Archive
1046 posts · Page 39 of 88. ← Blog
Turn text into a `[]float32` that places meaning in space — what an embedding is, cosine similarity implemented by hand in Go, calling an OpenAI-compatible /embeddings endpoint with net/http, and a worked pairwise-similarity example that scores related sentences higher.
Turn text into a []float32 that places meaning in space — what an embedding is, cosine similarity implemented by hand in Go, calling an OpenAI-compatible /embeddings endpoint with net/http, and a worked pairwise-similarity example that scores related sentences higher.
The opener to a series on evaluating agents in Go: why an agent isn't a function you can unit-test, why "it worked in the demo" doesn't survive contact with production, and the two things actually worth measuring — the steps it took and the answer it gave.
The opener to a series on evaluating agents in Go: why an agent isn't a function you can unit-test, why "it worked in the demo" doesn't survive contact with production, and the two things actually worth...
Predicting who will leave is the easy half. The hard half is acting on it: treating the persuadable, respecting a budget, and proving the intervention actually kept anyone.
Predicting attrition and acting on it: churn features and labels, uplift vs propensity (treat the persuadable), and an agentic retention workflow that recommends and executes interventions with guardrails and holdout mea…
How a single issuer event fans out into thousands of entitlements, why deadlines are terminal, and what the calculation engine actually has to get right.
The announcement to ex-date to record-date to payment lifecycle for mandatory and voluntary corporate actions, and the entitlement/election engine behind it.
When an AI agent spends your money, "the user said so" is not evidence. A signed mandate chain is.
A deep dive on the mandate chain as evidence: verifiable credentials (VCs), signing, the non-repudiable Intent→Cart→Payment chain, revocation and expiry, and why this replaces 'trust me, the user said so' with cryptograp…
How to model the card payment as a two-phase auth-then-capture flow plus a clearing tail — handling incremental auths, partial captures, reversals, expiry, and the auth-vs-settled reconciliation that trips up every ledger.
Teaches how to model the card transaction as a two-phase (auth then capture) plus clearing/settlement state machine, handling partial captures, incremental auths, auth expiry/reversal, and the auth-vs-settled amount reconciliation.
Wiring the 3DS Server, Directory Server, and issuer ACS into a handshake that produces a cryptogram your authorization message can carry.
Teaches how to integrate 3-D Secure 2: the 3DS Server, Directory Server and issuer ACS handshake, frictionless vs challenge decisioning, device data collection, and liability-shift outcomes feeding the authorization.
How a token vault and scheme-issued network tokens push the raw PAN out of your application systems, so most of your services fall out of PCI-DSS scope entirely.
Teaches how a token vault and network tokens (TR-31/EMV payment tokens) remove PAN from application systems, cutting PCI-DSS scope, and how token provisioning, cryptograms, and detokenization boundaries are architected.
Almost everything interesting in JavaScript is asynchronous — network calls, file reads, timers — and TypeScript types all of it through one generic: `Promise<T>`. But typing async code well means understanding the runtime it describes: the single-threaded event loop that makes non-blocking concurrency work. Types and runtime together are what let you write async code that's both correct and comprehensible.
Almost everything interesting in JavaScript is asynchronous, and TypeScript types all of it through one generic: Promise<T>. But typing async code well means understanding the runtime it describes — the single-threaded event loop that makes non-blocking concurrency work. Types and runtime together let you write async code that's correct and comprehensible.
Being right is not enough to change anything. Every engineer has watched a worse idea win because its advocate was more persuasive, more trusted, or simply better at bringing people along — and concluded, wrongly, that this is unfair politics they want no part of. But influence isn't manipulation; it's the skill of helping good ideas actually happen through other people. In any organization, your impact is bounded not by the quality of your ideas but by your ability to get others to understand, trust, and act on them.
Being right is not enough to change anything. Every engineer has watched a worse idea win because its advocate was more persuasive or trusted. But influence isn't manipulation — it's the skill of helping good ideas actually happen through other people, and your impact is bounded by it.
Treating the prompt as a real engineering artifact — grounded in how a next-token predictor actually works — with roles, specificity, few-shot examples, decomposition, chain-of-thought, grounding, temperature, injection defense, and versioned Go templates you can test.
Prompt engineering as a real engineering discipline: roles, specificity, few-shot, decomposition, chain-of-thought and its cost, grounding, and prompt injection — plus building prompts as versioned, testable Go text/template templates you treat like code.
How to build next-best-action and product recommendations for financial services without crossing privacy or fair-lending lines.
Building next-best-action and recommendations for financial products: signals and feature stores, candidate generation + ranking, suitability/eligibility constraints, and cold-start — without crossing privacy or fair-len…