https://mederic.me/blog Mederic Burlet ยท Blog 2026-07-16T00:00:00.000Z Mederic Burlet https://mederic.me Neurowire https://mederic.me/blog/scope-beats-autonomy Scope beats autonomy: a contrarian take on AI agents 2026-07-16T00:00:00.000Z 2026-07-16T00:00:00.000Z Mederic Burlet https://mederic.me Open-ended autonomous agents make great demos and poor production systems. Tightly scoped, observable, boring agents are what actually survive real workloads. https://mederic.me/blog/multi-agent-reasoning Multi-agent workflows a single engineer can reason about 2026-07-15T00:00:00.000Z 2026-07-15T00:00:00.000Z Mederic Burlet https://mederic.me A focused multi-agent system one engineer can reason about beats a sprawling one nobody trusts. Scope each agent, define tools explicitly, and observe everything. https://mederic.me/blog/measuring-ai-productivity An honest look at AI productivity claims, and how to measure 2-3x 2026-07-14T00:00:00.000Z 2026-07-14T00:00:00.000Z Mederic Burlet https://mederic.me A 2-3x productivity gain is real when you measure build success, cycle time, and effort reduction, not vanity metrics. Here is how to tell the difference. https://mederic.me/blog/evals-for-delivery-teams Evals for delivery teams: trusting AI output without re-checking every line 2026-07-13T00:00:00.000Z 2026-07-13T00:00:00.000Z Mederic Burlet https://mederic.me Trustworthy AI output comes from evals built into the real pipeline, not a benchmark: evaluate what matters, gate at the right point, and keep review habits that scale. https://mederic.me/blog/no-code-ai-workflow Build a tiny no-code AI workflow that saves you an hour a week 2026-07-12T10:30:00.000Z 2026-07-12T10:30:00.000Z Mederic Burlet https://mederic.me Chain a trigger, an AI step, and an action in a no-code tool like Zapier, Make, or n8n to automate one small repetitive task end to end, no programming needed. https://mederic.me/blog/make-yourself-unnecessary Make yourself unnecessary: what good advisory leaves behind 2026-07-12T00:00:00.000Z 2026-07-12T00:00:00.000Z Mederic Burlet https://mederic.me Good advisory leaves a team stronger, not dependent. Capability and judgement should stay with the team, through co-delivery, explicit reasoning, and grown champions. https://mederic.me/blog/make-a-song-with-suno Make a full song with AI in ten minutes using Suno 2026-07-11T10:30:00.000Z 2026-07-11T10:30:00.000Z Mederic Burlet https://mederic.me Describe the song you want, pick a style, generate a couple of takes, refine the parts you do not like, then export. Suno makes a full track in minutes. https://mederic.me/blog/predicting-ai-adoption What predicts whether an AI cohort actually sticks 2026-07-11T00:00:00.000Z 2026-07-11T00:00:00.000Z Mederic Burlet https://mederic.me Across 700+ practitioners, durable AI adoption tracks three predictors: training on their own codebase, role-specific tracks, and internal champions seeded in the team. https://mederic.me/blog/nano-banana-explained Nano Banana, explained: what Google's image model is good at 2026-07-10T10:30:00.000Z 2026-07-10T10:30:00.000Z Mederic Burlet https://mederic.me Nano Banana is the nickname for Google's Gemini image model, great at quick edits and keeping a subject consistent across pictures, with a few known limits. https://mederic.me/blog/sia-copilot-anatomy Singapore Airlines: a website feature in five weeks, down from nine 2026-07-10T00:00:00.000Z 2026-07-10T00:00:00.000Z Mederic Burlet https://mederic.me Embedding GitHub Copilot across Singapore Airlines' delivery lifecycle cut a feature from nine weeks to five, with 95% of the work AI-generated and effort down 60%. https://mederic.me/blog/local-vs-cloud-ai Local vs cloud AI: when to run models on your own machine 2026-07-09T10:30:00.000Z 2026-07-09T10:30:00.000Z Mederic Burlet https://mederic.me Run AI locally for privacy, no per-use cost, and offline use if you have decent hardware, or use cloud AI when you want the most capable models with zero setup. https://mederic.me/blog/three-training-tracks AI training needs a track per role, not one shared workshop 2026-07-09T00:00:00.000Z 2026-07-09T00:00:00.000Z Mederic Burlet https://mederic.me Engineers, leads, POs, QA, designers, and managers use AI for different work, so one shared workshop gives everyone half-relevant material. Role-specific tracks outperform it. https://mederic.me/blog/replicate-run-any-model Replicate: run almost any AI model without the setup 2026-07-08T10:30:00.000Z 2026-07-08T10:30:00.000Z Mederic Burlet https://mederic.me Replicate lets you run open AI models for images, audio, video, and text through a simple interface, with no GPU or environment to set up on your side. https://mederic.me/blog/demo-to-production-gap The demo-to-production gap is an organisational problem 2026-07-08T00:00:00.000Z 2026-07-08T00:00:00.000Z Mederic Burlet https://mederic.me A better model does not close the demo-to-production gap. The skills that win a pilot do not generalise, so architecture, guardrails, and behaviour change close it. https://mederic.me/blog/voice-cloning-elevenlabs Cloning a voice with ElevenLabs, responsibly 2026-07-07T10:30:00.000Z 2026-07-07T10:30:00.000Z Mederic Burlet https://mederic.me You can clone a voice with ElevenLabs in minutes, but only do it with a voice you own or have clear permission to use, never someone else's. https://mederic.me/blog/adoption-behaviour-change Adoption is a behaviour change, not a tooling rollout 2026-07-07T00:00:00.000Z 2026-07-07T00:00:00.000Z Mederic Burlet https://mederic.me Tools do not change behaviour, practice does. A launch plus a generic workshop spikes then fades, while role-specific practice and champions make adoption durable. https://mederic.me/blog/spotting-ai-slop How to spot AI slop and keep your own output good 2026-07-06T10:30:00.000Z 2026-07-06T10:30:00.000Z Mederic Burlet https://mederic.me AI slop is low-effort, generic text with vague filler, endless hedging, and no sources, and you avoid it by adding specifics, your own voice, and real editing. https://mederic.me/blog/prompting-is-editing Prompting is editing, not incantation 2026-07-06T10:30:00.000Z 2026-07-06T10:30:00.000Z Mederic Burlet https://mederic.me The real skill with AI is not finding magic words, it is giving feedback. Draft, say what is wrong, refine, repeat until the answer is right. https://mederic.me/blog/modern-prompting-no-roleplay Stop role-playing your prompts: what works on modern AI 2026-07-06T10:30:00.000Z 2026-07-06T10:30:00.000Z Mederic Burlet https://mederic.me You no longer need to tell modern AI it is a world-class expert or beg it to think step by step. Give it a clear goal, real context, and the format you want. https://mederic.me/blog/anatomy-of-a-good-prompt The anatomy of a good prompt, and three myths to drop 2026-07-06T10:30:00.000Z 2026-07-06T10:30:00.000Z Mederic Burlet https://mederic.me A good prompt is just five plain parts: a goal, real context, the output format, a few constraints, and an example or two. No magic words required. https://mederic.me/blog/ai-image-gen-replicate-nano-banana AI image generation, made simple: Replicate and Nano Banana 2026-07-06T01:49:17.000Z 2026-07-06T01:49:17.000Z Mederic Burlet https://mederic.me Want AI images without a powerful GPU? Use Nano Banana for quick photo edits, Replicate to try many models in your browser, and a LoRA for a repeatable style. https://mederic.me/blog/neurowire-taps-selectors Taps: turning feed-less websites into real feeds 2026-07-06T00:00:00.000Z 2026-07-06T00:00:00.000Z Mederic Burlet https://mederic.me Neurowire taps are per-host CSS-selector recipes that turn a plain HTML listing page into a real feed, so a site with no RSS becomes a first-class source. https://mederic.me/blog/never-paste-into-chatbot What you should never paste into a chatbot 2026-07-05T10:30:00.000Z 2026-07-05T10:30:00.000Z Mederic Burlet https://mederic.me Assume anything you paste into a chatbot may be stored or used for training, so never share passwords, secrets, other people's data, or confidential work. https://mederic.me/blog/dogfooding-neurowire-feeds Dogfooding @neurowire/core to power this blog's feeds 2026-07-05T00:00:00.000Z 2026-07-05T00:00:00.000Z Mederic Burlet https://mederic.me This site publishes its own Atom, JSON Feed, and NWF feeds from one canonical Neurowire model, because dogfooding your own library is the most honest test it gets. https://mederic.me/blog/understanding-loras Understanding LoRAs without the jargon 2026-07-04T10:30:00.000Z 2026-07-04T10:30:00.000Z Mederic Burlet https://mederic.me A LoRA is a small add-on file that teaches an image model one style, character or subject without retraining the whole thing, and you can stack a few. https://mederic.me/blog/nocturne-design-system Nocturne: an open-source Cyberpunk 2077 design system 2026-07-04T06:21:07.000Z 2026-07-04T06:21:07.000Z Mederic Burlet https://mederic.me Nocturne is an open-source design system inspired by Cyberpunk 2077 and Edgerunners: near-black surfaces, one hot neon accent, clipped corners, and machine-voice type, shipped as design tokens, framework-agnostic CSS, and React components. https://mederic.me/blog/building-neurowire Building Neurowire: one canonical model, six feed formats 2026-07-04T00:00:00.000Z 2026-07-04T00:00:00.000Z Mederic Burlet https://mederic.me Neurowire treats feeds as a data-modelling problem: one canonical model that every parser produces and every serializer reads, so adding a format is a single serializer. https://mederic.me/blog/everyday-ai-toolkit The everyday AI toolkit: Claude, Suno, ElevenLabs and friends 2026-07-03T10:30:00.000Z 2026-07-03T10:30:00.000Z Mederic Burlet https://mederic.me Match the job to the tool: Claude for writing and thinking, Suno for music, ElevenLabs for voice, and Replicate for running image models like Flux. https://mederic.me/blog/open-web-feeds The open web forgot about feeds, and that is worth fixing 2026-07-03T00:00:00.000Z 2026-07-03T00:00:00.000Z Mederic Burlet https://mederic.me Feeds let you publish once and let anything read it. As they eroded, following became an account on someone else's platform. Owning what you read is independence. https://mederic.me/blog/ai-for-your-day-10-wins AI for your actual day: ten small wins most people miss 2026-07-02T11:30:00.000Z 2026-07-02T11:30:00.000Z Mederic Burlet https://mederic.me AI is most useful for small daily tasks like drafting replies, summarising documents, planning trips, and tidying spreadsheets, not just for big flashy projects. https://mederic.me/blog/nwf-format-design Designing NWF: a feed format 62% smaller than JSON Feed 2026-07-02T10:30:00.000Z 2026-07-02T10:30:00.000Z Mederic Burlet https://mederic.me NWF is Neurowire's native feed format, roughly 62% smaller than the equivalent JSON Feed yet fully round-trippable, using interning, relative links, and date deltas. https://mederic.me/blog/fact-check-ai-answer How to fact-check an AI answer in 30 seconds 2026-07-01T13:00:00.000Z 2026-07-01T13:00:00.000Z Mederic Burlet https://mederic.me Open the cited source and check it actually says what the AI claims, then cross-check one independent source, paying closest attention to numbers, dates, and names. https://mederic.me/blog/unremarkable-workflow Why I optimise for the unremarkable workflow, not the wow demo 2026-07-01T10:00:00.000Z 2026-07-01T10:00:00.000Z Mederic Burlet https://mederic.me A hundred engineers using AI by default beats one jaw-dropping demo. Production compounds on the thousandth unremarkable run, so measure throughput, not wow. https://mederic.me/blog/neurowire-taps-pack Neurowire Taps Pack: 271 curated sources, 24 themes 2026-06-29T00:00:00.000Z 2026-06-29T00:00:00.000Z Mederic Burlet https://mederic.me The Taps Pack is a ready-made library of 271 vetted sources for Neurowire, grouped into 24 themes from Frontier AI Labs to Food. It's the curation layer ahead of the upcoming Neurowire SaaS. https://mederic.me/blog/neurowire-docs-launch Neurowire: an open feed engine, now with full docs 2026-06-28T00:00:00.000Z 2026-06-28T00:00:00.000Z Mederic Burlet https://mederic.me Neurowire turns any source, even feed-less websites, into one canonical feed you can serialize to Atom, JSON Feed, Markdown, RSS, or its own compact NWF format. The full documentation site is now live. https://mederic.me/blog/why-ai-pilots-stall Why AI pilots stall before production 2026-06-25T00:00:00.000Z 2026-06-20T00:00:00.000Z Mederic Burlet https://mederic.me AI pilots stall because they optimise for a demo, not for adoption. Production requires architecture, guardrails, and a change in how teams work, not a better model. https://mederic.me/blog/700-engineers-on-adoption What 700 trained engineers taught me about adoption 2026-05-12T00:00:00.000Z 2026-05-12T00:00:00.000Z Mederic Burlet https://mederic.me After training 700+ practitioners, the pattern is clear: adoption is a behaviour change, not a tooling rollout. Role-specific practice and internal champions are what make it stick.