Field notes from inside the work — GEO, agent deployment, evals, and what actually survives contact with production. Written from the projects we ship, with our own prices and numbers.
A software factory is a quality-gated line of senior engineers and AI agents, not bespoke projects, and why the mid-market should hire one.
Getting cited by AI answer engines
18 articlesWhat AI agents are, and which one you need
9 articlesHow to buy AI without getting burned
21 articlesWhat AI actually costs, and what it returns
8 articlesKnowing whether you are ready to build
6 articlesKeeping a live AI system working
Zapier pricing, checked 30 October 2026: Free for 100 tasks, Professional from $19.99 a month, Team from $69, both billed annually. Every tier, with examples.
Read
Make.com pricing, checked 30 October 2026: Free for 1,000 credits, Core from $9, Pro $16 and Teams $29 a month billed annually. Every tier and how credits work.
Read
HubSpot pricing, checked 30 October 2026: Free for 2 users, Sales Hub $7, $90 or $150 a seat, Marketing Hub $800 or $3,600 a month, onboarding up to $7,000.
Read
Salesforce pricing, checked 30 October 2026: Starter $25, Pro $100, Core $195, Advanced $395, Max $550 a user a month. Agentforce from $2 a conversation.
Read
Shopify pricing, checked 30 October 2026 on the US page: Basic $19, Grow $49, Advanced $299 a month paid yearly, Plus from $2,300. Fees and upgrade break-evens.
Read
Custom software cost, checked 30 October 2026: Clutch reviews show $10,000-$49,999 typical, $132,480 average, $25-$149 an hour by country. Example budgets.
Read
MCP is an open standard that connects AI apps to tools and data through one protocol. How it works, the security risks, and when an API is the better choice.
Read
Cursor pricing, checked October 2026: Plus $8, Premium $30, Super $100, Ultra $200 a month, Teams from $30 a seat. How usage works and what a team pays.
Read
Invoice processing automation explained: capture, extraction, 2- and 3-way matching, approvals, ERP posting, where AI fits, the controls and a checklist.
Read
A technical due diligence checklist in 9 areas, from architecture to AI data rights and licences, with red flags, the report to expect and founder prep.
Read
Magento to Shopify migration in 10 steps: what moves and what doesn't, a data mapping table, a redirect plan, app replacements, Plus or not, and a cutover list.
Read
LLMOps is how you keep LLM apps and agents working after launch: versioned prompts, regression evals, guardrails, tracing, cost budgets and model upgrades.
Read
AI in manufacturing, function by function: quality, maintenance, planning, supply, quoting, documents and ERP. The data each needs, sourced figures, a verdict.
Read
A forward deployed engineer works inside one customer's business and ships software against its real problem. Where the role came from and when to hire one.
Read
n8n pricing in 2026: Cloud from €20 a month for 2,500 executions, Business €667, a free self-hosted edition, and the cost at 5,000 and 50,000 runs.
Read
Webflow pricing, checked October 2026: Basic $15, Premium $25 a month billed yearly, plus $15 to $39 per seat. Every plan and add-on, with worked examples.
Read
Odoo pricing in the US, checked October 2026: Standard $31.10, Custom $61 a user a month billed yearly, 20% off year one. Plus hosting and worked budgets.
Read
Composable commerce builds a store from separate API-connected services. How it differs from headless and MACH, what it costs, and when to stay on one platform.
Read
Claude Code pricing, checked October 2026: Pro from $17 a month, Max $100 or $200, Team seats from $20, or pay per token. What a session and a team cost.
Read
Vibe coding security checklist for Lovable, Bolt, Replit, Cursor and Claude Code apps: 13 checks from Supabase RLS to AI spend caps, each with a 10-minute test.
Read
How to rank in ChatGPT: let OAI-SearchBot crawl you, appear in the results ChatGPT search reads, publish answer-first pages, and measure your citation rate.
Read
AI in logistics pays off on email quotes, order entry, documents, tracking updates and exceptions. Sourced figures, what it needs first, and a decision table.
Read
n8n lists more than 13,000 workflow templates. Which kinds suit a business, how to import one safely, and the eight fixes each one needs for production.
Read
Agentic workflows explained: workflow vs agent, six patterns from prompt chaining to tool-using agents, with business examples and when to skip them.
Read
AI agent use cases by function: 20 jobs from support to finance, each with the data it touches, the human checkpoint, the metric and a realism rating.
Read
AI agent observability tools compared: Langfuse, LangSmith, Phoenix, Helicone, Braintrust, Weave, Datadog and OpenTelemetry, priced on 23 Oct 2026.
Read
A free AI policy template: a 12-section company AI acceptable use policy with data rules and human review, mapped to NIST AI RMF, ISO 42001 and the EU AI Act.
Read
WordPress to Webflow migration in 9 steps: inventory, CMS design, CSV import, a copyable 301 redirect map, SEO carry-over and a cutover checklist.
Read
Docker's 3Cs (contain, curate, control) checked against OWASP, Google, Meta, NIST and real agent incidents, plus the gaps you still have to close yourself.
Read
A network pentest skips prompt injection, RAG poisoning and agent tool misuse. What an AI red team tests instead, mapped to OWASP LLM Top 10 questionnaire rows.
Read
What a mid-market ERP implementation costs, why the licence is the cheapest line, and where budgets blow up. From a firm that publishes its own prices.
Read
When ChatGPT and Perplexity disagree, a blended citation rate hides a zero on the engine buyers use. Score each assistant. Run the free AI Citation Audit.
Read
When to hire vs embed AI engineers: two senior seats open four months is the signal to stop recruiting. Embedded AI Teams start at $3,000–$7,500/engineer/mo.
Read
LLM-as-judge for AI agents is usable only after a human-labeled holdout calibration. Trust auto-scores then. Book the $25,000 AI Transformation Sprint.
Read
Build an AI agent eval set from real tickets. Stratify volume and failures, label correct answers, gate deploys. Book the $25,000 AI Transformation Sprint.
Read
AI for consulting firms should start with the archive, not a proposal bot. One firm got 1,200 hours a quarter back. Book the $25,000 AI Transformation Sprint.
Read
A multi-step AI agent at 95% per step is about 66% end to end after eight steps. Split or gate it. Book the $25,000, two-week AI Transformation Sprint.
Read
Companies get excluded from AI answers when crawlers, published facts, or the brand name conflict. The page can still exist. Run the free AI Citation Audit.
Read
AI agent eval metrics that should gate every deploy: golden-set size, accuracy thresholds, confidence gates. Book the $25,000 AI Transformation Sprint.
Read
AI patient intake EHR integration that cuts admin time when eligibility, consent, and chart write are one path. Book the $25,000 AI Transformation Sprint.
Read
AI agents for ecommerce operations pay back first on returns, inventory, and exceptions — with published ROI. Book the $25,000 AI Transformation Sprint.
Read
Four cost centres, and the model is the smallest. What an AI MVP cost covers to reach real users, and the line most budgets forget.
Read
AI systems don't crash. They decay while dashboards stay green. Five ways a live system degrades, and what AI system maintenance actually is.
Read
An AI project ROI calculator is simple arithmetic. The hard part is four inputs, and three are inflated by whoever builds the case.
Read
Check AI visibility free this afternoon: a spreadsheet, four tabs, what to ask, what to record, and three mistakes that ruin a DIY audit.
Read
A realistic first-year AI budget runs $75,000 to $300,000 for 20-to-500-person firms. How to split it across audit, build and operate so year two holds.
Read
Third vendor, same line. Why switching AI vendors resets you to zero, what the last engagement should have left, and how to make this the last.
Read
An AI readiness assessment scores your organisation: whether you can ship, what to fix first, what a good one contains, and when to skip it.
Read
Seven entries, each a question someone asks at an inconvenient hour. The runbook that turns a live AI system into something a person can be on call for.
Read
AI system handover: the inventory to collect, the test that proves it worked, and the four things that always go missing.
Read
Not the vendor's tricks, your own. Seven internal line items that never appear in a quote, why the biggest is your team's time, and how to price them.
Read
Five tells in the first meeting, before any code. Each is a question you can ask, and the answers say whether an AI project fails or should be funded.
Read
Your Zapier flows and RPA bots aren't obsolete: they're cheaper and more predictable than an agent for the work they fit. The line is your exception rate.
Read
An AI agent should stop when an action is hard to undo, a mistake would go unnoticed, or it isn't confident. Four supervision patterns, and how to choose.
Read
You've decided to build custom. Hire AI in-house vs agency depends on whether AI is core to your product, and who operates it in year two.
Read
B2B AI search visibility: shortlists are drafted by an assistant before anyone calls. You can check in five minutes whether you're on them.
Read
A one-page machine-readable summary of your site, in Markdown, at /llms.txt. What it is, what it isn't, and an honest answer on whether it does anything.
Read
Readiness isn't enthusiasm, it's five specific conditions. The checklist we run before we agree to build, and what to do if you only meet three of them.
Read
The headline number isn't the price, it's the entry fee for an open-ended meter. The five contract clauses that give the trap away, and what to ask for.
Read
The questions that separate a firm that ships from one that demos — what each is really testing, and what a bad answer sounds like. Ask ours the same ones.
Read
Product-market fit means the market wants what you built. Answer-Market Fit means its AI assistants recommend you by default. How to measure and reach it.
Read
GEO has no standard sticker price. The three ways it is priced, what drives the number, what agencies charge, and our own: Ascent from $4,000 a month.
Read
A chatbot answers; an agent acts. The real distinction — autonomy, tools, and multi-step work — and how to tell which one your workflow actually needs.
Read
HIPAA compliant AI needs a BAA at every hop touching PHI, minimum necessary access, audit logs and human review. Which AI vendors sign BAAs, and a checklist.
Read
We ran 18 buying questions through Google AI Mode: the most-named firm appeared in 20% of answers. What a good AI citation rate is.
Read
How AI support automation SaaS hits majority autonomous resolution without torching CSAT: tier design, escalation, and evals, with real numbers.
Read
When a buyer asks an AI assistant for a vendor, the answer isn't ranked, it's assembled. What the engines retrieve, what they trust, and how to be cited.
Read
AI agent cost, checked 30 October 2026: from $8,000 to about $150,000 to build, plus tokens and $3,000 to $20,000 a month to run. Tables and worked examples.
Read
The six layers a production AI agent stack needs: model, orchestration, retrieval, evals, observability, guardrails, and where teams cut corners.
Read
Generative engine optimization is how you get cited when search splits into blue links and answer engines. Be the source an LLM quotes, not the one it skips.
Read
Pilot purgatory is an engineering problem, not an ambition problem. Here are the eval, ownership, and rollback gates that separate a demo from a deployed agent.
ReadWhat changed in production AI this month. The signal, pulled from inside real deployments — not the hype feed.
Unsubscribe in one click. We never share your email.
The agent patterns, model releases, and tooling that actually reached production this month.
Eval results and benchmarks from real deployments — what moved, what regressed.
GEO shifts: who answer engines started quoting, and why.
If you’d rather see it work than read about it, a 30-minute discovery call is the fastest path.
