LinkedIn

2026-10-26

CODING · 1 SOURCE · InfoQ AI, ML & Data Engineering

InfoQ outlines evolution of agentic harnesses from chains to graphs to code

An InfoQ article summarizes three paradigms for building agentic harnesses around LLMs — chains (linear workflows), graphs (explicit control-flow with nodes/edges), and code (sandboxed, execution-first systems) — and argues the field has moved from ad‑hoc glue to production-grade, observable architectures. The piece highlights tradeoffs (latency, fragility, resilience) and recommends treating LLM outputs as untrusted, decoupling planning from execution, and investing in observability and minimal necessary abstractions.

6.0

2026-10-13

CODING · 1 SOURCE · InfoQ AI, ML & Data Engineering

QCon AI New York 2026 confirms sessions on production agents, evals, and LLM cost controls

QCon AI New York 2026 (Dec 15–16, The Westin Jersey City Newport) has published confirmed sessions from senior engineers covering production challenges for agents, evals, and LLM cost management. Speakers include Nancy Wang (identity/authorization for agents), Ronak Nathani (LinkedIn Kubernetes ops agent), Fabio Flores (DoorDash eval loop), Tejas Chopra (prompt compression and caching), Min Chen (AI-native code review at LinkedIn), and Nathen Harvey (AI maturity at Google Cloud).

5.0

2026-10-09

COMPANIES · 1 SOURCE · The Verge AI

Nikon disqualifies Small World in Motion winner after AI-assisted post‑processing admission

Nikon says the original first‑place video in its Small World in Motion contest was disqualified for violating rules on generative AI after Dr. Ning Xu admitted using an unsupervised neural‑network method for AI‑assisted post‑processing; the entry was removed and Nguyen Nam Nhat is now listed as first place. Nikon also said it will revisit competition rules and evaluation procedures for future entries.

6.0

2026-09-25

COMPANIES · 1 SOURCE · InfoQ AI, ML & Data Engineering

QCon AI New York 2026 highlights: agent authorization, ops agents, model serving, evaluation

QCon AI New York (Dec 15–16, 2026) has confirmed 23 sessions covering identity and authorization for autonomous agents (keynote by Nancy Wang, 1Password), guardrails for an operations agent on large-scale Kubernetes (LinkedIn), Netflix’s five‑year consolidation of its model‑serving platform, and post‑deployment evaluation and moderation platforms. The program frames AI engineering as systems engineering, focusing on bounded agent authority, observability, cost/latency trade‑offs, and continuous evaluation for production systems.

5.0

2026-09-19

COMPANIES · 1 SOURCE · InfoQ AI, ML & Data Engineering

LinkedIn builds Contextual Agent Playbooks — organizational context layer for AI agents using MCP

At QCon AI, LinkedIn engineer Ajay Prakash presented 'Contextual Agent Playbooks and Tools', an organizational context layer built on the Model Context Protocol (MCP) that supplies procedural memory, code search and runbooks directly to coding agents. LinkedIn says the system (used across hundreds of workflows) yields a 20% productivity boost with no loss in reliability and discussed its architecture and operational guardrails.

7.0

2026-09-16

COMPANIES · 1 SOURCE · xAI

Grok Bot launched for enterprises with access, network and audit controls

Grok Bot is now available for enterprise customers; Grok and Cursor Enterprise customers get free access for two weeks and can invite their whole organization. The release adds governance features — access, network, and audit controls — and describes Bots that run in isolated cloud environments, can use apps and websites, learn workflows, message each other, and handle end-to-end tasks across functions like sales, recruiting, marketing, finance, and engineering.

6.0

2026-09-11

MODELS · 1 SOURCE · InfoQ AI, ML & Data Engineering

LinkedIn trains AI job-search ranking 8× faster using multi-teacher distillation

LinkedIn published technical details of the training infrastructure for its AI-powered job search, describing a multi-teacher distillation pipeline that compresses knowledge from large teacher models into a compact 0.6‑billion-parameter ranking model. The company reports this approach yields up to an 8× speedup in training for the production ranking model. (Article by Claudio Masolo)

7.0