Team knowledge
Turn one person's best prompt into a skill the whole team can use
How to turn one person's best AI prompt into a shared team skill: capture the context, write the steps, add examples, test it and give it an owner.
Author
David McGuckin
Co-founder of Shane and Opinly. Writes about how teams work with AI, and what gets lost between the tools.
Team knowledge
What leaders should know about the AI their teams use
What leaders should know about the AI their teams use: which tools people use, what context goes in, and whether output follows company decisions.
AI at work
Why every AI chat starts from zero (and what it costs your team)
AI chats start from zero because your team's context lives outside the tool. Here is what that costs, where AI memory falls short, and how to fix it.
Team knowledge
The handover problem: keeping context when people change roles
The handover problem: when people change roles, the reasons behind their work leave too. Here is what gets lost, a checklist, and how to fix it.
AI at work
Shadow AI: why workers bring their own AI, and what to do about it
Gartner found 88% of workers with enterprise AI also use personal AI tools. Here is why shadow AI happens, the real risks, and a six-step plan to fix it.
Team knowledge
Meeting notes are not memory: from transcripts to decisions
Meeting notes record what was said, not what was decided. How to turn AI transcripts and summaries into decisions your team and AI tools can find.
AI at work
The hidden cost of AI tool sprawl
AI tool sprawl costs more than licenses. It splits your team's context, prompts and decisions across tools. Here is how to audit, cut and connect.
Agents
Agent memory vs RAG vs fine-tuning: what your team actually needs
Agent memory, RAG and fine-tuning solve different problems. Here's what each one does, where it breaks, and which one your team actually needs.
Team knowledge
A shared brain for your team: what it is and how to start
A shared brain for your team holds the decisions, skills and context behind your work for people and AI tools. What it is and a four-week plan to start.
Agents
Guardrails for AI agents: permissions, sources and audit trails
A practical guide to AI agent guardrails: least-privilege permissions, trusted sources and readable audit trails, with a checklist for new agents.
AI at work
ChatGPT vs Claude vs Gemini: the model matters less than the context
ChatGPT, Claude or Gemini for work? All three are capable. The bigger difference comes from the context you give them. Here is a test and what to do.
Agents
How to brief a coding agent so it follows team decisions
How to write AGENTS.md, CLAUDE.md or Cursor rules and task briefs so coding agents follow your team's decisions, plus what to enforce with hooks.
AI at work
AI memory explained: what ChatGPT, Claude and Gemini remember
What ChatGPT, Claude and Gemini remember between chats, how to control it, and why personal AI memory does not help your team share context.
AI at work
Duplicate work: how teams end up solving the same problem twice
Why teams end up doing the same work twice, how AI chats and scattered tools make it worse, and six simple habits that stop duplicate work early.
Team knowledge
How to keep a decision log your team will actually use
A simple decision log format, what to log, and the habits that keep it current, so people and AI tools can find out why things are the way they are.
AI at work
How to write a team AI policy people will actually follow
A team AI policy people follow fits on one page, sorts rules by data type, and makes the approved path easy. Here is a template and a one-week rollout.
Team knowledge
Onboarding with AI: give new hires context on day one
How to use AI in onboarding: the context to prepare before day one, a sample first-week plan, and the problems to watch for with new hires and AI.
Agents
Context engineering for teams: a practical guide
A step-by-step guide to context engineering for teams: what to give AI tools and agents, where to keep it, who owns it, and how to keep it current.
Agents
How to give AI agents your company context without copy-pasting
Four ways to give AI agents your company context without copy-pasting: chat projects, repo instruction files, MCP connections and a shared source.
Agents
MCP explained for people who don't write code
A plain-English guide to MCP, the Model Context Protocol: what it is, how connectors work in Claude and ChatGPT, and what to check before connecting.
AI at work
Claude Projects vs ChatGPT Projects for teams: what each one shares
Shared ChatGPT projects let teammates see each other's chats. Shared Claude projects share files and instructions only. Here is how to pick for your team.
AI at work
AI for support teams: keep every answer on current policy
How support teams stop AI from quoting old policy: one source of record per policy, effective dates, a change checklist and clear rules for automation.
AI at work
How to tell if AI is actually helping your team
Measure AI at work with three numbers per workflow: time to a usable first draft, rework rate, and whether output follows your team's decisions.
Team knowledge
Knowledge silos in the AI era, and how to break them
Knowledge silos now hide in private AI chats and per-tool memory. Learn the five silo types, a one-hour audit, and practical fixes for your team.
Agents
Agent handoffs: passing context between AI agents without losing it
How to hand work from one AI agent to the next without losing the reasoning: a handoff template, a read-back check and a worked example you can copy.
AI at work
Stop AI sales drafts from quoting old pricing
Why AI sales proposals pick up old prices, and how to fix it: one dated price book, number-free templates and a quick pre-send check on every figure.
Team knowledge
How to write docs your AI tools can actually use
Most AI tools read your docs in short chunks, not whole pages. Seven rules, an example and a 30-minute audit to write docs that ChatGPT and Claude can use.
Agents
Context windows explained: why your AI forgets the start of a chat
A context window is what an AI model can see as it replies. Why long chats lose their start, what context rot is, and habits that keep key details in view.
Team knowledge
Async decision-making for remote teams that use AI
A simple async decision process for remote teams: one owner, a one-page proposal, a comment deadline and a recorded outcome, plus where AI helps and where it doesn't.
Team knowledge
A single source of truth for an AI-first team
What a single source of truth means when your team uses AI: what goes in it, the three rules that keep it current, and how to set one up in a week.
Team knowledge
Company knowledge needs an expiry date
Keep AI answers grounded in current information with review dates, named owners and clear rules for expired company knowledge.
Agents
What should an AI assistant do when two documents disagree?
Define how an AI assistant handles conflicting company documents, including authority, scope, effective dates and escalation.
Team knowledge
Build a project kickoff brief that survives the first meeting
A practical project kickoff brief covering the outcome, constraints, decisions and evidence that teammates and AI assistants need.
Agents
Test your AI knowledge base with questions your team actually asks
Build a small set of real questions to check whether your AI knowledge base retrieves current, relevant and permitted sources.
Team knowledge
Give every important document an owner, not just an author
Assign clear responsibility for maintaining shared company knowledge, including review, corrections and ownership changes.
AI at work
Build a brand voice brief an AI writer can follow
Turn vague brand adjectives into useful writing guidance with approved examples, audience context and a simple review checklist.
AI at work
Turn support feedback into product evidence without losing the detail
Create a useful path from customer support conversations to product decisions while preserving scope, evidence and uncertainty.
AI at work
A sales-to-success handoff should transfer promises, not just notes
A practical handoff for customer teams that records promised outcomes, contractual scope, open questions and the evidence behind each commitment.
Agents
How to keep client context separate when your agency uses AI
Organise AI work across multiple clients with clear access boundaries, separate source collections and checks before external delivery.
Team knowledge
Make incident reviews useful to the next person on call
Turn incident reviews into searchable operational knowledge with clear symptoms, tested actions, decision reasons and follow-up ownership.
Agents
Choose what belongs in an AI task brief
A simple way to select relevant context for an AI task without sending every document your team owns.
Team knowledge
Keep product requirements current while the work is changing
Track requirement changes so teammates and AI assistants can distinguish current scope, superseded decisions and unresolved proposals.
Team knowledge
A shared glossary can prevent surprisingly expensive AI mistakes
Define ambiguous company terms so AI assistants and teammates interpret metrics, customer stages and product language consistently.
Agents
Design an approval queue that keeps AI work moving
Make human review effective with clear approval triggers, decision-ready evidence and rules for changes after approval.
Agents
A source link is not proof: reviewing citations in AI answers
Check that citations in AI answers support the exact claim, apply to the current situation and are accessible to the intended reader.
Agents
Offboarding must include the context your AI tools can reach
Include AI connectors, shared projects and stored context in employee offboarding, using an explicit access inventory and verification.
AI at work
Plan the week with AI without turning guesses into commitments
Use AI to prepare weekly plans from current priorities, capacity and dependencies while keeping proposed work separate from commitments.
Team knowledge
Give customer interviews a useful life beyond the transcript
Organise customer research so teams and AI assistants can find evidence without confusing a participant quote with a general conclusion.
AI at work
Create an out-of-office brief that answers the next question
Prepare useful holiday coverage with current work, decision boundaries, key contacts and clear rules for what should wait.
Team knowledge
Retire old knowledge without erasing why a decision was made
Keep outdated documents out of current AI answers while preserving the historical context needed to understand earlier decisions.