Why Postgres ignored our full-text search index
HOAi's AI agents at HOAi experienced full-text search queries taking 3.2 seconds or more because Postgres ignored the GIN index and materialized a CTE, scanning all pages for an association. The fix w…
HOAi's AI agents at HOAi experienced full-text search queries taking 3.2 seconds or more because Postgres ignored the GIN index and materialized a CTE, scanning all pages for an association. The fix w…
Databricks Lakebase, a Postgres-compatible database with decoupled storage on lake storage, enables sub-second branching and ephemeral instances, making it suitable for agentic data projects that need…
At the 2026 Posette event, run by Microsoft's Postgres team, experts highlighted integrating Postgres with AI, including building Model Context Protocol servers for safe AI agent queries, and showcase…
An engineer who builds AI products argues that system design interview prep is now the only moat against AI in technical hiring, since AI can handle coding but cannot defend architectural decisions un…
A developer argues that vector stores are the wrong tool for analytical queries on agent memory, such as counting or grouping stored facts. The post explains that similarity search cannot compute aggr…
Ablo, an open-source project on GitHub, introduces an authoritative transaction layer for shared application state in AI applications, enforcing authority, idempotency, conflicts, ordering, and confir…
An engineer from Frihet, a company building an agent-native ERP, explains that agent-callable write operations must be idempotent to prevent data loss and duplicate records. The post details how agent…
Aulinq, a multi-tenant, multilingual AI agent platform, was built from scratch by a solo engineer using a team of AI agents for planning, implementation, review, and verification. The engineer, who ha…
Rls-guard, a new open-source tool, generates and audits Postgres/Supabase row-level security (RLS) policies from a YAML spec, addressing misconfigured RLS that exposed 303 endpoints across 170 apps in…
A developer who started coding in 2025, when AI could write most code, describes the challenge of learning when the machine provides working solutions. They argue that the real skill is choosing to un…
Aulinq, a multi-tenant, multilingual AI agent platform, is being built from scratch by a solo engineer using a team of AI agents for planning, implementation, review, and verification. The engineer, w…
Supabase, the Postgres development platform, is hiring a Staff AI Platform Engineer to build the execution layer for its internal AI systems, including an event-triggered queue, a model-agnostic runti…
QM, a multiplayer agent harness for work in Slack and on the web, is designed for startups, allowing each employee to have an isolated workspace while collaborating in channels and projects. The core …
A developer built a Perplexity-style web search agent using Bun, React 19, Tavily, OpenRouter, and Postgres, then critically evaluated whether it truly deserved the 'agent harness' label. The engineer…
Betocmn released Widen, an open-source (MIT) native Mac app built with Swift that serves as a Postgres GUI with text-to-SQL capabilities, supporting local or cloud LLMs via OpenRouter or Apple's on-de…
Abacus AI launched Supercomputer, an always-on Linux virtual machine in the cloud that hosts AI agents, apps, and games for $10, preloaded with over 100 AI models and one-click deployment for Hermes a…
ClickHouse released clickhousectl v0.4.0, adding horizontal autoscaling for Cloud services, ClickPipe schema discovery, finer control over ClickPipe ingestion, partial updates for Postgres configs, an…
A developer's RE-call memory system, which never calls an LLM, scores lower on temporal reasoning (0.408 vs. 0.567) than Mem0 on the BEAM benchmark, but avoids any LLM cost and keeps data in Postgres.…
A refined prompt forces large language models to generate secure internal tool scaffolds that include architectural outlines for isolation and auditability, according to a developer who tested it on a…
An engineer at an ISP built a WhatsApp billing assistant using Corrective RAG (CRAG) and found that the main challenge was not retrieval but the model narrating correct numbers incorrectly. The system…