Blog
Engineering notes on AI agents, MCP, LLM evals and AI security – and the web apps around them. Sourced, with diagrams, written for people who ship.
AI agents
·12 min read
How to use Claude in OpenCode: the new Claude Agent provider on your Claude plan, API keys, Console, Copilot and OpenRouter, with costs and limits.
AI agents
·11 min read
Claude Code Review, now GA for Team and Enterprise: how agents verify findings, set review levels, cap spend, and compare with the GitHub Action.
LLMOps & evals
·11 min read
Claude plan prices as of October 2026, how the five-hour and weekly usage limits work, Team seats, API token prices and how to pick a plan.
AI agents
·12 min read
How to write a Claude skill: directory layout, frontmatter fields and limits, progressive disclosure, descriptions that trigger, scripts and testing.
LLMOps & evals
·15 min read
Claude Haiku 5.5 pricing by tier, benchmarks against Haiku 4.5 and Sonnet 5.5, effort levels, and which Sonnet 5.5 jobs can move to it.
LLMOps & evals
·15 min read
DeepSeek V4.1 Flash 1017 deep dive: the encoder-decoder split, CSA2 cache sharing, FP4 KV cache, benchmarks, and the real cost per agent task.
LLMOps & evals
·10 min read
How LLM rate limits work, which errors to retry, backoff with jitter, retrying in one layer only, and fallback chains that do not break your output.
LLMOps & evals
·8 min read
Prompt versioning in production: what belongs in a version, git vs a prompt registry, labels and rollbacks, eval gates in CI, and cache side effects.
LLMOps & evals
·9 min read
When to use the Anthropic, OpenAI and Gemini batch APIs, how limits, result matching and failures work, and how batch discounts stack with prompt caching.
AI agents
·11 min read
How to design agent tools that get picked and called correctly: task-shaped tools, descriptions, schemas, compact responses and errors a model can act on.
Retrieval & search
·9 min read
How to pick an embedding model for RAG in 2026: what MTEB and RTEB tell you, hosted vs open weights, prices, dimensions, and a one-week bake-off.
Retrieval & search
·10 min read
Chunks lose their document. How contextual retrieval, late chunking and contextualized embedding models fix that, what each costs, and when to skip it.
Retrieval & search
·9 min read
How RAG assistants leak documents and how to stop it: ACLs on every chunk, pre-filtering, row-level security in pgvector, permission sync and leak tests.
Security & compliance
·13 min read
What to check after the model answers: safe Markdown rendering, schema checks before actions, moderation classifiers, streaming rails and groundedness.
Web engineering
·10 min read
Product markup for B2B shops: snippet or merchant listing, which price to publish, part numbers, unit pricing, variants, Organization and SSR in Nuxt.
Web engineering
·9 min read
How to build an AI support assistant for a B2B shop: which requests to automate, tools that run in the customer context, handoff, AI Act and metrics.
LLMOps & evals
·11 min read
When a small model beats a frontier API: cost per resolved case, latency, privacy, distillation, quantization, routing and an eval plan for your traffic.
LLMOps & evals
·10 min read
Reasoning effort on Claude, OpenAI and Gemini: adaptive thinking, what thinking tokens cost, and how to pick a level with an effort sweep.
AI agents
·11 min read
How to use coding agents on a legacy migration: characterization tests first, one seam per task, review gates and differential verification.
AI agents
·12 min read
How async coding agents queue tasks, run in sandboxes, open draft PRs and pass CI. Provider limits, cost controls, review design and failure modes.
Retrieval & search
·10 min read
Product data is structured, so chunking it like PDFs fails. How to serialize PIM attributes, route spec questions to filters and keep answers exact.
Retrieval & search
·12 min read
How to rewrite follow-up questions in a B2B shop assistant: coreference, HyDE, multi-query expansion, filter extraction, latency and evaluation.
Retrieval & search
·10 min read
Question generation from chunks, hard negatives, answerability labels, German and Hungarian coverage, contamination and human spot checks.
Security & compliance
·12 min read
A practical red teaming checklist for LLM features: scope, OWASP 2025 test cases, promptfoo, garak and PyRIT, human testers and regression tests.
Web engineering
·11 min read
Streaming AI chat UI in Vue and Nuxt: fetch streams, abort and retry, safe markdown, aria-live announcements, keyboard support and reduced motion.
Web engineering
·9 min read
How to translate product and website strings with LLMs without breaking placeholders, plurals or tone: glossary, ICU messages, QA checks and review gates.
LLMOps & evals
·9 min read
How structured outputs and constrained decoding work on OpenAI, Claude, Gemini and vLLM, which schema rules matter, and what you still validate.
LLMOps & evals
·9 min read
How to evaluate AI agents: outcome vs trajectory graders, trajectory match modes, pass^k, isolated environments and LLM judges that hold up.
LLMOps & evals
·10 min read
A playbook for switching LLM models: deprecation timelines, contract fixes, a regression suite, prompt re-tuning, shadow traffic and canary rollout.
AI agents
·10 min read
Why LLM accuracy drops as context grows, and how clearing tool results, compaction, notes and sub-agents keep long-running agents on track.
Retrieval & search
·9 min read
Why PDF parsing decides RAG quality, how Docling, Marker, MinerU and VLM OCR differ, and how to test a parser on your own documents.
Retrieval & search
·7 min read
How to build RAG over German and Hungarian content: multilingual embeddings, compound words, stemming, accents and per-language evals.
Retrieval & search
·8 min read
How accurate text-to-SQL really is, how to give the model schema context, and the database and code guardrails that keep generated SQL safe.
Security & compliance
·6 min read
How LLMs hallucinate package names, how attackers register them, and the registry, lockfile and agent-harness controls that stop the install.
Web engineering
·8 min read
How to set up Nuxt i18n so search engines index every language: routing strategy, useLocaleHead, hreflang rules, partial translations and sitemaps.
AI agents
·7 min read
Where AI agents help with end-to-end tests: Playwright planner, generator and healer, MCP or CLI, and the guardrails that keep healed tests honest.
LLMOps & evals
·6 min read
How semantic caches reuse LLM answers for similar questions, how they differ from prompt caching, and how to avoid wrong hits, leaks and stale answers.
Retrieval & search
·5 min read
How binary and int8 quantization and Matryoshka truncation shrink vector indexes 4 to 32 times, what they cost in recall, and how rescoring wins it back.
Security & compliance
·6 min read
How attackers plant documents that RAG systems retrieve, what PoisonedRAG and OWASP show, and the ingestion, retrieval and answer controls that limit it.
Web engineering
·14 min read
How to stop abuse and runaway cost on a public LLM route in Nuxt: auth, per-user rate limits, prompt caps, token budgets, Turnstile and spend limits.
AI agents
·12 min read
What the Agent2Agent protocol standardizes in v1.0: agent cards, tasks, bindings, security, how it differs from MCP, and when it is worth using.
AI agents
·10 min read
How to build an internal AI copilot for B2B sales reps: the account data it needs, per-rep permissions, approval gates, KPIs and the works council.
Web engineering
·9 min read
What a B2B shop must expose so buyer-side procurement agents can find, compare and order: product data, price truth, quotes, identity and protocols.
Web engineering
·8 min read
How to automate RFQ handling with LLMs: document intake, line extraction, part-number matching, contract pricing and a review queue that stays fast.
Web engineering
·9 min read
How to automate B2B order entry from email with LLMs: reliable mailbox intake, line extraction, validation rules as code, idempotency and GDPR.
AI agents
·8 min read
AI agent for after-sales service: serial number to spare part, RMA drafting, manual RAG, and the rule that identifiers only come from tools.
Web engineering
·8 min read
AI agent for a B2B customer portal: live order, invoice and reorder data, per-user permissions, the cache boundary and honest deflection metrics.
Web engineering
·8 min read
How to raise PIM data quality with LLMs: ETIM and ECLASS classification, unit and language normalization, duplicate detection and a stewardship queue.
Web engineering
·9 min read
How to onboard supplier product data with LLMs: deterministic BMEcat and Excel imports, PDF price list extraction, GTIN validation and supplier scorecards.
LLMOps & evals
·10 min read
Self-hosting an LLM for GDPR: when it is required, GPU memory for open-weight models, EU prices as of October 2026 and break-even per million tokens.
AI agents
·8 min read
OpenCode is an MIT-licensed terminal coding agent for any model, hosted or local. Agents, permissions, MCP and LSP, plus the data-protection trade-offs.
Web engineering
·9 min read
Where the Digital Product Passport stands in October 2026, which data a DPP record needs, and how LLMs extract supplier evidence without inventing values.
AI agents
·8 min read
How to build an agent for ERP integration error handling: an error taxonomy from IDoc and OData contracts, allowlisted runbooks, safe retries and dedup.
Security & compliance
·11 min read
How secrets leak through coding agents, and the controls that stop them: deny reads, a sandbox, pre-commit scans, push protection, OIDC and rotation.
AI agents
·8 min read
Pydantic AI 2.55: typed dependencies, validated output and OpenTelemetry tracing for Python agents. What 2.0 changed, Logfire costs, who should pick it.
Web engineering
·8 min read
How punchout catalogs work: the cXML PunchOut and SAP OCI round trips, Secure OCI, what a supplier shop must implement, and when to buy a gateway.
Web engineering
·8 min read
How to sync orders between a B2B shop and the ERP: SAP OData, IDoc and BAPI options, the outbox pattern, idempotency keys and routine reconciliation.
Web engineering
·9 min read
llms.txt is a proposal, Markdown content negotiation is a header. What AI agents fetch, what the logs show, and how to serve both from Nuxt and nginx.
AI agents
·9 min read
Gemini CLI review: Apache-2.0 and still releasing, but the free individual route closed on 18 June 2026. Left: Code Assist, billed API keys and Vertex AI.
AI agents
·8 min read
Temporal: agent loops as durable workflows, so retries, approvals and timers survive crashes. Costs, data residency, determinism, when to skip it.
Web engineering
·12 min read
How B2B platforms resolve customer-specific prices, how to cache them without leaks, explain them in a dispute, test them and round VAT.
Web engineering
·12 min read
How to design RFQ and quote management in B2B: states, versioned quotes, price overrides, expiry rules, order conversion and a build checklist.
Retrieval & search
·11 min read
Zep: a hosted agent-memory API on a temporal knowledge graph. Credits on writes, free retrieval, Flex from $125/month, Graphiti as the self-hostable part.
LLMOps & evals
·8 min read
DeepEval: LLM checks as pytest-style tests with built-in judge metrics. The library is free and Apache-2.0; judge calls and data flow are the real cost.
LLMOps & evals
·8 min read
DSPy compiles prompts from signatures, a metric and examples: what its optimisers cost in model calls, and when a hand-written prompt still wins.
Web engineering
·12 min read
Grounded LLM enrichment for PIM attributes and copy: source spans, schema-checked output, confidence routing, provenance and cost per 1,000 SKUs.
Web engineering
·10 min read
Instrument on-site search with one event schema, five metrics with targets, position-bias-aware reading, a weekly zero-result review and GDPR limits.
Web engineering
·8 min read
Multiplayer 3D sailing in plain three.js: Gerstner waves shared by GPU and CPU, one sky function for sky, water and fog, and a tiny WebSocket relay.
LLMOps & evals
·8 min read
llama.cpp runs open models in plain C and C++ on Metal, CUDA, Vulkan or the CPU. I cover GGUF quants, llama-server and where it falls short.
LLMOps & evals
·7 min read
Opik: traces, LLM-as-a-judge metrics, prompt versions and an optimiser on one Apache 2.0 platform. Free to self-host, Pro cloud $19/month, US-hosted.
Web engineering
·11 min read
Visual search for a B2B shop: image embeddings, OCR of part numbers, image-to-text lookups, hybrid filters, cost and evaluation on your own photos.
Web engineering
·11 min read
Caching a headless commerce front end in Nuxt: route rules, Nitro and CDN keys, ISR limits, tag purge, and keeping customer prices out of shared caches.
Retrieval & search
·13 min read
Microsoft GraphRAG and LightRAG: what indexing costs, and when a knowledge graph beats vector RAG for multi-hop, global questions and product catalogues.
Security & compliance
·11 min read
Usage logs can make an AI coding tool a monitoring system. What Austria (§ 96 ArbVG) and Germany (§ 87 BetrVG) require, and what to agree before rollout.
AI agents
·12 min read
E2B gives each agent run its own Firecracker microVM, billed per second. Where it fits, what the EU option costs, and where self-hosting stops.
Web engineering
·11 min read
How the Nuxt Security module behaves in practice: safe defaults, strict mode trade-offs, nonce CSP in SSR and SSG, route rules and limits.
Web engineering
·12 min read
Component-level WCAG 2.2 patterns for Vue and Nuxt: focus in modals and Teleport, live regions, comboboxes, what axe-core misses, and a test ladder.
Security & compliance
·12 min read
EU AI Act after the Digital Omnibus: GPAI duties, high-risk dates of 2 Dec 2027 and 2 Aug 2028, provider vs deployer on OpenAI and Anthropic, AI literacy.
LLMOps & evals
·11 min read
Three open TTS models on one laptop: 96 articles became 1,512 minutes of narration, via chunked synthesis and AAC at 192 kbit/s.
AI agents
·11 min read
AI coding economics: what the METR, DORA, Microsoft and GitHub studies show, what they do not prove, and a break-even model for one senior vs a team.
Security & compliance
·12 min read
A worked DPIA under GDPR Art. 35 for an AI assistant that drafts customer email replies from order data: when it is needed, the risks and owners.
Retrieval & search
·10 min read
Multimodal RAG with ColPali: page-image embeddings, MaxSim scoring, multi-vector storage costs, compression options and when they beat parsed text.
Retrieval & search
·8 min read
How coding agents find code: AST chunking with tree-sitter, repo maps, Merkle-tree index sync, code embedding models in 2026, and when grep beats an index.
AI agents
·11 min read
Vibe coding breaks on real codebases. Write a spec with acceptance criteria, a plan and tasks, let the agent tick them off, and agree it before any code.
Web engineering
·10 min read
Browserbase rents managed Chrome per minute and Stagehand adds natural-language steps. What it costs, where the meters run and when plain Playwright wins.
Web engineering
·11 min read
WebMCP lets a page publish typed, callable tools to an in-browser agent. What the standard does, how much ships today, and when a plain MCP server wins.
Retrieval & search
·8 min read
Rerankers in October 2026: pointwise, listwise and late interaction, Cohere, Voyage, bge, Qwen3, Jina and mxbai, prices, self-hosting and choosing k.
Retrieval & search
·8 min read
Vector search in Elasticsearch and OpenSearch: kNN and filters, BBQ and binary quantization, RRF hybrid search, GPU builds, and AGPL vs Apache licensing.
AI agents
·14 min read
OpenAI dots: always-on GPT-6 Astra agents with their own computer. What launched, how the safeguards work, and what changes for work, IT, SaaS and Europe.
LLMOps & evals
·11 min read
Ollama serves open models over one HTTP API on your own hardware. What it does well, where throughput falls short, and what the MIT licence does not cover.
Security & compliance
·10 min read
A review of Guardrails AI: 65 hub validators, eight on-fail actions, the August 2026 shutdown of hosted inferencing, and when NeMo Guardrails fits better.
Retrieval & search
·8 min read
turbopuffer reviewed: object storage as the source of truth, SPFresh and RaBitQ, hybrid search, per-GB pricing against Pinecone, and when it wins.
Retrieval & search
·8 min read
Tables in RAG: why chunking breaks them, pdfplumber, Camelot, Docling and cloud extractors, what TEDS misses, serialization, and routing questions to SQL.
Web engineering
·9 min read
Home Assistant on EPEX Austria prices, replayed hourly for a Tesla and a boiler: cheapest-hour charging at 6.5 vs 18.9 ct/kWh, saving about €590 a year.
LLMOps & evals
·11 min read
Portkey: an OpenAI-compatible gateway for retries, fallbacks, caching, guardrails and cost tracking. Its config, latency cost and when to self-host.
Retrieval & search
·8 min read
Fine-tuning embedding models for your domain: when it beats a reranker, hard negatives, sentence-transformers v6 losses, Matryoshka, evals and cost.
Retrieval & search
·8 min read
Learned sparse retrieval in practice: how SPLADE expands terms, models and licenses, index size and latency, engine support and when it beats BM25.
AI agents
·9 min read
modelcontextprotocol/servers reviewed: seven reference servers, what each one teaches, their SDK versions, and why none belongs in production.
Retrieval & search
·8 min read
Building a knowledge graph with LLMs: a minimal ontology, extraction prompts, entity resolution, provenance, incremental updates, evaluation and storage.
Retrieval & search
·8 min read
Keeping a RAG index current: staleness budgets, dirty tracking, CDC from Postgres with Debezium, deletes and permissions, blue/green swaps and costs.
AI agents
·10 min read
A review of Aider 0.86.2, an Apache-2.0 terminal pair programmer whose benchmark ranks models honestly and whose release cadence has stopped.
LLMOps & evals
·8 min read
Claude Opus 5.5 is #1 of 211 models on Artificial Analysis with 58 points. At medium effort it matches Opus 5 for $1.34 per task instead of $5.86.
Security & compliance
·12 min read
EU AI Act Article 50 from 2 August 2026: AI interaction disclosure, machine-readable marking, deepfakes, provider vs deployer, and a checklist.
Retrieval & search
·9 min read
LanceDB review: an Apache-2.0 embedded vector library with IVF and HNSW index choices, hybrid search with rank fusion, and what the Enterprise tier adds.
Retrieval & search
·10 min read
pgvector 0.8.7: iterative scans for filtered search, HNSW and IVFFlat, binary quantisation at 100M vectors, and the CVE behind an index-build patch.
Retrieval & search
·10 min read
Mem0: facts extracted from every turn, the April 2026 benchmark table and its platform-only caveat, four cloud tiers, and what self-hosting leaves out.
LLMOps & evals
·10 min read
LLM routing with typed decisions: Choice, Score and yes-probability answers with calibrated confidence, thresholds and human hand-off, using Jev.
Web engineering
·12 min read
Headless B2B product configurator: rule engine or solver, where rules live, server-side pricing, Nuxt on a commerce API, TYPO3 and 100k+ variants.
AI agents
·10 min read
A review of the OpenAI Agents SDK: the runner loop, tracing, guardrails and approvals, plus what the release churn and the Responses-only features cost.
AI agents
·13 min read
How to design AI agent memory: context vs session vs long-term tiers, what to write and never store, retrieval, compaction, poisoning and GDPR erasure.
AI agents
·9 min read
OpenHands 1.25.0: an MIT-licensed coding agent platform with a web canvas, CLI, sandboxed execution and scheduled automations, and where it gets heavy.
Retrieval & search
·10 min read
Milvus 3.0.2 is the most complete open-source vector database and the heaviest to run: architecture, hybrid search, costs, and where not to use it.
Retrieval & search
·10 min read
A review of Microsoft GraphRAG 3.2.0: MIT, maintenance mode, and an indexing bill that is decided before the first query runs.
AI agents
·8 min read
Harness engineering for coding agents: guides and sensors, where to run each check, red/green TDD, and mutation testing of the tests the agent wrote.
AI agents
·10 min read
Cursor bundles an editor, a terminal agent and cloud runs in one plan. What its two usage pools cost, and when Copilot, Claude Code or Cline wins.
Security & compliance
·9 min read
Why prompt injection can't be filtered away: the lethal trifecta, six design patterns that contain it, egress rules and a red-team checklist for AI agents.
AI agents
·10 min read
An engineering review of Claude Code: the extension surface, the real cost per developer, and the exact boundary of the Bash sandbox.
AI agents
·11 min read
OpenAI Codex CLI, the open-source terminal coding agent: how its sandbox, approval policy and config.toml work, and what unattended CI runs cost.
Security & compliance
·11 min read
Can an LLM API be GDPR compliant? EU data residency on OpenAI, Claude via Bedrock and Google Cloud, zero data retention, pseudonymisation and self-hosting.
AI agents
·17 min read
rtk, lean-ctx, context-mode, Serena and 16 more token savers for coding agents, ranked by evidence, with my own measurements on a real Nuxt codebase.
Retrieval & search
·10 min read
Firecrawl turns URLs into clean Markdown through one hosted API. What it costs, where crawl accounting breaks down, and when to run the AGPL core yourself.
Retrieval & search
·13 min read
Semantic search for B2B shops without breaking part-number search: hybrid BM25 and vectors, filters, DE/EN/HU, LLM query parsing, reranking and metrics.
Retrieval & search
·13 min read
Cutting hallucinations in production RAG: citation APIs, abstention, claim-level checks, faithfulness metrics, source UI, and what still slips through.
Security & compliance
·10 min read
Semgrep: 30-plus languages, YAML patterns matched in seconds, a free LGPL-2.1 engine. Cross-file analysis, rulesets and AI triage sit behind paid tiers.
LLMOps & evals
·10 min read
Langfuse: LLM traces, prompt versions and experiments on one MIT-licensed platform. What self-hosting costs, how unit pricing adds up, and where it loses.
Security & compliance
·10 min read
MCP security checklist: the threat model, tool poisoning, rug pulls, RFC 9207 issuer checks, per-issuer credentials, scoped tokens and audit logs.
AI agents
·10 min read
GitHub's cloud coding agent takes an issue and opens a pull request. What the 59-minute session limit, AI credits and review duty mean in production.
AI agents
·12 min read
Orchestrator-worker, fan-out, critic, handoff: what multi-agent systems really buy you, what they cost in tokens, how they fail, and a table to decide.
LLMOps & evals
·12 min read
How to trace LLM agents with OpenTelemetry: GenAI semantic conventions and their status, span tree, token metrics, sampling, PII, evals and tool options.
Security & compliance
·11 min read
AI agent sandbox checklist for CI: isolation, egress allowlists, short-lived scoped credentials, blocked metadata endpoints, untrusted project config.
Security & compliance
·9 min read
A review of Lakera Guard: one endpoint before the model, the PINT benchmark behind its scores, and why the free tier stops at 10,000 requests a month.
Security & compliance
·10 min read
What detect-secrets does, how its committed baseline differs from gitleaks and TruffleHog, why verification calls matter in CI, and where the tool stops.
Retrieval & search
·8 min read
RAG in 2026: when a cached 1M-token context beats retrieval, when hybrid search still wins, when agentic search fits, and what each costs per request.
AI agents
·9 min read
MCP 2026-07-28 drops sessions and the initialize handshake. For server authors: _meta, server/discover, MRTR, auth and a migration checklist.
AI agents
·13 min read
Approval gates for AI agents: where they belong, how to avoid rubber-stamping, and how interrupt and resume work in LangGraph, OpenAI and Claude SDKs.
Retrieval & search
·10 min read
RAG pipeline step by step: parsing, chunking, pgvector, BM25 and vectors fused with Reciprocal Rank Fusion, reranking, citations and retrieval evals.
LLMOps & evals
·10 min read
OpenRouter: 500+ models from 80+ providers behind one OpenAI-compatible endpoint, with fallbacks and pass-through pricing. Costs and where it breaks.
Web engineering
·13 min read
How to fix LCP, INP and CLS in Nuxt 4 sites and shops: images, hydration, fonts, third-party scripts, prerender vs SSR vs ISR, and measuring real users.
Retrieval & search
·10 min read
Chroma is an Apache-2.0 vector database for embedded, single-node or cloud use. Where it is pleasant, and where its best search is cloud-only.
AI agents
·10 min read
Goose, an Apache-2.0 Rust coding agent under the Linux Foundation: how its permissions, recipes and MCP extensions compare with commercial tools.
AI agents
·10 min read
LangGraph for production agents: checkpointed supersteps, interrupts and streaming, where the durability model stops short, and what LangSmith costs.
AI agents
·10 min read
How the agent loop works in code, which stop conditions and budgets to enforce, and how outer loops like Ralph and Claude Code /loop and /goal behave.
AI agents
·11 min read
Mastra review: agents, workflows, memory, MCP and evals in one TypeScript framework. What its Apache-2.0 core covers, and what the ee/ split costs.
AI agents
·10 min read
LlamaIndex in 2026: an MIT-licensed Python data and agent framework with 300+ integrations, event-driven Workflows, and a focus shifted to LlamaParse.
AI agents
·10 min read
Zed 1.22 review: edit predictions, ACP external agents, parallel threads, the $20 default monthly ceiling on Pro, and the extensions it trades away.
Retrieval & search
·11 min read
Pinecone review: read units scale with namespace size, schemas are fixed at creation, and when self-hosting is the better buy.
LLMOps & evals
·10 min read
Braintrust: traces become datasets and gated experiments. Starter and Pro tiers, open-source parts, and where Phoenix, Langfuse or LangSmith win.
LLMOps & evals
·10 min read
Promptfoo in 2026: MIT-licensed evals and red teaming, now inside OpenAI. What it does well, where the YAML approach breaks, and what the tiers cost.
LLMOps & evals
·10 min read
Arize Phoenix: an ELv2-licensed tracing and eval server on your own database. Strengths, operating cost, and where Langfuse, Braintrust or LangSmith win.
LLMOps & evals
·10 min read
Helicone: an Apache-2.0 LLM gateway and observability platform. What its proxy architecture buys, what it costs you, and how self-hosting really looks.
AI agents
·7 min read
Agent skills in practice: about 20 skills in one master folder for three coding agents, from reproducing bugs with real data to PRs, with guardrails.
Web engineering
·12 min read
Syncing product data between SAP or Infor, Pimcore and a shop: delta vs full sync, change detection, idempotent imports, Messenger queues, replays.
LLMOps & evals
·11 min read
vLLM turns a Hugging Face checkpoint into an OpenAI-compatible server. What PagedAttention and continuous batching buy, and what running it actually costs.
Security & compliance
·12 min read
Where to redact PII in LLM pipelines: reversible tokens vs masking, Presidio and cloud DLP, German and Hungarian gaps, GDPR for pseudonymised data.
Web engineering
·13 min read
Does the European Accessibility Act cover a B2B shop? Scope under BFSG and BaFG, the microenterprise exemption, 2026 enforcement and a WCAG 2.2 fix plan.
Security & compliance
·9 min read
Rebuff scores prompts with heuristics, an LLM, a vector store of past attacks and canary tokens. Archived in May 2025; last release January 2024.
Security & compliance
·10 min read
Protect AI model scanning after the Palo Alto Networks acquisition: what became of Guardian, what ModelScan still does, and how free scanners compare.
AI agents
·8 min read
Context engineering decides what a coding agent has in context: rules in AGENTS.md, procedures in skills, and when an MCP tool beats a shell command.
AI agents
·11 min read
Cline: an Apache-2.0 agent for VS Code, JetBrains and the terminal. What Plan and Act, checkpoints and auto-approve guarantee, and where safety leaks.
Retrieval & search
·13 min read
pgvector, Qdrant, Weaviate, Milvus, Pinecone, OpenSearch or Elasticsearch? A practical 2026 guide to filtering, hybrid search, scale, cost and EU hosting.
Web engineering
·9 min read
Agentic commerce protocols compared: what UCP covers, how AP2 proves a payment was authorized, where ACP fits, and what a shop should build now.
AI agents
·13 min read
Voice agents: realtime speech-to-speech or a cascade of STT, LLM and TTS? Latency per stage, turn-taking, tool calls, German and Hungarian, AI Act.
Web engineering
·12 min read
What generative engine optimization is, what the research really supports, and the GEO audit I ran on this site: 12 checks, 7 fixes, code included.
AI agents
·10 min read
CrewAI, an MIT-licensed Python multi-agent framework: crews for autonomous teamwork, flows for controlled state, the token bill and where it hurts.
Retrieval & search
·10 min read
Weaviate: hybrid BM25 and vector search in one query, HNSW and disk-based HFresh, quantisation, a built-in MCP server, and what licence keys now cover.
LLMOps & evals
·9 min read
Prompt caching, cheap-model-first routing and batch APIs are the levers that cut LLM cost and latency in production. Here is how to use each one.
Web engineering
·10 min read
WebMCP in practice: declarative form attributes, document.modelContext.registerTool, tool annotations, security gates, local testing and a checklist.
Web engineering
·10 min read
Playwright: one Apache-2.0 API for Chromium, Firefox and WebKit, with a test runner, agent CLI and MCP server. What it costs and where it falls short.
Web engineering
·10 min read
ElevenLabs audio API review: model lineup, latency, credit and per-character pricing, tier-gated formats, and where OpenAI and Amazon Polly win.
Retrieval & search
·10 min read
A review of Qdrant: filterable HNSW, four quantisation methods, the memory tiers in v1.19 and the operations nobody publishes any more.
LLMOps & evals
·10 min read
LangSmith review: per-trace billing, 14 and 180 day retention, OpenTelemetry ingestion, offline and online evals, and its pull toward an agent runtime.
Web engineering
·10 min read
Replicate: thousands of open models behind one prediction API, billed per second. Cold boots, version churn and the one-hour data deletion.
Retrieval & search
·11 min read
Unstructured parses PDFs, Word files and images into typed RAG elements: an Apache-2.0 library, and a platform at $0.015 a page after 10,000 free pages.
LLMOps & evals
·10 min read
LiteLLM: the MIT-licensed OpenAI-compatible gateway most platform teams run in front of providers. What it does well, what it costs, where it breaks.
LLMOps & evals
·10 min read
Ragas scores RAG and agent pipelines on faithfulness, context precision and recall, generates test data, and tracks runs. Apache-2.0; judge billed apart.
AI agents
·8 min read
AI code review cannot keep up with agent-written PRs. What the data says, size budgets, stacked PRs, AI as first pass, and who stays accountable.
Security & compliance
·12 min read
AI agent identity and least privilege: its own identity, delegated tokens, an off switch, audit and offboarding, and what Entra, Okta and Auth0 ship.
LLMOps & evals
·8 min read
LLM evals turn a vibe check into a test suite: error analysis on real traces, grader choice, a validated LLM judge, pass^k and a CI gate.
Web engineering
·9 min read
Nuxt AI end to end: a server route that holds the API key, streaming parts, strict structured output, tools needing approval, errors and Article 50.
Retrieval & search
·12 min read
Evaluating RAG: recall at k, MRR and nDCG vs faithfulness and answer relevance, a golden set from real queries, a calibrated LLM judge and CI evals.
LLMOps & evals
·12 min read
Fine-tuning vs RAG vs prompting: what each changes, what it costs, who still offers SFT, DPO and RFT in 2026, and a decision tree.
