniques raised accuracy from 32% to over 90% against a leading coding agent while reducing cost and latency; specialized search alone improved table-discovery performance by up to 40%, while parallel thinking added latency and token costs before further optimization.


### [Energy trading analytics in a real-time market](https://yomu.fyi/post/energy-trading-analytics-in-a-real-time-market.md)
- Company: [Databricks](https://yomu.fyi/company/databricks.md)
- Author: Caitlin Gordon
- Published: May 8, 2026
- Type: Problem & solution

Energy trading markets settle every 15 minutes, while many analytics environments still rely on nightly batch pipelines, creating latency between changing conditions and trading decisions. The post presents Databricks Genie as a conversational interface that lets traders and portfolio managers query actual market data, weather integrations, historical position data, and current books. Its example combines a node’s 90-day natural-gas basis distribution with a Northeast temperature anomaly, while the described system can query real-time and historical data together. Genie also includes settlements, curtailments, and ancillary-service data, with governed access so users see only authorized information. The conclusion is that faster data access can remove information latency and compound margin without replacing trading expertise; the source states that Genie is available today.


### [First-party audience data is the ad sales relationship now](https://yomu.fyi/post/first-party-audience-data-is-the-ad-sales-relationship-now.md)
- Company: [Databricks](https://yomu.fyi/company/databricks.md)
- Author: Elena Tesser
- Published: May 8, 2026
- Type: Problem & solution

The post argues that media companies face a stronger need to turn first-party audience data into an advertising sales advantage as third-party cookies decline and buyer attribution expectations rise. Advertisers are buying audiences rather than inventory, so sales teams need granular audience insights, validated campaign performance, clear attribution, and revenue context to compete in RFPs. Databricks Genie is presented as a natural-language interface to governed first-party data, allowing leaders to query defined audience segments such as users who completed at least 75% of automotive content in 90 days, segmented by income quartile and household ownership. The same analytical environment connects demographic composition, content and behavioral signals, post-campaign measurement, attribution, and revenue pacing against budget and prior year.


### [Building outcome-based pricing for Fin for Sales](https://yomu.fyi/post/building-outcome-based-pricing-for-fin-for-sales.md)
- Company: [Intercom](https://yomu.fyi/company/intercom.md)
- Author: Aisling O'Reilly
- Published: May 8, 2026
- Type: Announcement

Fin for Sales uses outcome-based pricing built around qualified pipeline rather than activity: customers pay $10 per qualified lead, with qualification criteria defined by the customer. The model reflects Fin’s role in engaging prospects, gathering information, evaluating them against those criteria, and routing high-intent buyers to sales representatives. The team rejected revenue-share pricing because attribution would include factors outside Fin’s control, while measuring closed revenue would require deep CRM integrations and slow implementation. Disqualifications and support queries are priced at $1, matching the stated service pricing, while the higher qualified-lead price represents pipeline creation. The company says customer research across several pricing models favored outcome-aligned pricing, and cites early customer feedback reporting at least ten times the value.


### [Operating room utilization is hiding in your scheduling data](https://yomu.fyi/post/operating-room-utilization-is-hiding-in-your-scheduling-data.md)
- Company: [Databricks](https://yomu.fyi/company/databricks.md)
- Author: Adam Crown
- Published: May 8, 2026
- Type: Explainer

Operating room utilization measures in-room surgical minutes against allocated block-time minutes, yet most US health systems reportedly run at 65–75% versus an 80% industry target. Daily performance reports arrive the next morning, after schedules are set and opportunities to release unused blocks, redeploy staff, or backfill add-on cases may have passed. The post presents Databricks Genie as a natural-language interface for querying scheduling, utilization, and outcomes data without a data analyst request. Its proposed analytical environment combines scheduling data, actual case logs, block-release records, contribution margin, and staffing costs, with breakdowns by surgeon, service line, facility, and day of week. Genie surfaces specific intervention targets, although the post says it provides data access rather than automating OR management.


### [Why telecom churn prediction misses the intervention window](https://yomu.fyi/post/why-telecom-churn-prediction-misses-the-intervention-window.md)
- Company: [Databricks](https://yomu.fyi/company/databricks.md)
- Author: Elena Tesser
- Published: May 8, 2026
- Type: Problem & solution

Telecom churn programs often intervene after customers have already shifted behavior, contacted support, or decided to leave, even though earlier signals exist in operational data. The post frames the gap as organizational: propensity models may be sophisticated, but retention leaders need timely, specific answers about high-value customers, likely triggers, and historically effective interventions. Databricks Genie is presented as a natural-language interface over customer behavioral and commercial data, able to surface targets such as premium postpaid customers with usage declines above 20%, recent support contacts, and contracts ending within 90 days. Its described capabilities combine usage, support, billing, network experience, competitive tenure, and intervention history while supporting segment and individual analysis. The proposed operating model prioritizes interventions by customer lifetime value and aims to act early enough for retention efforts to change outcomes.


### [Growth analytics is what comes after growth hacking](https://yomu.fyi/post/growth-analytics-is-what-comes-after-growth-hacking.md)
- Company: [Databricks](https://yomu.fyi/company/databricks.md)
- Author: Madelyn Mullen
- Published: May 8, 2026
- Type: Explainer

Growth analytics is presented as the next stage after growth hacking, arguing that competitive acquisition now depends on precise unit economics, cohort quality, and rapid conversion optimization rather than isolated tactics. It distinguishes product analytics, which explains feature use and user flows, from growth analytics, which connects acquisition sources and costs with activation, revenue, retention, and cohort behavior. The stated bottleneck is fragmented tooling: answering questions such as 90-day LTV by channel correlated with seven-day activation can require manually joining multiple systems and delay weekly budget decisions. Databricks Genie is described as a governed natural-language interface over unified acquisition, behavioral, and billing data, supporting attribution-to-LTV analysis, payback modeling, and paid-versus-organic comparisons. The text reports a 50% relative acquisition-rate lift, from 8% to 12%, for customers using Genie, and shorter onboarding insight cycles from months to weeks.


### [Real-world evidence for medical affairs: who can actually use it?](https://yomu.fyi/post/real-world-evidence-for-medical-affairs-who-can-actually-use-it.md)
- Company: [Databricks](https://yomu.fyi/company/databricks.md)
- Author: Adam Crown
- Published: May 8, 2026
- Type: Explainer

Real-World Evidence (RWE) is increasingly sought by payers, providers, and regulators, but the post distinguishes it from abundant Real-World Data (RWD), which must undergo rigorous study design, analysis, and interpretation to become credible evidence. It identifies four Medical Affairs use cases: regulatory submissions and commitments, payer formulary discussions, rapid HCP scientific exchange, and internal pipeline or portfolio decisions. The stated operational problem is that teams with claims, EHR, registry, and other assets often lack the fluency or capacity to answer complex questions within competitive and regulatory timelines. Databricks Genie is presented as a natural-language interface that can query unified RWE assets, including a treatment-initiation and 12-month-persistence example that reportedly surfaces in seconds rather than requiring several days of data-science work. The post also describes governance, logged and attributable requests, treatment-pathway awareness, and access controls for MSL support.


### [Wealth advisor productivity starts with the client conversation](https://yomu.fyi/post/wealth-advisor-productivity-starts-with-the-client-conversation.md)
- Company: [Databricks](https://yomu.fyi/company/databricks.md)
- Author: Kim Hatton
- Published: May 8, 2026
- Type: Explainer

Wealth management client reviews are intended to turn portfolio information into advisory conversations, but substantial meeting time is spent confirming allocations, benchmark performance, and major positions. Preparing for these meetings requires advisors to combine portfolio, tax, estate, and goal-related information from multiple systems for each client, often under time pressure. Databricks Genie is presented as a conversational way to query client portfolio data in real time, including a tax-loss-harvesting question that combines unrealized losses with an estimated current-year tax rate. Its described capabilities include unified holdings, transaction, tax-lot, and profile data; household-level analysis; authorization controls; and external market context, with the stated aim of reducing information preparation so advisors can conduct deeper, more personalized conversations.


### [Supabase Is Now an Official ChatGPT App](https://yomu.fyi/post/supabase-is-now-an-official-chatgpt-app.md)
- Company: [Supabase](https://yomu.fyi/company/supabase.md)
- Author: gregnr
- Published: May 8, 2026
- Type: Announcement

Supabase is now an official app in ChatGPT, allowing users to connect Supabase projects and manage database infrastructure through conversation. The app provides 29 tools for executing SQL on Postgres, designing and modifying schemas, listing tables and extensions, checking security recommendations, and handling project operations such as logs, costs, pausing, and restoring. It also supports development branches and migrations, serverless edge functions, and direct Supabase documentation search, while ChatGPT Projects can scope chats to a project reference. Users install it from ChatGPT’s app directory, authorize access to their Supabase organization, and can use it on all Supabase plans with paid ChatGPT plans. The stated result is conversational management of Supabase projects without leaving ChatGPT.


### [ClickHouse Release 26.4](https://yomu.fyi/post/clickhouse-release-26-4.md)
- Company: [Clickhouse](https://yomu.fyi/company/clickhouse.md)
- Author: ClickHouse
- Published: May 8, 2026
- Type: Announcement

ClickHouse Release 26.4 introduces 39 new features, 45 performance optimizations, and 238 bug fixes, focusing on broader SQL compatibility and indexing improvements. The update expands standard SQL support by allowing VALUES clauses as table expressions with column aliases, PostgreSQL-style EXTRACT units, NATURAL JOIN, and SET TIME ZONE commands. For text search, LIKE and ILIKE pattern queries using splitByNonAlpha tokenizers scan inverted index dictionaries instead of executing full-table scans when the dedicated evaluation setting is active. The release also provides the JSONAllValues function to extract all leaf values from a JSON column into a string array, enabling text skip indexes that significantly reduce scanned data and improve query latency.


### [Monitor Unreal Engine Game Performance with Application Metrics](https://yomu.fyi/post/monitor-unreal-engine-game-performance-with-application-metrics.md)
- Company: [Sentry](https://yomu.fyi/company/sentry.md)
- Author: Ivan Tustanivskyi
- Published: May 8, 2026
- Type: Announcement

Unreal Engine games frequently experience performance issues such as frame-rate drops, hitches, and network degradation that do not register as application crashes. To address the lack of live production telemetry, the Sentry Unreal SDK introduces automatic performance metrics. The integration periodically samples frame times, network health, active UObject counts, physical memory usage, and garbage collection pause durations across desktop, console, and Android platforms. Telemetry entries attach contextual hardware and environment attributes alongside trace IDs to connect aggregate latency spikes directly to underlying traces and spans. Enabled by default in Unreal SDK version 1.11.0, this telemetry provides developers with fleet-wide visibility into hardware-specific bottlenecks across game releases.


### [Zero-Growth Stack, Real Gains: How Stack Allocation Can Save 10% CPU in Go](https://yomu.fyi/post/zero-growth-stack-real-gains-how-stack-allocation-can-save-10-cpu-in-g.md)
- Company: [Uber](https://yomu.fyi/company/uber.md)
- Published: May 7, 2026
- Type: Benchmark

At Uber, repeated Go goroutine stack expansion consumed substantial CPU in a service whose stack-memory usage remained low, making memory a viable trade-off. Go starts goroutines with 2KB stacks and doubles them when needed, copying the previous stack; the post also notes that adaptive stack sizing and stack shrinking can add runtime cost. Uber patched the runtime, disabled adaptive sizing and shrinking, and used profile-guided analysis of pprof traces plus assembly-derived function stack usage to choose a static power-of-two starting size. For the profiled service, the analyzer identified about 19KB of required stack usage, leading to a 32KB setting instead of 2KB. After deployment, stack-growth CPU fell from close to 10% to below 1%, while most instances used about 50MB of stack and a few reached 200MB.


### [Announcing Fin for Ecommerce: Fin’s next role as a Customer Agent](https://yomu.fyi/post/announcing-fin-for-ecommerce-fin-s-next-role-as-a-customer-agent.md)
- Company: [Intercom](https://yomu.fyi/company/intercom.md)
- Author: Robert Davitt
- Published: May 7, 2026
- Type: Announcement

Fin for Ecommerce is a new Customer Agent role for Shopify merchants, combining shopping assistance with ecommerce support before and after purchase. It helps shoppers discover products through conversational questions, live browsing context, catalog retrieval, comparisons, complementary recommendations, cart updates, and checkout guidance, while handling returns, refunds, exchanges, order changes, tracking, and shipping questions in the same conversation. The system uses Fin Apex 1.0 with an ecommerce retrieval engine and connects to Shopify to sync products, variants, content, order data, inventory, and APIs. Merchants can add Messenger and set Fin live in minutes without manual training; Shopify API integrations also let Fin use Procedures for complex requests, with drafts based on account data and company policies for review. The announcement positions Fin as a single Agent spanning discovery, purchase, and post-purchase support, with named ecommerce brands already using it.


### [Introducing Postgres Query Insights in ClickHouse Cloud](https://yomu.fyi/post/introducing-postgres-query-insights-in-clickhouse-cloud.md)
- Company: [Clickhouse](https://yomu.fyi/company/clickhouse.md)
- Author: Amog Iska
- Published: May 7, 2026
- Type: Announcement

ClickHouse Cloud introduced Query Insights in preview for Managed Postgres to help teams diagnose slow database queries. Powered by the open-source extension pg\_stat\_ch, the tool streams per-statement telemetry directly into ClickHouse to enable fast aggregations across billions of execution rows. Postgres normalizes query literals into placeholders during the parse-analyze phase before telemetry leaves the database, preventing sensitive data exposure. Telemetry emission maintains around three percent producer overhead by utilizing a non-blocking try-lock on a shared-memory ring buffer. Users can examine high-level database health metrics, rank query patterns by runtime or latency percentiles, and inspect execution flyouts detailing disk spills, cache hits, and parallel worker behavior.


### [AI Is Changing What Customers Need From a Database. MongoDB 8.3 Is Built for It](https://yomu.fyi/post/ai-is-changing-what-customers-need-from-a-database-mongodb-8-3-is-buil.md)
- Company: [MongoDB](https://yomu.fyi/company/mongodb.md)
- Author: Ben Cefalo
- Published: May 7, 2026
- Type: Announcement

MongoDB announced the general availability of MongoDB 8.3, designed to support high-throughput AI workloads without requiring application code changes. Compared to version 8.0, the release provides a 35 percent boost in write throughput, a 45 percent increase in read speeds, and 15 percent faster ACID transactions. Additionally, cross-region connectivity for AWS PrivateLink is now generally available, enabling private traffic routing between Atlas clusters across distinct AWS regions without public internet exposure. MongoDB Atlas supports deployments across 130 regions spanning AWS, Google Cloud, and Microsoft Azure, including multi-cloud cluster topologies. These infrastructure updates target enterprise demands for sub-100ms retrieval, sub-second context updates, zero downtime, and strict data residency compliance.


### [How lakebase architecture delivers 5x faster Postgres writes](https://yomu.fyi/post/how-lakebase-architecture-delivers-5x-faster-postgres-writes.md)
- Company: [Databricks](https://yomu.fyi/company/databricks.md)
- Author: David Wein, Vlad Lazar
- Published: May 7, 2026
- Type: Benchmark

Lakebase’s separation of Postgres compute and distributed storage removes the local-disk torn-page risk that necessitates full page writes (FPW) in traditional deployments. The change disables FPW on compute and moves full page image generation into the pageserver, which creates reset points after a configured number of WAL deltas while preserving bounded read reconstruction. In HammerDB TPROC-C tests, 32-vCPU throughput rose from 95,686 to 439,300 new orders per minute, while average WAL per transaction fell from 58KB to under 4KB, a 94% reduction. Production validation reported WAL reductions from 30MB/s to 1MB/s on a 56-vCPU project, p99 read latency improvements of 30% to 50%, and up to threefold regional storage p99 improvement. The rollout reached all Lakebase Serverless and Neon databases without restarts or customer interruption, using the existing XLOG\_FPW\_CHANGE mechanism.


### [Why talent transformation is the missing focus of enterprise AI](https://yomu.fyi/post/why-talent-transformation-is-the-missing-focus-of-enterprise-ai.md)
- Company: [Databricks](https://yomu.fyi/company/databricks.md)
- Author: Christy Seto, Pratyarth Rao
- Published: May 7, 2026
- Type: Announcement

Enterprise AI adoption is presented as a talent problem as much as a technology or strategy problem: insufficient worker skills are identified as the biggest barrier to integrating AI into work, while hiring alone cannot fill demand. The proposed response is continuous upskilling for both technical practitioners and line-of-business users, replacing one-time enablement with learning tied to current work and changing platform capabilities. Databricks Academy Pro is an annual, per-seat subscription combining self-paced courses, weekly live reviews, unlimited public instructor-led classes, hands-on labs in hosted Databricks environments, and one certification exam voucher per user each year. Starter, Growth, and Enterprise tiers add private online community access, a custom Academy portal, and a designated Talent Transformation program manager as seats increase. The offering is available today, alongside private instructor-led training and standalone certification vouchers.


[Newer posts](https://yomu.fyi/posts/page/131.md) · [Older posts](https://yomu.fyi/posts/page/133.md)