AI Agents
How AI agents are designed, orchestrated, measured and kept under human control: harnesses, instructions, costs and the interfaces people work in.
- 2026
AI Agents
The frontier runs on gas. Most office AI does not have to.
The FT reports Anthropic agreed to pay $3.4bn for 1.7 GW of gas generators. Our bet: much office AI can run on a small local model. Evidence for and against.
- 2026
AI Agents
“Don't do that”, “VERY IMPORTANT”, “Can you…?”: what the evidence says about negation, capitals and questions in prompts
Few studies test two phrasings of the same instruction inside an actual agent prompt. We reviewed the 2026 vendor guides, the papers and the field reports on negation, capital letters, repetition and the question form, and kept only what they state: where the evidence is strong, where it is thin, and which circulating figures we discarded.
- 2026
AI Agents
The augmented expert: agentic platforms must be built around people
AI still falls short of a professional on four expert projects in five, and the human's judgement is what turns an agent's report into a deliverable. A benchmark of eleven agentic platforms in October 2026 shows the same blind spot: built for one person, for developers or for processes, they rarely give people a shared space to review, correct and sign the agents' work. Junyr's approach starts from that space.
- 2026
AI Agents
Keywords for AI agents: what the evidence supports, and the ten we teach
Lists of trigger words for AI agents circulate with claims their sources do not make. We checked them against the papers and current vendor guidance, then set out the ten action and effort keywords Junyr teaches and where each word belongs: prompt, tool or harness.
- 2026
AI Agents
Why agentic projects don't (yet) have a positive ROI
Agentic projects rarely pay back today, less because of the technology than because companies copy their human processes and organisation charts onto generalist models. What taking over failed projects taught us, and a three-step path: equip people, imagine the company, then give agents objectives rather than tasks.
- 2026
AI Agents
Lean orchestration: five rules from the bill of a multi-agent run
On one multi-agent development run, 19% of the cost went to subagent caches that expired while tests ran, and 8% to starting new agents. Five rules on waiting, spawning, reading, reporting and orchestrating, with the prices and Claude Code settings behind each one.
- 2026
AI Agents
Harness engineering: the software layer that turns a model into an agent
What an agent harness is, what a source-code audit of eleven production systems actually found inside one, and which of the figures circulating about agent failure can be sourced.
- 2026
AI Agents
Agentic processes in business: where code, skills and judgement belong
A technical method for making an agentic process replayable: measure skill discovery, reserve judgement for useful steps and enforce controls in code.
- 2026
AI Agents
Cowork and durable agents: regaining control of dependencies
Cowork can support agent discovery and some production work, but durability depends on testing, contracts, controlled versions and a fallback plan.
- 2026
AI Agents
After chat: designing the AI work interface
Chat remains useful for exploration and exceptions, but durable processes need business context, controls and an interface fitted to the action.
- 2026
AI Agents
Deciding with your data: what agentic AI really changes
A practical method for framing, analysing and checking a decision with company data, while separating compute cost, integration cost and reliability.
- 2026
AI Agents
LLM context: sizing the window, KV cache and prompt caching
A technical guide to selecting useful context, calculating KV memory and comparing API caches without confusing compute, latency and billing.
- 2026
AI Agents
Engineering agentic systems: golden rules, architecture and security of the “Human-in-the-Loop”
HITL, HOTL and HOOTL: choosing the right supervision regime, enforcing executable limits and calibrating human escalation without mistaking statistical coverage for certainty.