This is the next instalment in both the StyloAgent and GEPA article series. It continues The StyloAgent Workflow, Part 2 and Evolving Decision Policies with GEPA and Decision Models, bringing...
Monday, 19 October 2026 16:00
//
11 minute read
In the previous part, we checked whether generated prose contains an answer and whether evidence supports its claims. We kept those checks separate from whether the answer reads well.
Now suppose...
Thursday, 15 October 2026 12:00
//
13 minute read
How do we check that generated prose contains the right information, rather than merely sounding like a good answer?
Ask an agent for a refund status when the authoritative tool says pending. “Your...
Wednesday, 14 October 2026 09:00
//
18 minute read
lucidRESUME needs to turn one complete career transcript into distinct, credible résumés. Select an applied-AI job: foreground agent architecture, evaluation and tool controls. Select a database job:...
Tuesday, 13 October 2026 23:00
//
9 minute read
The first form extracts perfectly. Then the address moves, the label changes, or the next document calls it something else. We add another rule. This series explores how to retain what those...
Saturday, 10 October 2026 12:00
//
20 minute read
In Part 1, I suggested a fairly simple approach to interviewing developers: prepare properly, make the process clear, and let candidates discuss code they understand. Then explore the decisions behind...
Friday, 02 October 2026 13:40
//
18 minute read
In the first StyloMail article, I used Jev to ask specific questions about email and get typed, probabilistic answers back. Nimble, from Bespoke Labs, brings that technique to a model I can host...
Thursday, 01 October 2026 22:00
//
15 minute read
Bit of an odd one today; thought I'd share how I spec new work. The text below is NOT an article, it's a research paper which I'll convert to a spec. I spent about 3 days so far on the idea.
See Part...
Thursday, 01 October 2026 02:00
//
50 minute read
Scott Galloway | Hands-on Engineering Leader | Principal Engineer | Systems Architect | AI Systems Engineer
I build systems, and I lead the people who build them. Across more than 30 years in...
Tuesday, 29 September 2026 12:00
//
6 minute read
I asked lucidRESUME for an Engineering Lead résumé.
It produced two pages covering six relevant roles, two recent projects and the
skills which mattered to the target. The prose was the prose I had...
Saturday, 26 September 2026 12:00
//
16 minute read
Every recruitment site performs the same little confidence trick:
Please upload your CV.
Splendid. Now type your CV into these boxes.
Name. Email. Phone. GitHub. Current employer. Describe your...
Wednesday, 23 September 2026 12:00
//
19 minute read
Yes, I'm getting on the Jev bandwagon. I wanted to see how far I could get using it to build a behavioural spam-blocking proxy in .NET Core. Something that looks at mail in both directions: what...
Tuesday, 22 September 2026 22:00
//
32 minute read
A résumé should work like a scientific paper: human-written prose for
communication, machine-readable structure for discovery, and references that
connect claims to evidence.
As I once more hunt for...
Friday, 18 September 2026 12:00
//
36 minute read
The same four-part shape keeps appearing across StyloBot: establish a base, retain the useful delta, measure drift, and consolidate when the evidence warrants it. Compression is not a component; it is...
Thursday, 10 September 2026 12:00
//
14 minute read
Part of the Stylo.Bot release series. Behaviour-Aware ASP.NET UI covers the server-rendered dashboard surface; Finding and Fixing Unbounded Growth covers the reliability discipline behind bounded...
Friday, 24 July 2026 12:00
//
20 minute read
Part 1 was the shape of the thing. This part is what it does.
A model only earns its keep under real work : dropping the fleet on a codebase it has never seen, pushing one change across repositories,...
Saturday, 18 July 2026 16:05
//
12 minute read
This is Part 1 of two : the problem and the StyloAgent model. Part 2 : The Workflow in Practice applies it.
Code generation stopped being the problem a while ago. The models write good code. They...
Saturday, 18 July 2026 16:00
//
20 minute read
StyloBot v8 lets a site give AI crawlers a controlled Markdown view of its pages at its own local edge, without ceding the gateway to a CDN. This piece is about the extractor that does the conversion...
Tuesday, 23 June 2026 18:00
//
30 minute read
Bot detection should not stop at allow/block. This post shows how StyloBot's classification result becomes application logic in TypeScript: server middleware for Express and Fastify, template helpers...
Monday, 01 June 2026 10:30
//
19 minute read
How do you test a detector whose answer is supposed to change as it learns? This post is about BDF, the Behavioural Definition Format that makes StyloBot testable: one file defines a class of traffic,...
Monday, 01 June 2026 10:30
//
23 minute read
