InfoQ - AI Architecture

Yelp Combines Native and Server-Driven UI for its AI Assistant

Leela Kumili — Fri, 06 Nov 2026 14:25:00 GMT

Yelp combines native mobile controls with server-driven conversation rendering in its AI Assistant using the CHAOS framework. The architecture separates view configuration from conversation data, supports backend-driven chat interactions, and enables faster UI updates without new app releases. Yelp also discusses cross-platform challenges and reuse for its Biz Ask Anything pilot.

By Leela Kumili

Inkitt Builds a One-Shot PR Creator with Resumable Agent Orchestration

Leela Kumili — Wed, 04 Nov 2026 14:36:00 GMT

Inkitt built a one-shot pull request creator that automates small, low-risk code changes from task intake to draft PR creation. Its event-driven orchestrator persists workflow state, coordinates short-lived coding agent containers, bounds retries, and enforces permission restrictions while retaining human review and approval before changes can be merged.

By Leela Kumili

Presentation: Panel: Who Builds the Frontend Now? (And What Breaks When They Do)

Luca Mezzalira, James Hall, Danielle An, Ivan Zarea — Wed, 04 Nov 2026 11:00:00 GMT

The panelists explain how AI tools and vibe coding reshape frontend and mobile engineering. They share insights on evolving junior developer roles, managing AI-generated code review fatigue, designing systems for autonomous agents, enforcing architectural guardrails, and navigating economic shifts in open-source software sustainability.

By Luca Mezzalira, James Hall, Danielle An, Ivan Zarea

Article: Systemic Approach to Memory, Knowledge, and Context in Agentic AI Architectures

Adi Polak — Mon, 02 Nov 2026 11:00:00 GMT

The article argues that reliable agentic AI architecture depends on a context engine that selects, injects, compresses, and expires information before it reaches the model. It separates context, memory, and knowledge, and recommends tiered memory, curated knowledge, and token budgeting. It also covers common anti-patterns, such as context stuffing and stale data loops, with mitigations.

By Adi Polak

DoorDash Cuts Grocery Reorder Latency from 16 to 2 Seconds with AI Agents

Leela Kumili — Fri, 30 Oct 2026 13:31:00 GMT

DoorDash reduced grocery reorder latency from 16 to 2 seconds by precomputing recurring purchase needs using batch LLM inference and deterministic validation. Live catalog resolution keeps product selections current, while an editable shopping interface avoids unnecessary model calls. The company reports that shopping list views doubled and the flow’s order rate increased by approximately 34%

By Leela Kumili