Analysis
217 articles
Analysis and opinion on where AI is going and what it means for a business that has to make decisions now.
Latest
Showing 1 to 20 of 217
The super-agent architecture: what DeepSeek's blueprint means for your business
A business field guide to DeepSeek's super-agent architecture: router and worker layers, event-driven proactivity, full-duplex interaction, durable state, the watchdog, the published evidence, the security gap, and a 90-day build sequence.
DeepSeek Harness: Build Custom Business Agents Without Vendor Lock-in
DeepSeek released Harness, an MIT-licensed open-source agent runtime, challenging proprietary platforms like Claude Code and OpenAI Agents. This post explores what Harness is, why it matters now, and how enterprises can leverage it for custom agent workflows without vendor lock-in.
How Do You Test An AI Agent Before It Touches A Live Business Workflow?
Agents cannot be tested like software. Build an eval set from real work, sandbox the tools, shadow the queue, graduate autonomy, then turn failures into regression tests.
What Actually Makes A Local LLM Fast, And When Does On-Prem Beat The Cloud?
Bandwidth sets single-stream speed, quantization decides what fits, and utilisation decides whether on-prem beats per-token pricing. The arithmetic, without hype.
Does Your Local AI Really Stay Offline, And How Would You Prove It?
Local means the model runs on your hardware, not that nothing leaves. Six leak paths, the settings to turn off, and the cable test that produces evidence.
Who Is Accountable When Your AI Agent Makes A Costly Mistake?
76% of organisations defined accountability for AI agents, yet 45% had incidents where responsibility was unclear. What accountability requires beyond a policy.
Is MCP The New Enterprise Integration Layer, And Should Your Business Care?
ADP and Precisely shipped MCP servers this month. MCP standardises integration but not permissions. Where the security boundary sits, and what to build first.
Why Does Your AI Agent Keep Forgetting, And What Is That Costing You?
An agent has a context window, not a memory. Unbounded transcript replay causes drift and memory poisoning. Here is what to store, what to expire and how to test it.
What Does Real AI Agent ROI Look Like, Beyond The Vendor Case Study?
Real agent ROI is measured in one unit of work: volume, touch time, rework and cycle time. Here is a defensible calculation and the costs most cases leave out.
Should Your AI Agent Harness Be Open Source, Or Locked To One Vendor?
Vendor lock-in rarely lives in the model. It hides in memory, tool schemas, sandboxes and eval data. Five checks tell you whether you can actually leave.
Your AI Agent Has Employee-Level Access, So Who Is Watching What It Does?
An agent with employee-level access is an insider-risk problem, not a model problem. Scope every agent like a new starter: identity, least privilege, gates and expiry.
Can You Run AI Agents Fully On-Premises Without Handing Your Data To A Cloud Vendor?
Oxide's VM-per-session pattern makes self-hosted agents practical, Ollama shipped local speech, and our two DGX Sparks sustain 35 tokens a second.
LangChain's Open-Source Design Agent: What It Takes to Make AI Look On-Brand
LangChain open-sourced Content Studio, the Slack design agent behind 3,000+ assets. What the harness gets right, what a request costs, and whether to self-host.
How Granola Grew AI Search Users 4,600%: The AEO Playbook Explained
The full breakdown of Granola's 4,600% AI search growth: how the AEO system works and how to run it.
What Is Google's SLEEP Framework? LLM Memory Consolidation Explained
Google's SLEEP framework lets a deployed LLM fold new knowledge into its weights without catastrophic forgetting. How consolidation and dreaming work, what the benchmarks show, and what is still unproven.
Claude for Legal Artifacts: What the Gallery Does and What It Cannot Do
Anthropic's Claude for Legal gallery ships 19 ready-made artifacts and 60+ connectors. What they do, where privilege, verification and confidentiality bite, what the Legal Agent Benchmark really says, and how the same pattern runs on open-weight models inside your own environment.
Liquid AI LFM3: Why A 1.7B Model Is Now A Business Option
Liquid AI's LFM3 family puts six specialised models on one 2B backbone, and the text model runs in about 1 GB at 4-bit. Here is what the benchmarks actually show, where a small model beats a frontier model on cost and custody, and the four conditions where on-device AI pays for itself.
MiniCPM-OCR 1.0: A Free 3.5B Pair That Reads Messy Scans And Flags Its Own Mistakes
OpenBMB's MiniCPM-OCR 1.0 is a 1.3B open-weight parser that leads real-world document benchmarks, and Jev is a 2B checker that scores every region so you know exactly what a human must review. What the numbers actually say, where the launch claims overreach, and how to run the pair on your own hardware.
Local AI vs Subscriptions: What 25 Seats Really Cost in 2026
At 25 seats, cloud AI subscriptions cost $6,000 to $9,000 a year before API usage. A 128GB DGX Spark lists at $6,950 and pays back in about 15 months. Where local wins, where cloud still wins, and the hybrid routing pattern that works in practice.
Lovable Moved 70 Million AI-Built Apps Off Next.js: What the 98.5% Lift Means
Lovable migrated 910,000 lines from Next.js to TanStack Start on Cloudflare Workers and now runs 70 million AI-built apps. Inside the numbers, how TanStack Start actually works, the 11-minute outage, and the 98.5% jump in AI-tool traffic that came from pre-rendering alone.
What's actually useful in AI, every Friday
We follow everything happening in AI and send what's worth your time: new models, AI agents, and how to put them to work. One email a week, unsubscribe anytime.