Loading…
Browse by type
Problem & solution reads
Problem & solution posts on Yomu, summarised newest first.
- 910 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.
Problem & solution posts
Smarter personalization: How property data helps us understand user price sensitivity
Existing systems estimate user price sensitivity from spending behavior or demographic proxies, missing residential property values and creating one-dimensional profiles. This invention proposes a four-step method that combines public property data with LLM-assisted data structuring, building-level price estimation, hierarchical clustering, and user mapping. The method collects public property records, uses LLMs to standardize attributes such as postcode, transaction price, and property size, then aggregates transactions within buildings to calculate weighted average sale prices. A hierarchical clustering model groups buildings into affluence tiers based on estimated resale values, accounting for regional market differences, and users are mapped to these tiers via aggregated geographic signals. The approach remains unimplemented and untested in live markets, with potential applications in personalization, advertising, and operational planning subject to future technical validation and privacy approvals.
How to design an AI agent for resolution instead of rapport
Most conversation design guidance focuses on voice and tone, but consumers prioritize immediate issue resolution (40%), speed (40%), accuracy (38%), and 24/7 availability (38%) over rapport. The post recommends opening with capability, loading context before the first turn using persistent profiles, and designing a second option when the first fails. Escalation should be triggered by conversation rules like a second failed attempt or explicit request, not treated as an error condition. Confirmation turns should be cut except for irreversible actions, and agents should clearly state what they cannot do. An agent with customer history, a backup path, and a clean exit is more helpful than one with a carefully written persona but lacking those features.
RISED: Rubrics for Agentic Multi-Environment Selection and Self-Distillation
Training a single LLM agent jointly across diverse interactive environments is challenged by scalar rewards that provide limited information about cross-environment relationships and no within-group reward contrast when rewards are identical. RISED addresses this by using rubrics—textual descriptions of rollout behaviors—to guide both online data selection and policy supervision. An LLM judge tags each rollout with a predefined rubric vocabulary shared across environments, and these profiles select data aligned with the batch’s behavioral composition while limiting overlap with already-selected data. Positive rubrics supply token-level supervision via an on-policy self-distillation teacher, while negative rubrics steer subsequent rollouts away from recurring failure modes. Across model backbones, RISED achieves the highest mean pass rate across environments and ranks first or second in every individual environment.
How Genie Ontology powers product development at Databricks
General-purpose AI agents fail on business questions because they lack enterprise context such as authoritative tables, business rules, and trusted experts; the missing institutional knowledge is scattered across dashboards, documents, and people. Databricks’ Genie Ontology addresses this by continuously updating institutional knowledge from certified Unity Catalog concepts and automatically learned snippets from dashboards, notebooks, SQL queries, and connected apps. OntoRank ranks sources by authority using certification, usage, and authorship signals, so Genie grounds answers in the most trusted and relevant data. In a weekly adoption review, a product manager prompts Genie, which uses MCP to search Google Docs and Jira while running live SQL for fresh analysis. The resulting report includes citations, forecasting, scheduling, and even conversion into a shareable Genie Agent, all within permission boundaries.
How we scaled engineering enablement and infrastructure at Intercom - The Intercom Blog
Intercom’s engineering enablement team transformed the company from a patchwork of legacy systems and recurring incidents into a stable infrastructure that empowers fast-moving product teams. The company learned that selecting core technologies is not enough without a clearly defined strategy for understanding, guiding their use, and investing in the teams behind them, as lacking this leads to persistent friction. They defined a dedicated core technology team, learned and standardized their tooling, and implemented approaches to hire and grow engineers who own the infrastructure. These efforts reduced operational friction and incident frequency, allowing the business to move more confidently. As a result, product teams run faster and the infrastructure is now a reliable foundation for growth.
The Ticket: Fueling The AI machine with the knowledge it needs
The performance of an AI-driven customer support engine depends directly on the quality of the knowledge that feeds it, as accurate, up-to-date content is critical for giving customers instant and trustworthy answers. Investing time and care into help content can significantly boost automated resolution rates, as Intercom has experienced firsthand. Many busy support teams struggle to prioritize maintaining their help centers due to limited resources, but filling content gaps and updating content after launching new products is essential for AI success. Knowledge content compounds in value over time; Intercom’s transition from its Resolution Bot to the Fin AI chatbot resulted in resolution rates skyrocketing from the start. Knowledge management should be cultivated as a company-wide responsibility, with input from product, engineering, sales, and marketing teams, and in the near future, internal knowledge will also be fed to AI to help agents answer complex queries.
CX leader Camille Acey on the evolving dynamics in customer service - The Intercom Blog
Camille E. Acey, a seasoned CX leader and consultant, describes the profound transformation underway in customer service, driven by AI, layoffs, and rising customer expectations. She advises startups to avoid over-hiring senior full-time roles and instead use fractional CX leaders who can establish strategy while junior or mid-level staff manage daily operations. Camille emphasizes that AI cannot replace human empathy and should be deployed first on repetitive, low-hanging tasks, preserving simpler issues for junior talent development. She notes that layoffs will degrade service quality unless leaders secure organizational buy-in, communicate resource impacts, and prioritize essential functions. Customer service teams must partner with product to prioritize requests that deliver the most value for the right target users, not fulfill every wish.
Turning the tide: CS expert Jo Causon on reviving customer satisfaction rates - The Intercom Blog
UK customer satisfaction scores have fallen to 2015 levels, the worst drop since the national index began in 2008. Jo Causon, CEO of the Institute of Customer Service, attributes the decline to a perfect storm of recruitment and retention difficulties alongside technology that has not yet delivered on its promises. She notes that organizations spend roughly 20% of their time rectifying problems they created, a massive inefficiency. To reverse the trend, Causon advises embedding a service culture across every department, understanding the full customer journey, and proactively eliminating pain points rather than just handling complaints. Data shows that a 1% rise in employee engagement yields nearly a 0.5% increase in customer satisfaction, reinforcing that customer service must be an organization-wide priority.
Why your non-root container dropped its capabilities (and how to fix it)
A platform engineer traces why a non-root OpenShift container configured with CAP_NET_RAW still fails ping with Operation not permitted. The root cause is that SCC is only an admission-time gate that does not enforce runtime privileges. CRI-O translates the PodSpec into an OCI spec with the capability in the Bounding, Effective, and Permitted sets but deliberately omits ambient capabilities. During the runtime’s UID transition from root to the target non-root user, the kernel clears both Permitted and Effective sets, leaving an empty CapEff. The only mechanism that survives a UID transition for non-root processes is ambient capabilities, which CRI-O intentionally avoids to preserve the Kubernetes assumption that switching to a non-root user drops capabilities. To resolve this, file capabilities can be applied directly to the binary via setcap, avoiding the need for ambient capabilities.
Powering AI-led research through simulation
Grab built sim-rs, a self-contained simulator that models its fulfillment marketplace to enable rapid experimentation with dispatch strategies. The simulator processes a city-day of marketplace activity in tens of minutes, using historical data and configurable components for batching, allocation, and cancellation. Agents connected through an autoresearch loop propose changes, run reproducible experiments, and receive computed verdicts, with safeguards against specification gaming such as immutable core data and scoped changes. The simulator also supports A/B/n comparisons within a single run, exposing all arms to the same demand and dynamics to improve translation to production. By making each attempt take minutes instead of weeks, sim-rs allows agents to test thousands of ideas cheaply and receive honest feedback, accelerating research while keeping the simulator faithful through automated translation of production logic and behavioral modeling.
How Genie One reshapes work for finance teams
Finance teams must interpret data to guide decisions, but answering follow-up questions often requires manual extraction and metric negotiation, delaying answers past leadership discussions. Genie One is a data-smart AI coworker grounded in business context such as approved metric definitions, fiscal periods, and entity rollups, using Genie Ontology to unify context. It supports workflows including budget variance analysis, cash flow forecasting, financial close management, and spend analytics, allowing plain-language queries like “Which entities have unreconciled intercompany balances above $100,000?” Users can review tables behind answers, schedule recurring reviews, and have results posted to chat with visualizations. Genie One respects each user’s existing permissions, so a corporate controller sees enterprise-wide items while a regional accountant sees only relevant entities.
How to choose your first Genie Agents for maximum impact
With over 1 million Genie Agents created in 2026, the challenge is selecting which to build first for maximum impact. The post presents a rubric scoring candidate workflows on five variables: business impact, demand frequency, data readiness, scope clarity, and governance risk. Scores of 20-25 indicate readiness to build, 14-19 need shaping, and under 14 suggest the workflow is not a good fit; an executive champion is essential regardless of score. Examples include a pension fund’s risk Q&A agent that scored high and saw quick adoption, and a wealth manager’s analytics agent that failed due to metadata gaps. The rubric helps avoid common pitfalls like the ‘everything agent’ and the ‘vanity demo’ by focusing on narrow scope and governed data.
In Capital Markets, the Buy Side Runs on NAV. Finance Protects the Fee.
Buy-side asset management finance departments face growing complexity from AI agents influencing valuation, redemption, and reconciliation workflows, while protecting net fee margin and NAV integrity remains their core mission. Databricks Genie One is presented as a data-smart AI coworker grounded in Genie Ontology, which captures business meaning and keeps definitions current as strategies and fee arrangements shift. Behind the assistant, Genie Agents automate overnight fund operations: ingesting custodian files, pricing positions, reconciling records, and producing a preliminary NAV for review. Every figure is traceable to its source, permissioned by role, and provable to investors or regulators, enabling finance teams to see forming risks early. The system does not make investment or valuation decisions; a human remains in the loop for every action.
Kube AuthKit: Unified Kubernetes and OpenShift auth in Python
Kube AuthKit is a lightweight Python library that unifies Kubernetes and OpenShift authentication behind a single API, eliminating conditional code paths across local, pod, notebook, and CI/CD environments. It supports four strategies—kubeconfig, in-cluster, OIDC, and OpenShift OAuth—auto-detected by an AuthFactory that probes environment variables and in-cluster markers in a defined order. The library handles token lifecycle transparently, with in-memory storage by default and optional OS keyring persistence for local development to avoid repeated logins. It provides two OIDC flows: device code for headless environments and authorization code with PKCE for interactive applications, both with automatic token refresh. Kube AuthKit returns a standard Kubernetes Python client ApiClient, ensuring full compatibility with the official library, and is actively maintained by the Open Data Hub community for OpenShift AI environments.
AutoSynthData: Generating Training Data for Enterprise Agents
AutoSynthData, built by ServiceNow CoreAI, generates training data for enterprise agents by targeting capability gaps from evaluation, using a stronger teacher such as Qwen3.8-27B to demonstrate successes. It uses a target model’s failures and a stronger teacher’s successes to decide what to learn next. The system produces tasks composing a system specification, user prompt, and verifier, ensuring feasibility, realism, and difficulty against the target environment. After sample-level checks and batch-level review, the dataset grows via target and multiply phases, generating 2,000 samples in 18 hours for the Hybrid domain. In EnterpriseOps Gym, synthetic SFT on Gemma-4-26B-A4B-it improved mean Pass@1 by 7.2 points (35% relative) in Hybrid and from 18.77% to 27.18% in ITSM, showing the approach works across domains.
Architecting Secure Identity: Extending Auth0 PrivateLink with Intelligent Gateways
Enterprises centralize authentication into a single Auth0 environment but must comply with frameworks like PCI-DSS, HIPAA, and SOC 2 that restrict data to private channels. Auth0 Outbound PrivateLink provides a secure unidirectional connection between Auth0 and AWS infrastructure, avoiding the public internet. However, a single PrivateLink connection per environment cannot directly reach multiple isolated VPCs for staging and production. The Intelligent Gateway Pattern solves this by deploying an API gateway or reverse proxy at the PrivateLink termination point to fan out traffic. Auth0 Actions append context such as custom headers like X-Target-Env or specific paths, and the gateway inspects these to route requests to the appropriate isolated VPC, decoupling secure transport from internal routing. This pattern unblocks identity consolidation by allowing a single Auth0 tenant to serve both staging and production workloads while maintaining strict VPC isolation.
Language Discrimination Improves Linguistic Learning in Multilingual Speech Models
Multilingual self-supervised speech models underperform monolingual models under a matched total pretraining data budget, but strengthening language discrimination during pretraining reduces this gap while preserving cross-language sharing. In a controlled English/French HuBERT setting, two interventions—an auxiliary language classifier and per-language k-means targets—improve language discrimination. Continuous-feature phone discrimination error (phone-ABX) decreased from 11.6% in the bilingual baseline to 10.4%, approaching the monolingual 10.8%. Lexical performance (sWUGGY) rose from 52.1% to 56.7% (monolingual: 58.5%), and prosodic performance (ProsAudit lexical subtask) from 68.9% to 72.9% (monolingual: 72.6%). The strongest gains occur when language discrimination is introduced in the first HuBERT iteration; later or repeated interventions yield smaller improvements and increase language-wise segregation, supporting a causal role for language discrimination in reducing the cost of multilingual learning.
Build Applications on NVIDIA BlueField Faster with NVIDIA DOCA Agent Skills
General-purpose AI agents lack domain-specific knowledge for NVIDIA DOCA development, often inventing APIs or skipping hardware checks, leading to correction cycles. DOCA AI agent skills provide a structured, machine-readable specification in a SKILL.md file containing verified API signatures, hardware capability requirements, and build constraints for components like Flow, GPUNetIO, and PCC. In a 65-prompt evaluation, agents without skills satisfied only 19% of graded checklist items, while agents with skills satisfied 100% across all prompts. The skills reduce correction cycles; in a side-by-side demo, the with-skills agent used 73% less handwritten code and 46% fewer hardware commands. The skills are available on GitHub and enable developers to build faster, ship more stable code, and deploy with fewer unknowns on BlueField infrastructure.
Accelerating airline retailing innovation: how Datalex modernized with AWS Experience-Based Acceleration and agentic AI
Datalex, a leader in airline ecommerce, needed to modernize its mature EJB2/Java 8 system for Modern Airline Retailing while maintaining continuous airline operations. Over three days, 16 Datalex engineers and 6 AWS specialists proved migration feasibility by extracting a Reservation service into a Spring Boot microservice on Java 21. The team used agentic AI tools—Kiro and AWS Transform Custom—to automate code changes, and established repeatable patterns for DevSecOps, observability, and a multi-agent AI prototype via Amazon Bedrock AgentCore. A business service proxy using the Strangler Fig pattern enabled incremental migration with backward compatibility. The board approved significant investment, the prototype team expanded into a full Agile team, and the EBA shortened discovery from an estimated 8–12 weeks to three days.
Graph-centric agentic intelligence
Graphs encode relationships and provide scaffolding for causal inference and compositional reasoning, which is essential for AI agents reasoning over complex networks. The post traces the evolution of graph intelligence from passive topology models to active agentic reasoning, culminating in a three-pillar approach for root cause analysis. The approach combines a continuously synchronized network digital twin graph with a cascaded pipeline of graph algorithms—decomposition, clustering, and centrality ranking—that narrow the search space. An agentic orchestration layer selects and composes these algorithms adaptively based on failure characteristics, performing complexity triage and consulting an incident knowledge base. The system achieved root cause analysis in minutes on commercial networks, demonstrated with NTT DOCOMO at MWC.
Top topics
- Architecture832
- Performance814
- LLMs658
- Machine Learning620
- Open Source563
- AI Agents549
- AI465
- Developer Experience448
Weekly digest
The best engineering reads, once a week.