HQ Paphos, Cyprus · worldwide
AI agent articles: development cost and process, trustworthy UX patterns and the trading-bot engineering behind Polymarket.
A trader asked us to rewrite his weather market maker in Rust. We measured the opportunity first — 256,000 order-book snapshots across 1,702 temperature buckets — and told him not to build it. What the reward economics actually look like, why the richest markets are the worst, and why we threw away our own positive result.
By Alexander Vinokurov
Every page of 99francs.agency is served as clean Markdown to any client that asks — same URL, one Accept header, about a tenth of the bytes. Here is the Next.js setup behind it: the proxy rewrite, the converter route, llms.txt — and the six-week bug that quietly served our homepage to every AI agent while every browser test passed.
By Alexander Vinokurov
What a production AI agent costs in New Zealand in 2026 — public NZ market benchmarks, realistic custom-build ranges, ongoing costs and a lower-risk way to pay only after each phase works.
By Alexander Vinokurov
How a market-making bot survives on a fast prediction market: the anti-pickoff logic behind a live Polymarket system — pre-signed cancels, event-reactive requoting, order-book imbalance guards and enforced post-only quoting, and how they fire together the instant the underlying moves.
By Alexander Vinokurov
Before a prediction-market trading strategy touches real money, we put it through backtests against real order-book depth and a staged ladder of simulation modes — inert, virtual, mirror, then a small real bring-up. Here is how the de-risking pipeline works, and why every promotion is gated by evidence rather than optimism.
By Alexander Vinokurov
A live market-making bot on the Polymarket prediction market was leaking money to a slow control loop. We kept the quant logic in Python and moved only the latency-critical execution path into a Rust sidecar — cutting the reaction time on the most expensive event from roughly two seconds to the low tens of milliseconds.
By Alexander Vinokurov
New Zealand's AI Advisory Pilot co-funds an AI plan for SMEs — what it actually covers, the gap between a funded plan and a working agent, and how outcome-based development removes the build risk.
By Alexander Vinokurov
How we design and build AI agents that survive production, not just the demo — feasibility proof, behavior prototypes, tested action maps, provider fallbacks, and an outcome-based model where you pay only when the agent works.
By Alexander Vinokurov
A field guide to designing AI agents people actually trust — six UX patterns for control, autonomy, uncertainty, memory, voice, and failure, each drawn from agents we have shipped.
By Alexander Vinokurov
