blog

Notes on AI, delivery, and adoption.

Answer-first essays on getting AI from pilot to production: architecture, enablement, and the agentic systems behind it.

Topics: everyday-ai (19) open-source (11) enablement (8) ai-adoption (7) feeds (7) tools (7) research (4) architecture (3) fsi (3) image-gen (3) productivity (3) prompting (3) quality (3) agents (2) mcp (2)
Latest

How to spot AI writing before you hit send

A quick, non-technical checklist for catching the giveaway signs of AI-written text in your own drafts: the vocabulary, the lists of three, the flat rhythm, the long dash, and the too-neat ending.

2 min read
everyday-ai quality
Read article
02
3 min read

Langdrift: scoring how differently a translation lands

Langdrift compares audio of an original and its translation and returns a drift score: how far apart the two land cognitively, catching accurate but off translations.

open-source research translation
Read
03
3 min read

Why 'make it sound human' never quite works

AI writing gives itself away on three levels: the characters, the words, and the shape of the whole piece. The deepest one is decided while the text is being written, which is why a clean-up pass at the end cannot fully fix it.

everyday-ai tools
Read
04
5 min read

Verso: one JSON source, decks branched per audience

Verso defines presentations as JSON instead of slide documents, so one source can branch per audience and export to PDF, HTML, or PNG cleanly.

open-source presentations
Read
05
5 min read

AI writing has a tell. I built a free tool that removes it.

Ghostwriter is a free, open-source tool that makes AI-written text read like a person wrote it, by removing the hidden characters, the giveaway words, and the report-shaped structure that flag it as machine-made.

everyday-ai tools
Read
06
4 min read

Petrify: removing people from footage, entirely on-device

Petrify detects and removes people from fixed-camera footage while keeping the live timestamp ticking, running fully on your own machine with no cloud upload.

open-source computer-vision
Read
07
3 min read

Scope beats autonomy: a contrarian take on AI agents

Open-ended autonomous agents make great demos and poor production systems. Tightly scoped, observable, boring agents are what actually survive real workloads.

agents mcp
Read
08
3 min read

Multi-agent workflows a single engineer can reason about

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.

agents mcp architecture
Read
09
3 min read

An honest look at AI productivity claims, and how to measure 2-3x

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.

research productivity fsi
Read
10
4 min read

Evals for delivery teams: trusting AI output without re-checking every line

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.

research enablement architecture
Read
11
3 min read

Build a tiny no-code AI workflow that saves you an hour a week

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.

everyday-ai productivity
Read
12
3 min read

Make yourself unnecessary: what good advisory leaves behind

Good advisory leaves a team stronger, not dependent. Capability and judgement should stay with the team, through co-delivery, explicit reasoning, and grown champions.

enablement
Read
13
4 min read

Make a full song with AI in ten minutes using Suno

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.

everyday-ai tools music
Read
14
6 min read

What predicts whether an AI cohort actually sticks

Across 700+ practitioners, durable AI adoption tracks three predictors: training on their own codebase, role-specific tracks, and internal champions seeded in the team.

ai-adoption enablement research
Read
15
6 min read

Nano Banana, explained: what Google's image model is good at

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.

everyday-ai image-gen
Read
16
3 min read

Singapore Airlines: a website feature in five weeks, down from nine

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%.

copilot fsi ai-adoption
Read
17
3 min read

Local vs cloud AI: when to run models on your own machine

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.

everyday-ai tools
Read
18
5 min read

AI training needs a track per role, not one shared workshop

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.

enablement fsi
Read
19
4 min read

Replicate: run almost any AI model without the setup

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.

everyday-ai tools
Read
20
4 min read

The demo-to-production gap is an organisational problem

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.

ai-adoption
Read
21
4 min read

Cloning a voice with ElevenLabs, responsibly

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.

everyday-ai tools voice
Read
22
3 min read

Adoption is a behaviour change, not a tooling rollout

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.

ai-adoption enablement
Read
23
3 min read

How to spot AI slop and keep your own output good

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.

everyday-ai quality
Read
24
3 min read

Prompting is editing, not incantation

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.

everyday-ai prompting
Read
25
4 min read

Stop role-playing your prompts: what works on modern AI

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.

everyday-ai prompting
Read
26
4 min read

The anatomy of a good prompt, and three myths to drop

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.

everyday-ai prompting
Read
27
6 min read

AI image generation, made simple: Replicate and Nano Banana

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.

everyday-ai image-gen
Read
28
3 min read

Taps: turning feed-less websites into real feeds

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.

open-source feeds
Read
29
3 min read

What you should never paste into a chatbot

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.

everyday-ai privacy
Read
30
3 min read

Dogfooding @neurowire/core to power this blog's feeds

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.

open-source feeds
Read
31
4 min read

Understanding LoRAs without the jargon

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.

everyday-ai image-gen
Read
32
4 min read

Nocturne: an open-source Cyberpunk 2077 design system

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.

open-source design-systems
Read
33
5 min read

Building Neurowire: one canonical model, six feed formats

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.

open-source feeds architecture
Read
34
3 min read

The everyday AI toolkit: Claude, Suno, ElevenLabs and friends

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.

everyday-ai tools
Read
35
3 min read

The open web forgot about feeds, and that is worth fixing

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.

feeds open-source
Read
36
4 min read

AI for your actual day: ten small wins most people miss

AI is most useful for small daily tasks like drafting replies, summarising documents, planning trips, and tidying spreadsheets, not just for big flashy projects.

everyday-ai productivity
Read
37
5 min read

Designing NWF: a feed format 62% smaller than JSON Feed

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.

open-source feeds
Read
38
3 min read

How to fact-check an AI answer in 30 seconds

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.

everyday-ai quality
Read
39
4 min read

Why I optimise for the unremarkable workflow, not the wow demo

A hundred engineers using AI by default beats one jaw-dropping demo. Production compounds on the thousandth unremarkable run, so measure throughput, not wow.

ai-adoption enablement
Read
40
2 min read

Neurowire Taps Pack: 271 curated sources, 24 themes

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.

open-source feeds
Read
41
3 min read

Neurowire: an open feed engine, now with full docs

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.

open-source feeds
Read
42
1 min read

Why AI pilots stall before production

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.

ai-adoption enablement
Read
43
1 min read

What 700 trained engineers taught me about adoption

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.

enablement ai-adoption
Read