Loading…
AI Agents
120 posts about AI Agents. Every summary links to the original.
How leading tech companies are killing the builder's tax with Lakebase
The post argues that AI-native applications face a “builder’s tax” because operational databases and lakehouse analytics are separated by CDC, ETL/ELT, and reverse ETL pipelines. This architecture can leave AI systems with stale data while duplicating governance and shifting engineering effort toward orchestration and failure management. It presents Lakebase, a fully managed serverless Postgres engine integrated with the Databricks Data + AI Platform, as a shared operational foundation where applications, agents, analytics, and governance use the same data. The proposed pattern combines a lakehouse intelligence layer, a low-latency Lakebase execution layer, and a continuous learning loop, with pgvector supporting agent memory and semantic search. Reported customer examples include faster feature onboarding, reduced on-call disruption, higher agent throughput, and consolidated data estates, though the results vary by organization.
Amey Banarse, Madelyn MullenInside one of the first production deployments of Lakebase: LangGuard's agentic workflow governance engine
LangGuard is presented as a runtime enforcement layer for enterprise agentic workflows, monitoring actions, decisions, tools, credentials, and intent across connected systems. Its GRAIL data fabric records multidimensional trace data, builds a live knowledge graph, and evaluates allow/deny/modify decisions against policy before tools, datasets, or models are accessed. The deployment uses Databricks Lakebase as the operational system of record, relying on PostgreSQL, serverless autoscaling, scale-to-zero, compute-storage disaggregation, hot-data caching, and copy-on-write branching for policy testing. LangGuard chose this architecture to handle bursty trace writes and low-latency enforcement reads without provisioning for peak demand, while keeping operational data available to Databricks analytics and AI capabilities without additional ETL. The stated next step is predictive governance: training behavioral models on historical traces to flag anomalous agent behavior before a policy violation.
Venkat Raghavan, Jason Keirstead, Ravi Srinivasan, Nina Williams, Amelia WestbergDatabricks partners with OpenAI on GPT-5.5
Databricks announces a partnership with OpenAI around GPT-5.5, described as OpenAI’s strongest frontier model for enterprise agentic work, complex document reasoning, and long-horizon coding agents. The model powers Codex and is presented as able to research, analyze data, create documents and spreadsheets, operate software, use tools, check outputs, recover from ambiguity, and continue through multi-part tasks. Databricks evaluated it on OfficeQA, a benchmark built from 89,000 pages of U.S. Treasury Bulletins that tests document retrieval, table interpretation, and precise calculation. With retrieval handled, GPT-5.5 scored 64.66% versus GPT-5.4’s 57.14%; in the full-agent OfficeQA Pro Agent Harness, it scored 52.63% versus 36.10%, representing reported improvements of roughly 13% and a 46% reduction in errors.
Hanlin Tang, Ahmed Bilal, Arnav Singhvi, Ivan Zhou, Harish GaurReal-Time Decisioning for AI Agents: Why you Need a Customer Context Layer First
Real-time decisioning for AI agents depends on more than customer records: it requires a customer context layer that captures what people are doing now and connects that behavior to identity. The post positions the data platform as the center of a composable martech architecture, with agents and applications operating on shared data in open formats such as Apache Iceberg and Delta Lake. Snowplow’s described approach places structured event collection, schema validation, enrichment, and identity resolution before data reaches the platform, while operating in the customer’s cloud environment. It distinguishes historical profiles from granular behavioral event streams and argues that agent interaction outcomes should return to the foundation as first-class events. The resulting four-stage loop—collect, resolve and enrich, serve, and learn—supports simultaneous real-time and historical context, with decision quality dependent on source data coherence.
Alex DeanLLM apps: Real-world use cases, core building blocks and risks to know
LLM applications are presented as production systems that extend beyond chatbots by connecting foundation models to external data, tools, APIs, memory and workflows. Modern categories include assistants and copilots, retrieval-augmented generation (RAG), autonomous agents, multi-agent systems and local or on-device inference, each with distinct capabilities and trade-offs. A typical RAG pipeline uses vector search over a curated knowledge base, then supplies retrieved passages to the model; chunking, source freshness and retrieval accuracy affect results. Production systems also require orchestration, evaluation, observability, governance, guardrails, audit trails and human-in-the-loop checkpoints, especially when agents can call tools or execute workflows. The source distinguishes prompt engineering, which guides behavior without changing model weights, from fine-tuning, which adapts models to domain-specific tasks, and describes a unified path combining data, models, retrieval, orchestration, evaluation and governance for production deployment.
Databricks StaffBridging data science and marketing: Databricks unveils Delta Sharing integration for Adobe Experience Platform and agentic marketing workflows
Databricks and Adobe announce three partnership milestones aimed at connecting governed Lakehouse data with marketing activation in Adobe Experience Platform. The changes include Delta Sharing support for zero-copy access, a Databricks Genie connection to Adobe Marketing Agent through Model Context Protocol (MCP), and an upcoming Adobe Marketing Agent beta for the Databricks Marketplace. Using Unity Catalog as the source, Experience Platform can access shared tables and views as virtual tables, while Adobe Data Distiller queries live Databricks data without copying underlying records. Through MCP, agents in both platforms can use governed datasets, metadata, models, campaign metrics, SQL Warehouses, and Model Serving endpoints with natural-language interactions. The stated outcome is a shared, real-time context for audience creation, campaign analysis, closed-loop attribution, and model improvement, while reducing data movement, duplication, latency, egress, and governance overhead.
Justin Fenton, Dan Zuckerberg, Katy YuanGet hands-on with agents, vibe coding and more at Data+ AI Summit
Data + AI Summit returns to San Francisco from June 14 through June 18, 2026, with Databricks Training and Certification offering more than 20 hands-on courses across AI agents, vibe coding, data engineering, and Lakebase. Training-exclusive days on Sunday and Monday are designed to provide dedicated learning time, while sessions continue during the conference week. New courses cover agentic development with Genie Code, Claude Code, Cursor, MCP servers, and structured prompting; production agent deployment with MLflow’s ResponsesAgent framework and tracing; Lakeflow Spark Declarative Pipelines; and AI/BI dashboards and Genie Spaces. Onsite certification exams cost $100 plus taxes, a 50% discount, and seven listed exams are available. The Learning Hub adds labs, skills assessments, customized learning plans, and community access.
Pratyarth RaoIntroducing Genie Agent Mode
Databricks introduces Agent mode in Genie spaces, an agentic process that plans, explores, and reasons over data to answer business questions. For each question, Genie can confirm an issue, test potential contributors through multiple queries, reflect on results, and decide what to investigate next, using Unity Catalog metadata and author-defined semantics from the Genie space. It produces a findings report with quantified results, identified contributors, visualizations, and references to the underlying SQL, and may include actionable recommendations. The agent scales its reasoning to task complexity, using validation for straightforward questions and more planning for multi-step investigations; in AI/BI Dashboards, Genie uses Agent mode by default. Workspace admins enable the feature in Workspace Previews, after which users turn on the Agent toggle in Genie spaces; API support and unstructured document analysis are planned additions.
Hanlin SunGoverning coding agent sprawl with Unity AI Gateway
Databricks introduces coding agent support in Unity AI Gateway to address security, cost, and visibility challenges created by organizations using multiple coding tools. The gateway provides a unified governance hub for Codex, Cursor, and Gemini CLI, combining access controls, usage statistics, operational observability, cost management, guardrails, and inference capacity. Agent access can be governed centrally, with audit logs in Unity Catalog, MCP servers managed in Databricks, MLflow tracing, shared cost limits, and coding metrics and traces ingested into Unity Catalog-managed Delta tables through OpenTelemetry. The announcement says developers can authenticate with Databricks credentials across connected services, use centralized budgets and model capacity, and let organizations analyze adoption, developer velocity, and rate-limit pressure in the lakehouse; support for Cursor, Gemini CLI, and Codex CLI is available to all Databricks customers.
Aarushi Shah, Ankit Mathur, Bilal, Kevin Stumpf, Rohit Agrawal, Harish Gaur, Ana NietoWhy your agents can't read enterprise documents — and how to fix it
Enterprise agents often reason well over clean text but struggle with scanned PDFs, inconsistent layouts, nested tables, images, and handwriting, making document processing an accuracy ceiling for business workflows. The post announces Document Intelligence, a pipeline of chainable AI Functions: ai_parse_document converts scans into layout-enriched structured text, while ai_classify and ai_extract support routing and entity extraction. On OfficeQA treasury-bond documents, preprocessing with ai_parse_document produced a 16% average performance gain across tested agent frameworks without changing their reasoning harness. Across invoice, contract, medical-note, and financial-filing extraction tasks, it reportedly delivered the highest accuracy at 5–7x lower cost than comparable pipelines, with serverless batch infrastructure scaling the same SQL call from 100 to 100,000. Databricks integrates ingestion, orchestration, governance, and agent building through Lakeflow Connect, Lakeflow Jobs or Spark Declarative Pipelines, Unity Catalog, and Agent Bricks, aiming to replace fragmented services with reusable workflows.
Archika Dogra, Sergei Tsarev, Erich ElsenAgentic reasoning in practice: Making sense of structured and unstructured data
Enterprise questions that connect structured records with unstructured text are difficult for single-turn retrieval systems to answer reliably. The post evaluates Databricks Agent Bricks Supervisor Agent (SA), a declarative agent builder built on the internal aroll framework, across STaRK’s Amazon, MAG, and Prime domains and six KARLBench tasks. SA decomposes questions, routes sub-questions to Genie or Knowledge Assistant, combines results, and can reformulate queries or use SQL JOINs when initial retrieval is incomplete. It outperforms rerun SoTA baselines by 4% on STaRK-Amazon, 21% on MAG, and 38% on Prime, while delivering a 23% improvement on FinanceBench and consistent gains across KARLBench; the authors attribute the results to multi-step tool selection, reflection, and precise instructions rather than custom code.
The Databricks AI Research TeamAgent 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.
Kasey UhlenhuthRamp ·
We proactively fixed ~100 security issues in 6 days with 0 humans
Ramp Security Engineering describes a six-day experiment in which home-grown agents found, validated, and fixed nearly 100 latent backend security issues, including some high-severity findings, without human involvement until pull-request review. The issues had not been uncovered by penetration testing, bug bounty testing, static analysis, or trials of 10+ code-scanning vendors, and all were patched within a week of discovery. The pipeline used specialized vulnerability detectors, adversarial manager agents that rejected 40% of initial proposals in sample testing, integration tests for validation, and an internal coding agent that generated patches. Live interactive validation struggled with complex preconditions, so test-based validation became the main approach; a human team member still reviewed and landed each pull request.
Eli BlockRamp ·
Why We Built Our Own Background Agent
Ramp built Inspect, a hosted background coding agent that writes code and verifies its work using the context and tools available to engineers. For backend tasks it can run tests, inspect telemetry, and query feature flags, while frontend work can be checked visually with screenshots and live previews. Each session runs in a sandboxed Modal VM initialized from repository-specific images and snapshots, with integrations including GitHub, Slack, Sentry, Datadog, LaunchDarkly, Braintrust, and Buildkite. Inspect supports frontier models, MCPs, custom tools, and skills, and provides Slack, web, Chrome extension, pull request, and browser-based VS Code workflows whose changes remain synchronized. Ramp reports that about 30% of merged pull requests in its frontend and backend repositories are written by Inspect.
Zach Bruggeman, Jason Quense, Rahul SengottuveluGrab ·
SpellVault’s evolution: Beyond LLM apps, towards the agentic future
SpellVault began as Grab’s no-code platform for building LLM apps, using Retrieval-Augmented Generation (RAG) and plugins to connect applications with knowledge sources and external systems. Users could ground responses in Wikis, Google Docs, text, and PDFs, invoke custom HTTP endpoints, and access apps through the web, Slack, or APIs. The platform later added citations, Python execution for mathematical problems, scheduled actions, and drag-and-drop Workflows combining LLM calls, code, and Knowledge Vault lookups, while its executor moved toward graphs with nodes, edges, and states. SpellVault now exposes apps and RAG through MCP, allowing external agents and compatible clients to invoke apps and search, retrieve, or add Knowledge Vault information; TinyMCP adds MCP capabilities to FastAPI as a router.
Felix Haryanto LieRamp ·
Automation, Squared
The article presents “second-order automation,” in which one agent designs reusable workflows for another agent to execute. Its spreadsheet system pairs an “architect” that watches a screen recording, generates detailed prompts, identifies required files and context, with a “doer” that searches workbooks and performs the instructions. The design addresses first-order automation’s dependence on users to supply precise prompts and fresh context for every task, which limits scalability. On an approximately 50-task SpreadsheetBench subset, the spreadsheet agent reached 49.5% accuracy on soft-restriction tasks versus OpenAI’s 45.5%, and 32.5% on hard-restriction tasks versus GPT-4o’s 13.4%; some one-to-two-hour tasks finished in under 10 minutes. The article concludes that recorded workflows can let non-technical users create reusable automations with little additional input, although architect performance has not yet been formally benchmarked.
Hunter PruettRamp ·
How To Build Agents Users Can Trust
Ramp describes how it built and shipped LLM-backed agents for expense management, focusing on the trust risks created by low-quality or unexpected finance outputs. It recommends choosing ambiguous, high-volume problems with asymmetric upside, then combining reasoning and citations grounded in product or user-provided context with an explicit “Needs review” path when the agent is unsure. The policy agent uses expense policies to approve, reject, or escalate expenses, while deterministic rules such as dollar limits, vendor blocklists, and category restrictions constrain autonomy. Ramp reports that more than 65% of approvals are fully handled by the agent, while users can progressively move from suggestions to autonomous actions through workflow-based controls and evaluation.
CJ Enright, Will Koh, Felix ZhangRamp ·
How Ramp Fixes Merchant Matches with AI
Ramp describes the difficulty of mapping payment-processor card acceptor data to useful merchant records when names, MCCs, and locations are vague, misleading, or affected by rebranding. Users can submit a replacement merchant name, website, and category, but deciding whether the request is legitimate and whether to update an existing record or create one requires additional context from related receipts, extracted line items, and transaction memos. Ramp addresses this with an AI agent built around an LLM, embeddings, rapid online analytical processing queries, multimodal retrieval-augmented generation, and guardrails that constrain permitted changes. The agent handles requests in under 10 seconds, and monitoring indicates it improves nearly 99% of transaction classifications, while fewer than 10% receive a second correction request. The same flow has also been extended to batch remapping and credit-card statement matching.
Chami Lamelas, Anton BiryukovGrab ·
Streamlining RiskOps with the SOP agent framework
Risk Operations teams investigating Account Takeover (ATO) cases must gather data across systems, run SQL queries, and make decisions under pressure, creating delays and error risk. The SOP-driven LLM agent framework represents the workflow as a natural-language, indentation-based tree whose steps specify queries, external functions, and decision criteria. During execution, the SOP planner navigates the tree and produces JSON-formatted instructions, while a Worker Agent invokes APIs or SQL queries and stores results in a feedback loop. The process ends by synthesising investigation data into a report and final decision. In reported results, handling time fell from 22 to 3 minutes per ticket, 87% of ATO cases were automated since launch, and the error rate was zero.
Fujiao LiuGrab ·
Introducing the SOP-driven LLM agent frameworks
Grab introduces an LLM agent framework that uses Standard Operating Procedures (SOPs) to guide enterprise automation and improve consistency in complex processes. It represents SOPs as trees of action and decision nodes, while a planner uses Depth-First Search, prompt generation, and backtracking to direct an LLM-powered worker agent; context compression and limited APIs are used to address hallucination and efficiency concerns. An SOP editor, plugins for APIs, Python, and SQL, workflows, a GRAG pipeline, playground, multilingual user agent, and state stack extend the framework’s capabilities. Reported evaluations include over 99.8% accuracy, an Account Takeover Investigations bot automating 87% of cases and reducing investigation time from 23 minutes to three, and fraud investigations cutting AHT by 45% and saving over 300 man-hours monthly.
Fujiao Liu
