◈AI Codex

Articles

Practical AI, by persona.

Decision guides, implementation patterns, and what building with AI actually looks like. Pick your context — the reading list adjusts.

Everything published, by type.

Start here

If you're new, read these first.

Decision guide · 9 min

New to AI? Start here.

You've heard about AI. You've maybe tried it once, got something weird, and closed the tab. This is the honest version of what it is, why most people's first attempts disappoint them, and what to actually do.

→
Decision guide · 7 min

What's safe to share with Claude, and what isn't

The most common reason people hold back from using Claude for real work is not knowing whether pasting something in puts it at risk. Here is the direct answer for each plan as of November 2026, including the training setting most Pro users have never checked.

→
Decision guide · 7 min

Claude Team vs. Enterprise: the actual differences, for IT and legal

A side-by-side of Claude Team and Claude Enterprise as of November 2026: current prices, the new usage-based Enterprise billing, data handling, identity, audit, and retention. Written to be shared with IT and legal without edits.

→
PromptWhat goes wrong · 9 min

The most common Claude mistakes — and how to fix each one

The mistakes that cause 80% of Claude frustration are predictable, and most of them happen in the first sentence of your message. Here's the full list, in order of how much they cost you.

→
Decision guide · 11 min

Which Claude Academy courses are actually worth your time

Claude Academy now has 29 free courses plus hundreds of tutorials and use cases. Nobody gets through that. Here is the triage, updated November 21, 2026: the two courses almost everyone should take, short tracks for five roles, and what to skip.

→

Series

Claude + Tool guides

Using Claude alongside Notion, Slack, HubSpot, Jira, Confluence, Salesforce, and more.

See all 15 guides →
// for developers

Implementation guides. Production-focused, code included.

Feature update · 8 min

The Usage and Cost Analytics API: one query for who spent what, on Console and Enterprise

On October 29, 2026 Anthropic released the Usage and Cost Analytics API in beta. Two endpoints report tokens and dollars for Claude Console and Claude Enterprise organizations, grouped by model, workspace, API key, or the person behind each request. The old usage and cost endpoints are now legacy. What changed, working queries, and the freshness rule that will trip up your dashboards.

→
Feature update · 9 min

API version 2026-10-21: temperature is gone, and your SDK upgrade is a major version

On October 21, 2026 Anthropic released the first new Claude API version since 2023-06-01, along with new major versions of every SDK. Requests that send temperature, top_p, or top_k now fail with a 400. API keys move to the Authorization header. Here is what breaks, what to change, and how to upgrade without an outage.

→
InfrastructureFeature update · 8 min

Claude on Google Cloud, run by Anthropic: the full API with Google IAM and billing

On October 22, 2026, Anthropic made its own Claude API available inside Google Cloud. You authenticate with Google IAM, pay on your Google Cloud bill, and get every Claude Platform feature the day it ships, including Managed Agents. Here's how it differs from Claude on Vertex AI, how to set it up, and when to pick each.

→
Feature update · 8 min

User profiles: stop one end customer from getting your whole API organization banned

On October 20, 2026 Anthropic launched user profiles, which tag each API request with the end customer it is for, so a safety restriction lands on that customer instead of your whole organization. Organization webhooks (beta) tell you when it happens. Who needs this, and how to wire it in.

→
Feature update · 6 min

OpenTelemetry tracing for Claude: see every model call and tool use in your own observability tools

On October 14, 2026 Anthropic added OpenTelemetry export (public beta) for the Messages API, Claude Managed Agents, and the Claude SDKs. What gets traced, where the traces can go, and what to look at first.

→
Feature update · 7 min

Dynamic workflows in Claude Managed Agents: the agent writes the program that runs the other agents

On October 9, 2026 Anthropic added dynamic workflows to Claude Managed Agents (beta). An agent can write a program that runs many agents in phases and combines their results, server-side. How to turn it on, how it differs from subagents, and the budget and limits to set first.

→
Making the call

Decision guides for the questions that actually matter.

BusinessDecision guide · 6 min

Anthropic's Forward Deployed Engineer learning path: what's in it and who can take it

Anthropic now has a free, self-paced Claude Forward Deployed Engineer learning path of about 9.5 hours. It is only open to Claude Partner Network members. Here is what it covers, how to get the same material for free if you are not a partner, and how it fits with the exams and the Frontier Academy residency.

→
BusinessDecision guide · 7 min

The four Claude certifications, and the rule that blocks most people

Anthropic runs four paid, proctored Claude certification exams through Pearson, and you can only sit them if you work at a Claude Partner Network company. Here is what each exam covers, how to prepare for free, and how they differ from free Academy badges and the Frontier Academy residency.

→
BusinessDecision guide · 7 min

Showing AI ROI to your CEO — what to measure and how to report it

Your CEO doesn't want a technology update. They want to know if the investment is working and whether to do more. Three types of evidence actually work: time saved, error rate improvement, and throughput. Here's how to measure them and how to present them.

→
Decision guide · 7 min

Bringing Claude to your team when you're not the decision-maker

You use Claude. You can see the value. But you don't run the team and you can't mandate anything. Here's the three levers you actually have and the moves that work.

→
Decision guide · 15 min

What AI Is Actually Doing to Your Job

Block is eliminating middle management. Altman and Amodei predict the first billion-dollar one-person company. 36% of B2B companies already cut their SDR teams. The future of work isn't theoretical — it's playing out role by role, with specific data, right now.

→
BusinessDecision guide · 7 min

Where to start with AI on your team

Most teams should start with AI, and most should start smaller than they think. How to find the one boring, frequent task that proves the value in 30 days, and which tasks to leave alone for now.

→
Decision guide · 8 min

How HR teams are actually using Claude

From job description drafting to performance review prep — the practical applications that save HR time without creating compliance risk.

→
ToolsDecision guide · 5 min

Claude Code: what it is and whether your engineering team should use it

Claude Code is a different product from Claude.ai — it is an agentic coding tool that runs in the terminal. Here is what it does and when it makes sense.

→
FoundationDecision guide · 5 min

When not to use Claude

Claude is genuinely powerful. It is also genuinely wrong for certain kinds of work. Knowing the difference is as important as knowing what it does well.

→
BusinessDecision guide · 6 min

Which Claude model should your team use?

The November 2026 lineup: Fable 5.2, Opus 5.5, Sonnet 5.5 and Haiku 5.5. How to pick, why Sonnet 5.5 is the right default for most work, and why tuning effort usually beats switching models.

→
AgentsDecision guide · 5 min

Claude Managed Agents: what they are and when your organization should use them

Managed Agents run Claude on long, multi-step jobs in Anthropic's cloud, so you don't build the infrastructure. You pay normal token rates plus $0.08 per session-hour while an agent runs. Still in beta. Here's who it suits, what it costs and how to start.

→
ToolsDecision guide · 4 min

Prompt caching: why it matters when you're building with Claude at scale

If your application sends the same long system prompt on every request, you're paying to re-process it every time. Prompt caching stops that.

→
ToolsDecision guide · 6 min

Connectors and Skills: connecting Claude to your team's work

Connectors let Claude reach the tools your team already uses. Skills teach it how your team does recurring work. What each one does, which to turn on first, and how to keep it manageable.

→
ToolsDecision guide · 5 min

What MCP actually means for your business (it's not just for developers)

The Model Context Protocol sounds technical. The practical implication is simple: AI tools can now connect to your actual systems in a standardised, safe way. Here's what that means for how you work.

→
ToolsDecision guide · 5 min

How to set up Claude Projects for your team (and what most people miss)

Projects are the most underused feature in Claude. Here's how to configure them so your whole team gets consistent outputs — not whatever each person happens to type.

→
RetrievalDecision guide · 5 min

Do you actually need RAG? The decision most operators get wrong

Most teams jump to RAG because it sounds like the right answer. Half of them didn't need it. Here's how to know which situation you're in — before you build anything.

→
EvaluationDecision guide · 6 min

How to know if your Claude integration is actually working

Most teams go live on gut feel and find out six weeks later that Claude has been quietly giving wrong answers. Here's how to know before that happens — without being an engineer.

→
ToolsDecision guide · 5 min

Five habits that separate operators who get results from those who don't

The gap between people who get consistent value from Claude and people who don't isn't intelligence or skill — it's four habits most people never develop. Here's what effective Claude users actually do differently.

→
What goes wrong

The failure patterns that catch most teams off guard.

EvaluationWhat goes wrong · 5 min

Why AI still isn't reliable enough to run on its own

AI is brilliant most of the time and makes strange mistakes the rest. That gap, not intelligence, is why whole jobs still aren't automated. Here is why it happens and how to pick work AI can do reliably today.

→
BusinessWhat goes wrong · 6 min

Why the skills you build stop getting used

Most teams build more skills than they use. The inventory grows; the invocation count per skill falls. Here's why skills die after the first week — and what to do instead.

→
BusinessWhat goes wrong · 7 min

Six metrics that tell you if Claude Cowork is actually working

Most teams measure adoption by asking "is anyone using it?" That question misses everything that matters. Here are the six numbers that tell you whether your Cowork rollout is working — and what each one is hiding when it looks fine.

→
BusinessWhat goes wrong · 8 min

Getting your team to actually use the agent — the change management problem nobody warned you about

Building the agent is the easy part. Getting people to use it is where most Agent Operators fail. Three types of resistance — trust, speed, job fear — each with a different fix. And one thing that kills adoption faster than anything else.

→
BusinessWhat goes wrong · 9 min

The month-4 problem: when Claude adoption quietly stops

Most teams who roll out Claude see strong early results and a quiet decline by month 4. It's not that Claude stopped working — it's that the rollout stopped. Here's what actually happened, and what to do about it.

→
What goes wrong · 6 min

Why your CLAUDE.md stops working — and how to keep it accurate

Most teams set up CLAUDE.md once and never touch it again. Three months later, Claude is ignoring parts of it, following instructions that no longer apply, and producing inconsistent output for reasons nobody can identify.

→
What goes wrong · 8 min

Why Claude keeps feeling inconsistent — and the actual fix

Claude isn't being random — inconsistency almost always has a specific cause you can find and fix. Memory closed part of the gap; here are the four causes that remain, in order of how often they appear.

→
BusinessWhat goes wrong · 5 min

What AI actually cannot do

Claude now searches the web, remembers across sessions, reads your files through connectors and runs code. Here is what it still genuinely cannot do, and why the remaining limits are about judgment, not features.

→
EvaluationWhat goes wrong · 6 min

What to tell clients about AI (and what not to)

The wrong AI conversation with a client creates a problem you'll spend months managing. The right one positions you as the person who gets it before everyone else does. Here's the script for both scenarios.

→
BusinessWhat goes wrong · 7 min

What goes wrong when founders build AI products

The failure modes for AI startups are specific and predictable. Most of them have nothing to do with the AI.

→
ToolsWhat goes wrong · 5 min

Why RAG implementations fail (and how to avoid the most common mistakes)

RAG is one of the most powerful things you can build with Claude. It's also where a lot of teams get stuck. Here are the failure patterns worth knowing before you start.

→
FoundationWhat goes wrong · 5 min

The hallucination patterns that catch operators off guard

Everyone knows AI can make things up. What surprises people is which specific situations trigger it — and how confident Claude sounds when it does.

→
ToolsWhat goes wrong · 5 min

Why your first AI pilot probably failed

Most AI pilots don't fail because the AI wasn't good enough. They fail for three very predictable reasons — none of which are technical.

→
AgentsWhat goes wrong · 6 min

Why most AI agent pilots fail in the first month

Building an AI agent that demos well is easy. Building one that works reliably in production is hard. The gap between the two is almost always one of the same five problems.

→
PromptWhat goes wrong · 5 min

The system prompt mistakes that make Claude worse, not better

More instructions don't mean better results. Most system prompts fail in one of five predictable ways — and fixing them is usually the highest-leverage thing you can do to improve your Claude integration.

→
In practice

What it actually looks like when teams implement AI.

In practice · 9 min

What using Claude actually looks like for a solo founder

The founders who use AI well don't use it for everything — they use it for the three tasks that used to eat half their week. Here's what those tasks are and exactly how the workflow runs.

→
In practice · 7 min

What using Claude actually looks like for an ops manager

Operations work is mostly translation: turning messy reality into clear documentation, turning vendor conversations into decisions, turning incidents into processes. Here is where Claude actually fits.

→
In practice · 8 min

What using Claude actually looks like for a marketing manager

Where Claude genuinely saves hours for marketing managers, where it falls flat, and what the actual workflow looks like.

→
In practice · 8 min

What using Claude actually looks like for a CS manager

A CS manager who uses Claude well can do meaningful work on renewals, QBRs, and escalations in the gaps between other work. Here's what that workflow actually looks like across a full day.

→
BusinessIn practice · 6 min

Using Claude for customer discovery: what works and what makes it worse

Customer discovery is the one job where Claude is most dangerous if used wrong. Here's how to use it to prepare better, synthesize faster, and avoid the trap of letting it replace the conversations.

→
BusinessIn practice · 5 min

The weekly review with Claude: a system for actually thinking about your week

A weekly review sounds like a productivity cliché — until you do one with Claude. Here's the version that takes 20 minutes and actually changes what you do the following week.

→
BusinessIn practice · 7 min

Getting your first ten customers for an AI product

Distribution is the hard part. The ten moves that actually work at the earliest stage — before you have brand, before you have case studies, before you have anything except the product.

→
BusinessIn practice · 5 min

How to validate your startup idea using Claude (without fooling yourself)

Claude can't tell you if your idea is good. It can find the weak assumptions before you build. Ask it to argue against the idea, answer five questions, and rehearse customer interviews, then check everything with real people.

→
BusinessIn practice · 6 min

How HR teams use Claude to make onboarding actually work

New hires spend their first week confused and HR spends it answering the same 40 questions. Here is the workflow that fixes both — without building a chatbot.

→
BusinessIn practice · 6 min

How CS managers use Claude to prepare for QBRs and renewals

QBR prep used to take half a day per account. Here is the workflow that gets it to 45 minutes — without cutting corners on the things that actually matter.

→
BusinessIn practice · 6 min

Claude for engineering teams: beyond the obvious

Engineers are often the last team to adopt Claude, and the first to find the most interesting uses once they do. The field note on what actually works — beyond autocomplete.

→
ToolsIn practice · 5 min

What AI actually looks like for a data and analytics team

Data teams have a counterintuitive relationship with Claude — it is not about the analysis, it is about everything around it.

→
BusinessIn practice · 5 min

What AI actually looks like for a legal team

Legal has real limits with AI — and real opportunities. Here is where Claude fits in a legal context, and what should stay out of scope.

→
BusinessIn practice · 5 min

What AI actually looks like for a product team

Product managers spend a disproportionate amount of time writing. Here is where Claude changes that — and how to set it up so it actually fits how product work gets done.

→
BusinessIn practice · 5 min

What AI actually looks like for a finance team

Finance teams deal with high-stakes, high-precision work. Here is where Claude genuinely helps — and where it has no place.

→
BusinessIn practice · 5 min

You've been asked to set up Claude for the company. Start here.

The first two weeks for whoever owns a Claude rollout, as of November 2026: learn how each team works before you configure anything, set the few controls that matter on day one, and know what a good first month looks like.

→
BusinessIn practice · 6 min

What AI actually looks like for an operations team

Ops has more to gain from AI than almost any other function — but the use cases look different to what most people expect.

→
BusinessIn practice · 6 min

What AI actually looks like for a sales team

Not "AI will write your emails." What sales teams are genuinely using Claude for, what works, and the one thing most reps get wrong.

→
BusinessIn practice · 5 min

How to actually evaluate whether your AI rollout is working

Most AI rollout evaluations are either too vague ("the team likes it") or too technical (automated test suites that miss what users actually care about). Here's what works.

→
AgentsIn practice · 5 min

When Claude starts doing the work: what AI agents look like in practice

An agent isn't just a chatbot that can click buttons. It's a fundamentally different relationship between a human and an AI. Here's what that looks like when it's working.

→
EvaluationIn practice · 6 min

Running your first AI pilot: a 30-day plan

Most AI pilots succeed technically and fail politically. The evidence exists — it just wasn't collected in a way anyone can act on. Here's how to design a pilot that produces results your organization will actually use.

→
ToolsIn practice · 7 min

Using Claude for customer support: what actually works

Customer support is the most common first AI use case for a reason — and the place where the most teams get burned. Here's what a working implementation looks like, and what the common shortcuts miss.

→
The concepts

Clear explanations of the ideas behind the tools.

BusinessHistory · 3 min

Anthropic is public: what the IPO means for Claude users and IT teams

Anthropic listed on Nasdaq as ANT on November 19, 2026, after pricing its IPO at $83 a share and raising $81.3 billion. For people who use Claude at work, almost nothing changes day to day. Here's what does, and what to do with it.

→
ToolsHow it works · 5 min

Computer use on Claude Team and Enterprise: what admins should set up first

Computer use lets Claude see a person's screen and work in desktop apps. It's in beta on Team and Enterprise, off by default, and has no sandbox. Here's what it can reach, the settings that limit it, and a safe way to roll it out.

→
ToolsHow it works · 4 min

Open your apps inside Claude: how interactive connectors work

Since November 10, 2026, some connected tools (Asana, Canva, Notion, Confluence and others) can open beside your Claude chat or full screen, and Claude can edit them while you watch. Here's which apps, how to start, and what admins should check.

→
ToolsHistory · 3 min

What changed in Claude this week

A short weekly note on what changed in Claude for admins and developers, and what to do about it. This week: Anthropic went public, published an FDE learning path, computer use reached Team and Enterprise, the old Skilljar course site is closing, and two things retire on November 30.

→
BusinessHistory · 6 min

Where is AI heading? Five shifts to plan for in 2027

AI is moving from chat answers to agents that do work on their own, while prices keep falling and AI tools turn into a full office suite. Here are the five shifts from the second half of 2026 that matter most, and what each one means for your team.

→
BusinessHow it works · 5 min

Claude Team plan: price, seats and what's included (2026)

Claude Team costs $20 per seat per month billed annually ($25 monthly), or $100 for a Premium seat with 5x the usage. It is for 2 to 150 people and includes Claude Code, Cowork, SSO and admin controls. What you get, what you don't, and who it's right for.

→
ToolsHow it works · 5 min

Chat and Cowork merged on Claude Enterprise on November 16: the admin checklist

Since November 16, 2026, the unified chat and Cowork experience is on by default for Claude Enterprise organizations that hadn't chosen. Conversations start as chats and move into a cloud sandbox when they need code or files. Here is what changed, who can't turn it on, and the settings to check now.

→
EvaluationHow it works · 10 min

Enterprise Frontier Safeguards: the fix for "we need zero retention, but we also need misuse detection"

Claude Fable 5 shipped with a 30-day data retention requirement so Anthropic could detect misuse spanning multiple sessions. That locked out every customer whose compliance position depends on zero data retention. On September 1, 2026 Anthropic announced Enterprise Frontier Safeguards, which moves the monitoring data into the customer’s own cloud account under their own keys and sends detections to the customer’s security team instead of Anthropic’s. Here is how it works and what to do about it now.

→
BusinessWhat's missing · 15 min

What Claude Academy doesn't teach you

Anthropic's 355 free resources are the best product training in the industry. There are still nine things a vendor course structurally cannot cover, and they are the things that consume an AI deployment: vendor choice, failure modes, budget fights, deprecations, and the career itself.

→
BusinessHow it works · 9 min

Claude, Codex, or Cursor: choosing your AI platform in 2026

Three serious AI agent platforms, three different strengths. A decision framework for operators and IT teams choosing where to standardize — without the hype.

→
InfrastructureHow it works · 7 min

Keeping your agent costs under control as you scale

Your Claude bill went from $200 to $2,000 and you can't explain why. The four cost drivers — bloated system prompts, unnecessary context loading, high failure rates, and no usage monitoring — each have fixes. Cost per task is the metric that matters, not total spend.

→
BusinessHow it works · 10 min

Your first 90 days as an Agent Operator — what to build, in what order

Most people handed AI responsibility try to do everything at once and ship nothing reliable, or wait for a perfect plan and never start. The 90-day path is simpler: one team, one workflow, one agent that actually works. Then you expand.

→
BusinessConcept · 9 min

What is an AI Agent Manager (a.k.a. Agent Operator)? The role Levie says 500,000 companies will hire for

The person who runs AI agents inside a company is the fastest-emerging role in enterprise AI — call it AI Agent Manager, AI Ops Manager, or Agent Operator. Aaron Levie predicts 500,000 to 1 million of these jobs. Here is what the role actually involves, and why most companies already have this person without a title for it.

→
BusinessHow it works · 10 min

How Companies Actually Adopt AI: The Six Phases

Most companies think AI adoption is a switch you flip. It isn't. It's a progression — six distinct phases, each unlocking capabilities the last one couldn't. Here's what they are, what separates them, and which phase you're probably in.

→
How it works · 4 min

Why starting a new chat almost always saves your Claude limits

Every message makes Claude reread the whole chat, so ten questions in one long chat cost about 5.5 times as much as ten fresh chats. Start a new chat for each new task, keep repeated context in a Project, and pick the right model and effort.

→
AgentsConcept · 4 min

Advisor tool: pairing a fast executor with Opus-level judgment

The Advisor tool runs a fast model for most tasks while escalating complex decisions to Opus — combining speed and depth in a single agent workflow.

→
Concept · 3 min

Monitor tool: real-time background process streaming in Claude Code

The Monitor tool spawns a background process and streams its stdout line-by-line into the conversation without blocking Claude Code's main thread.

→
Concept · 3 min

Ultraplan: Claude Code's comprehensive planning mode

Ultraplan generates a detailed implementation plan before writing any code — useful for large multi-file changes where a wrong direction is expensive.

→
How it works · 6 min

Your manager said yes. Now what? The first 48 hours of a Claude rollout

Approval is not adoption. What to do in the window between 'we can use this' and 'we actually use this' — before momentum stalls and inertia wins.

→
BusinessHow it works · 9 min

How to build a business case for Claude at your company

Your manager doesn't need an AI pitch — they need a staffing and efficiency argument with AI as the mechanism. Here's how to write it so leadership can say yes.

→
BusinessHow it works · 8 min

How to get IT to approve your Claude rollout

IT isn't the enemy of your Claude rollout — they're the ally you haven't briefed yet. Here's exactly what IT needs to see before they can say yes, and how to give it to them without triggering a six-month procurement cycle.

→
BusinessHow it works · 6 min

Running Claude after the rollout: the ongoing admin workload

Most admin guides cover getting Claude set up. This one covers what happens after: the recurring work, the common incidents, the governance tasks, and what a realistic monthly admin time commitment looks like for a 100-600 person company.

→
BusinessHow it works · 6 min

Setting up a shared Claude Project for your team

If every person on your team sets up Claude from scratch, they will each get different results and most will give up. Here is how to give your team a consistent starting point — whether you have admin access or not.

→
BusinessHow it works · 5 min

Your first week with Claude at a new job

Most people's first week with Claude follows the same pattern: one good result, one confusing result, and a vague sense it's not as useful as advertised. Here's how to break that pattern in the first three days.

→
BusinessHow it works · 5 min

AI usage policy template (copy, edit, send to legal)

A complete, one-page AI usage policy template for company-wide Claude deployments — with three variants: general company, professional services, and healthcare-adjacent. Fill in the bracketed fields and you have a policy ready for legal review.

→
BusinessHow it works · 6 min

How to get a skeptical teammate to actually try Claude

Skeptical colleagues aren't anti-AI — they've usually had a bad experience, heard about one, or watched a tool get mandated without explanation. Here's how to address all three without being annoying about it.

→
How it works · 8 min

What to actually put in your CLAUDE.md

Everyone says to set up CLAUDE.md. Nobody shows you what to write. Here are four real starting templates — for a solo project, a team backend, an agency client repo, and an ops/admin setup — with annotations explaining what each section does.

→
How it works · 6 min

CLAUDE.md vs. hooks: instructions Claude follows and rules it cannot break

CLAUDE.md tells Claude what you want. Hooks make certain behaviors guaranteed. Most teams only use one. Here is how to know which one you actually need.

→
How it works · 7 min

Claude Code for your team: the five decisions that actually matter

Most teams let one developer set up the .claude folder and never discuss it again. These are the decisions you should make together — and what breaks when you skip them.

→
How it works · 7 min

Claude + Salesforce: what actually works

The Salesforce connector gives Claude read access to your CRM. The workflows that get real use — account research, pipeline summaries, pre-call prep — are ones where the value is in combining what Salesforce knows with what Claude can reason about.

→
How it works · 10 min

The Claude playbook for CS teams

System prompts, ticket workflows, escalation patterns, and QBR prep — the operational guide for deploying Claude across a customer success team.

→
PromptHow it works · 6 min

Your Claude prompt isn't working. Here's how to fix it.

Most prompt failures come from one of five fixable problems. Here's a diagnostic framework for figuring out what went wrong — and how to fix it without starting from scratch.

→
EvaluationHow it works · 5 min

How to reduce Claude hallucinations: a practical checklist

Hallucination is Claude stating something false with confidence. You can't remove it, but you can cut it sharply: give Claude the source, let it say 'I don't know', turn on web search for anything recent, ask for citations, and check the facts that matter.

→
ToolsHow it works · 7 min

Claude for CRM workflows: using Claude with HubSpot

Claude doesn't integrate natively with HubSpot, but the right workflows make it your best CRM assistant. Here's how sales and CS teams actually use Claude alongside HubSpot.

→
ToolsHow it works · 9 min

Automating workflows with Claude and Zapier

Zapier connects Claude to almost any tool you already use — without writing code. Here are the automations worth building, how to set them up, and what to watch for.

→
ToolsHow it works · 7 min

Setting up Claude in Slack: what to configure and what to skip

Claude works natively inside Slack through a built-in integration. Here's what it actually does, how to set it up properly, and whether it's worth using for your team.

→
PromptHow it works · 6 min

How to write a good prompt

Most prompt problems aren't caused by bad AI — they're caused by the same three things: no role, no context, no constraint. Here's how to fix all three in under two minutes.

→
BusinessHow it works · 5 min

Using Claude to declutter your digital life

Your Downloads folder, your desktop, your bookmarks, your subscriptions — the digital clutter that accumulates until your computer feels like a junk drawer. Here's how Claude helps you actually deal with it.

→
AgentsHow it works · 6 min

How to give Claude precise instructions when using connectors

Vague instructions get vague results. The difference between "find me that doc in Notion" and an instruction that actually works — every time.

→
BusinessHow it works · 7 min

What executives actually need to know about AI at work

You're not implementing it yourself — but you're approving the budget, setting expectations, and accountable for the results. Here's the executive-level view: what to ask, what to expect, and where things go wrong.

→
BusinessHow it works · 5 min

How to sequence a Claude rollout across multiple teams

Rolling out to 10 teams at once is a recipe for chaos. Here is the sequencing strategy that works — who to start with, how to expand, and what to do when a team is struggling.

→
BusinessHow it works · 6 min

Security and privacy for Claude admins: what you need to know

Before you roll Claude out to your team, you need to understand what Anthropic does with your data — and what your responsibilities are. Here is the non-alarmist version.

→
ToolsHow it works · 5 min

MCP for operators: what it means and when you need it

MCP is the plumbing that lets Claude connect to anything. Here is what operators need to understand — and when it becomes relevant for your organisation.

→
ToolsHow it works · 6 min

Claude Artifacts in 2026: docs, slides, dashboards and small apps

Artifacts were rebuilt in September 2026. They are now living docs, slide decks, designs, sheets, whiteboards, data dashboards and small apps that start private, can be shared inside your company, and export to Word, PowerPoint and PDF. What each type is for, what each plan gets, and the sharing rules to know.

→
FoundationHow it works · 5 min

Effort: how deeply should Claude think?

Extended thinking as a toggle is gone on current models — Claude Opus 5, Sonnet 5 and Fable 5 think by default and adaptively, and budget_tokens is not accepted. The control that replaced it is `effort`, which governs total token spend including tool calls. Here's when to raise it, when to lower it, and the two behaviours that will bite you.

→
FoundationHow it works · 5 min

The context window in practice: what it means for how you work

The context window shapes what Claude can and can't do in any given conversation. Here is how to work with it.

→
BusinessHow it works · 6 min

The human side of rolling out AI at your company

Getting Claude configured is the easy part. Getting people to actually change how they work is harder. Here is what that looks like when done well.

→
FoundationHow it works · 6 min

Prompt engineering for operators: what actually matters

Most "prompt engineering" advice is either too academic or too simplistic. Here is the practical version — the five things that reliably improve outputs.

→
BusinessHow it works · 6 min

How to actually measure the ROI of Claude at your company

The problem with AI ROI isn't that it's hard to measure — it's that teams measure the wrong things. Here's what to track instead, and how to present it in a way leadership will actually act on.

→
FoundationHow it works · 7 min

How to write a system prompt that actually works

The system prompt is the most powerful thing you control in Claude. Most people write them once, poorly, and wonder why outputs are inconsistent. Here's the method.

→
BusinessHow it works · 6 min

How to write an AI usage policy your team will actually follow

Most AI usage policies are either too vague to be useful or so restrictive they get ignored. Here is the framework that actually works.

→
BusinessHow it works · 5 min

How to structure Claude Projects across your whole organisation

Make one shared Project per team and use case, name them '[Team] — [Use case]', give each one an owner, and audit them every quarter. Here is the naming pattern, the instructions template and a starter map.

→
BusinessHow it works · 5 min

Free, Pro, Max, Team or Enterprise: which Claude plan do you need?

Claude's plans as of November 2026, in plain terms: what each costs, who it is for, and the simple rules for picking one for yourself or your company.

→
ToolsHow it works · 5 min

When to use Deep Research and how to get the most from it

Deep Research is a different tool from web search — it runs longer, uses more tokens, and is worth it for specific questions. Here is when to use it.

→
ToolsHow it works · 5 min

Claude Memory: what it remembers, how to use it, and how to manage it

Claude now remembers things about you across conversations. Here is how it works, what to tell it to remember, and how to keep it useful.

→
ToolsHow it works · 4 min

Claude connectors: which to turn on, which to leave off, and why

Connect only the tools people use every week. Extra connectors make answers slower and noisier, and every connector sees what the connecting person can see. A short admin checklist, plus what changed in November 2026 now that some apps open inside Claude.

→
ToolsHow it works · 5 min

Claude Skills: what they are, which to enable, and when to use them

Two different things get called Skills, and the confusion costs real time. Tools are what Claude can reach — web search, code execution, file creation. Skills are folders of instructions that teach Claude how your organisation works. Which to configure where, and why the leverage is in the ones you write yourself.

→
BusinessHow it works · 6 min

How to minimise your Claude token usage without sacrificing quality

Tokens are what you pay for. The practical ways to use fewer of them, from how you prompt to which model and effort level you choose. Updated for the November 2026 models.

→
BusinessHow it works · 5 min

Step-by-step: researching a prospect with Claude before a call

A concrete workflow for turning 30 minutes of pre-call research into 5 minutes — without losing the signal that makes a call go well.

→
ToolsHow it works · 4 min

How tool use works: what happens when Claude calls a function

Tool use is the mechanism that lets Claude take actions — call APIs, run code, search files — instead of just generating text. Here's exactly what happens when Claude uses a tool.

→
FoundationConcept · 3 min

Adaptive thinking: how Claude decides how hard to think

Claude doesn't apply the same effort to every question. Here's what adaptive thinking is, how it works, and why it matters for the outputs you get.

→
FoundationConcept · 5 min

When a well-crafted prompt isn't enough

Fine-tuning is how you train a model on your specific data to change its behavior at a deeper level than prompting can reach. It's powerful — and often unnecessary. Knowing which situation you're in saves a lot of time.

→
FoundationConcept · 4 min

The unit everything in AI is priced and measured in

Tokens are how language models read and write text — and how every AI API charges you. Understanding them turns abstract pricing into something you can predict and control.

→
FoundationConcept · 4 min

The dial between predictable and creative

Temperature controls how much Claude surprises you. Turn it down for consistent, focused answers. Turn it up for more varied, exploratory ones. Knowing when to do each is a real skill.

→
EvaluationConcept · 5 min

The problem of making AI do what you actually mean

Alignment is the core challenge of AI development: building systems that reliably do what humans intend. It's harder than it sounds, and understanding why helps you build better applications today.

→
InfrastructureConcept · 3 min

Why Claude starts talking before it's finished thinking

Streaming sends Claude's response token by token as it's generated, instead of waiting until the full response is ready. The difference in perceived speed is significant — and the implementation is simpler than you'd expect.

→
FoundationConcept · 5 min

Why AI gets confident things wrong — and how to design around it

Hallucination isn't a bug that gets patched. It's a structural feature of how language models work. Understanding why it happens is the first step to building applications that aren't derailed by it.

→
InfrastructureHow it works · 4 min

Pay for your context once, not every time

Prompt caching is Claude's way of remembering the expensive part of a conversation so you don't have to re-send — and re-pay for — the same context on every request.

→
FoundationConcept · 5 min

The engine under everything

A large language model is what Claude is at its core — and understanding how it works changes how you think about everything else in AI.

→
AgentsConcept · 5 min

How Claude reaches beyond the conversation

Tool use is the mechanism that turns Claude from a text generator into something that can actually do things — search the web, run code, query your database, send messages.

→
FoundationConcept · 5 min

Why Claude has values instead of just rules

Most AI safety is a list of don'ts. Constitutional AI is the method Anthropic used to teach Claude to reason about right and wrong — the same way you'd want a thoughtful colleague to.

→
RetrievalConcept · 5 min

How to give Claude a memory it doesn't have by default

RAG is the most practical technique in AI engineering — and the most misnamed. It's not magic. It's just giving the model the right pages of the book before it answers.

→
AgentsConcept · 5 min

When Claude stops answering and starts doing

There's a clean line between a model that responds to questions and one that takes actions in the world. Understanding that line is the most important thing to know about building with AI right now.

→
PromptConcept · 4 min

How to brief Claude before the conversation starts

The system prompt is where you stop asking Claude to be general-purpose and start making it yours. Most operators underuse it.

→
FoundationConcept · 5 min

The whiteboard every AI conversation shares

Context window is the single number that shapes everything about how Claude thinks with you — and most people are using only a fraction of it.

→