# Stuart Leo > Context Leadership: leadership used to be direction; now it's context. Your people and your AI agents act on what they can see, so leading means writing the plan, the decisions and the standards down once, keeping them in one place, and improving them every time they're used. I've built two methods for it: Resolute for the company and the C² Method for the codebase. Both are free to read here. I'm the author of the Resolute series and the builder of Waymaker, and I work hands-on with leadership teams at a fixed rate (typically 12–36 months, 30-day notice both ways, no title). ## Work with me - [Work](https://stuartleo.com/work): Sanitised receipts from real engagements: the diagnosis, the work, the outcome. - [About](https://stuartleo.com/about): Background, track record, and how I work. - [Speaking](https://stuartleo.com/speaking): Talks on context leadership: leading people and AI agents at the same time. - [Contact](https://stuartleo.com/contact): Talk to Stuart. ## Two methods for context leadership Context lives in one place and compounds. Resolute does it for a company; the C² Method does it for a codebase. ### Resolute (for the company) - [Map](https://stuartleo.com/map): Where each method starts. - [Resolute](https://stuartleo.com/resolute): The method's home. - [Start here](https://stuartleo.com/resolute/learn): The reader's questions, each with its short answer. - [The framework](https://stuartleo.com/resolute/framework): The Resolute Leadership Curve, the 12 Questions and the foundational principles, assembled. - [The library](https://stuartleo.com/resolute/library): Every canvas and instrument in the method. - [The free diagnostic](https://stuartleo.com/resolute/assessment): What the diagnostic reads and how to run it. - [About the method](https://stuartleo.com/resolute/about) ### C² Method (for the codebase) - [C² Method](https://stuartleo.com/c2): The method's home. - [The method](https://stuartleo.com/c2/method) - [Start](https://stuartleo.com/c2/start) - [The docs](https://stuartleo.com/c2/docs): 19 docs articles. - [Concepts](https://stuartleo.com/c2/docs/concepts) - [FAQ](https://stuartleo.com/c2/faq) ## Books - [Books](https://stuartleo.com/books): The Resolute series overview. - [Resolute](https://stuartleo.com/books/resolute): Lead with purpose. Navigate disruption. Build indestructible organisations. (published) - [Resolute: Teams](https://stuartleo.com/books/resolute-teams): A practical playbook for managers and department heads who want to execute strategy, not just discuss it. (next) - [The Resolute Leader](https://stuartleo.com/books/the-resolute-leader): Become the leader your organisation needs. (forthcoming) - [Resolute Brand](https://stuartleo.com/books/resolute-brand): Build the character of your brand. (forthcoming) - [Resolute Board](https://stuartleo.com/books/resolute-board): Govern with substance, not ceremony. (forthcoming) ## Writing & podcast - [Articles](https://stuartleo.com/articles): Context Leadership: the C² Method for codebases, Resolute for companies, and essays on leading in the AI era. - [Commander in Brief](https://stuartleo.com/podcast): Weekly fifteen-minute podcast for the operator at the head of the table. - [Podcast RSS feed](https://stuartleo.com/feed.xml): Subscribe in any podcast app. - [Full content](https://stuartleo.com/llms-full.txt): The complete text of every article inlined in one file. ## Dictionary [The Dictionary](https://stuartleo.com/dictionary): every term in both methods. ### Resolute - [The Resolute Method](https://stuartleo.com/dictionary/resolute-method): Resolute is a thinking system for building a business that does not depend on you. - [The Resolute Leadership Curve](https://stuartleo.com/dictionary/resolute-leadership-curve): The six stages every organisation climbs: Idea, Identity, Calibrate, Maturity, Mastery, Initiate. - [The 12 Questions](https://stuartleo.com/dictionary/12-questions): Seven questions of leadership and five of management: the operating core of the Resolute method. - [The 7 Questions of Leadership](https://stuartleo.com/dictionary/7-questions-of-leadership): The seven leadership questions of the Resolute method. Creating change — refining the core of the organisation toward a better future state. - [The 5 Questions of Management](https://stuartleo.com/dictionary/5-questions-of-management): The five management questions of the Resolute method. Executing the present — taking the current plan and delivering the outcomes. - [Idea (stage)](https://stuartleo.com/dictionary/idea-stage): The Idea stage is not about having an idea — everyone has those. - [Identity (stage)](https://stuartleo.com/dictionary/identity-stage): Identity is the search for fit — finding your role in a market that did not ask for you. - [Calibrate (stage)](https://stuartleo.com/dictionary/calibrate-stage): Calibrate is where the business adds people, skills and systems — and discovers whether they cohere or fragment. - [Maturity (stage)](https://stuartleo.com/dictionary/maturity-stage): Maturity is where growth becomes repeatable and fundable — predictable ROI rather than lucky quarters. - [Mastery (stage)](https://stuartleo.com/dictionary/mastery-stage): Mastery is market leadership — and the discipline to refuse to coast. - [Initiate (stage)](https://stuartleo.com/dictionary/initiate-stage): Initiate is the decision to start the next curve while the current one is still strong — not after the slowdown shows. - [Vision & Purpose](https://stuartleo.com/dictionary/vision-and-purpose): Leadership question 1 of the Resolute method: What is our vision, is it driven by our purpose, and what is holding us back from reaching it? - [Market & Customer](https://stuartleo.com/dictionary/market-and-customer): Leadership question 2 of the Resolute method: What is our market, who is our ideal customer, what do they value, and what perceptions do we need to build? - [Strategy & Positioning](https://stuartleo.com/dictionary/strategy-and-positioning): Leadership question 3 of the Resolute method: What is our strategy, where is our growth focused, and how do we improve our positioning? - [Business Model & Value](https://stuartleo.com/dictionary/business-model-and-value): Leadership question 4 of the Resolute method: What is our business model, is it creating value, what metrics tell us this, and what practices improve our value proposition? - [Customer Experience](https://stuartleo.com/dictionary/customer-experience): Leadership question 5 of the Resolute method: What is our customer's experience, how do we acquire, retain and grow customers through our journey and promise, and what improvements need to be made? - [Employee Experience](https://stuartleo.com/dictionary/employee-experience): Leadership question 6 of the Resolute method: What is our employee's experience, how do we acquire, retain and grow talent through our journey and promise, and what improvements need to be made? - [Focus & Strategic Goals](https://stuartleo.com/dictionary/focus-and-strategic-goals): Leadership question 7 of the Resolute method: What are the one, two or three things that, if delivered this quarter or half, will shift the needle on the business? - [Plan & Metrics](https://stuartleo.com/dictionary/plan-and-metrics): Management question 1 of the Resolute method: What is our plan, and what metrics tell us if we are succeeding? - [Roles & Accountability](https://stuartleo.com/dictionary/roles-and-accountability): Management question 2 of the Resolute method: What roles does the plan require, and who is accountable for what? - [Goals & Outcomes](https://stuartleo.com/dictionary/goals-and-outcomes): Management question 3 of the Resolute method: What goals must each role achieve this quarter, half or year? - [Meetings & Problem-Solving](https://stuartleo.com/dictionary/meetings-and-problem-solving): Management question 4 of the Resolute method: What meetings do we need, and how do we solve problems together? - [Data & Measurement](https://stuartleo.com/dictionary/data-and-measurement): Management question 5 of the Resolute method: What data do we need to measure progress and steer the business? - [Character](https://stuartleo.com/dictionary/character): Who you are: the inner reality your thoughts, decisions and behaviour are rooted in — who you are when no one is watching. - [Values](https://stuartleo.com/dictionary/values): What you stand for: how you believe people ought to behave — the standard you decide by. - [Skills](https://stuartleo.com/dictionary/skills): What you can do: the craft of changemaking — strategy, communication, decision-making. - [Systems](https://stuartleo.com/dictionary/systems): What you build so it scales beyond you: the frameworks that scale skill across an organisation — plans, roles, goals, meetings, data. - [Real growth is earned, not bought](https://stuartleo.com/dictionary/real-growth-is-earned-not-bought): High-value growth is layered over time — each stage developing the character, skills and systems that become the foundation for the next. - [Lead people; manage things](https://stuartleo.com/dictionary/lead-people-manage-things): Leadership and management are different crafts. - [Values reveal character, character scales culture](https://stuartleo.com/dictionary/values-reveal-character-character-scales-culture): The values you live — not the ones on the wall — expose your real character. - [Skills scale systems, systems scale efficiency](https://stuartleo.com/dictionary/skills-scale-systems-systems-scale-efficiency): The right competencies at each stage build layer upon layer of institutional capability. - [Questions are more valuable than answers](https://stuartleo.com/dictionary/questions-are-more-valuable-than-answers): Great leaders are defined by the questions they ask, not the answers they hand down. ### C² Method - [P = aic²](https://stuartleo.com/dictionary/p-aic2): Productivity = AI × (Context × Code). A mnemonic, not a law of physics — the "squared" is the two Cs, not a literal exponent. Your output is the AI crew multiplied by the Context and Code you build around it. - [The two Cs](https://stuartleo.com/dictionary/the-two-cs): Context and Code — the two systems C² optimises, and the two letters in C². They multiply; if either is zero, productivity collapses. - [Contextbase](https://stuartleo.com/dictionary/contextbase): What guides: briefs, patterns, gotchas, decisions. Written as you work, committed to git, read by the AI before it acts. It compounds. - [Codebase](https://stuartleo.com/dictionary/codebase): What runs: the software itself. Richer context makes sharper code; cleaner code surfaces sharper context. - [Pilot / Crew](https://stuartleo.com/dictionary/pilot-crew): The human is the pilot — sets course, reviews, owns the quality bar. The AI is the crew — writes code, runs tests, manages files. - [Harness engineering](https://stuartleo.com/dictionary/harness-engineering): The layer C² operates at — the gather → act → verify loop. The three layers nest: prompt ⊂ context ⊂ harness, each containing the one before. C² is a harness methodology. - [The layer triage](https://stuartleo.com/dictionary/the-layer-triage): A diagnostic for what broke, not a stack of what you build: cannot operate → the environment · unreliable → the loop and its stop rule · the process is complex → the topology. Deliberately not the same three as prompt/context/harness. - [The Cascade](https://stuartleo.com/dictionary/the-cascade): The six-tier chain every piece of work flows through: Platform PRD → Feature PRD → Prompt Brief → Task → Session Brief → Release Note. It doesn't terminate — it closes back onto the PRD. - [Prompt Brief](https://stuartleo.com/dictionary/prompt-brief): The atomic build unit — where the pilot hands off to the crew. Interactive (pilot present) or Autonomous (pilot absent). One brief ≈ one pull request. - [Quality gate](https://stuartleo.com/dictionary/quality-gate): The six-item check — goal, scope exclusions, testable AC, non-goals, testing approach, definition of done — every brief passes before execution. - [Bank switch](https://stuartleo.com/dictionary/bank-switch): How a PRD compounds without hoarding: each version absorbs the last (v1.0 → v1.1 → v2.0), leaving one live artefact that says where the work is now. - [Node](https://stuartleo.com/dictionary/node): One agent doing one bounded job. In C² a node is a Prompt Brief, and the brief is its contract. - [Edge](https://stuartleo.com/dictionary/edge): What crosses between two nodes — one agent's output becoming another's input. "And then" is not an edge. Name it by the artefact, not the order. - [Surface](https://stuartleo.com/dictionary/surface): Everything an agent mutates or contends for — files, data, external resources, a deploy target. Two agents on one surface is the anti-pattern. - [The concurrency rule](https://stuartleo.com/dictionary/the-concurrency-rule): Agents may run concurrently exactly when no edge connects them and no surface is shared. The test is the surface, not the headcount. - [False independence](https://stuartleo.com/dictionary/false-independence): Two agents whose briefs never mention each other, colliding over a shared database, a rate-limited API, or one deploy target. A hidden edge. - [Fan-out / barrier](https://stuartleo.com/dictionary/fan-out-barrier): Independent nodes running at once is a fan-out. Where their results merge — the integration brief, the PR — is a barrier. A barrier makes everything wait for the slowest, so earn it. - [Isolation](https://stuartleo.com/dictionary/isolation): Stopping one node's mess reaching the others — a git worktree per agent. It isolates the filesystem and nothing else. - [The shape](https://stuartleo.com/dictionary/the-shape): The fifth part of a filed flight plan: which briefs are independent, which are joined by an edge, where the barrier sits, which edges get verified. - [Anchor](https://stuartleo.com/dictionary/anchor): The one signal that decides done, which no agent in the run can produce by asserting it. A test that ran. A query that returned rows. A deploy that resolved. - [Loop on evidence](https://stuartleo.com/dictionary/loop-on-evidence): "The agent says it's done" is not a stop condition. Neither is "the review passed" when the review read the builder's own account of the work. - [Frozen rule](https://stuartleo.com/dictionary/frozen-rule): A rule marked non-negotiable precisely because it's the one an optimiser would bend to win. Every frozen rule exists because it got bent once. - [Verified edge](https://stuartleo.com/dictionary/verified-edge): A result that gets an independent pass before it counts. Independence is mechanical: a different model, inputs the author can't control, and teeth. - [Flight Planning](https://stuartleo.com/dictionary/flight-planning): The gate between "I have a PRD" and "I'm running build sessions against it". Five parts: the line, the briefs, the journey, the shape, and an optional red line. - [Closing the Flight Plan](https://stuartleo.com/dictionary/closing-the-flight-plan): The landing gate. A filed plan is closed on arrival — the landing, the deviation, the anchor, the learning. Filing spends context; closing makes it. - [The three gates](https://stuartleo.com/dictionary/the-three-gates): Flight plan (per PRD, judgement) · pull request (per PR, correctness) · closing (per PRD, judgement). The outer two bookend the build under one owner. - [The sweep](https://stuartleo.com/dictionary/the-sweep): Clearing the previous cycle's findings at the bank switch — done by the next flight plan, not by the closing. - [The Router (router.md)](https://stuartleo.com/dictionary/the-router-router-md): The file your agent reads first — the living index of the contextbase. Named for your agent. Links rather than embeds. - [Knowledge index](https://stuartleo.com/dictionary/knowledge-index): The index of 03-knowledge the Router points to. The AI reads the index, not every file. - [Learn loop](https://stuartleo.com/dictionary/learn-loop): Capture discoveries fast during a session, then periodically consolidate them into 03-knowledge and the Router. - [Compaction](https://stuartleo.com/dictionary/compaction): Keeping the working context lean. C² does it three ways: the Session Brief, the Router, and the Learn loop. - [Lead agent](https://stuartleo.com/dictionary/lead-agent): Executes — reads context, writes code, manages git, writes briefs. One leads per codebase surface. - [Bench agent](https://stuartleo.com/dictionary/bench-agent): Reviews, never executes. Independent second opinion on PRDs, security, architecture. Budget-capped. - [Specialist agent](https://stuartleo.com/dictionary/specialist-agent): A scoped subagent for repeatable tasks — QA review, release notes, security review. - [WIP cap](https://stuartleo.com/dictionary/wip-cap): Max five in-progress PRDs. Anything above goes to backlog — forces completion before starting. - [Brief-before-active](https://stuartleo.com/dictionary/brief-before-active): A PRD can't go in-progress without at least one Prompt Brief. If you can't write a brief, it's a thinking document. - [Monthly PRD review](https://stuartleo.com/dictionary/monthly-prd-review): A 30-minute monthly pass: walk every in-progress PRD; force-move stale ones to backlog. ## Articles: Resolute - [Resolute vs EOS (Traction): two operating systems for a company](https://stuartleo.com/articles/resolute-vs-eos): Looking for an EOS alternative? How Resolute compares with EOS (Traction): tools, meetings, rollout, AI, and which suits your business. Fair, with sources. - [Canvases and Clarity Statements: wide, then narrow](https://stuartleo.com/articles/canvases-and-clarity-statements): A Resolute canvas opens a hard question with divergent thinking; a Clarity Statement closes it with convergent thinking. How the pair works, and how to run it. - [Resolute vs charismatic leadership: what scales](https://stuartleo.com/articles/resolute-vs-charismatic-leadership): Charismatic and resolute leadership are not opposites. Charisma is a trait; resolute leadership is a practice that leaves leaders behind. Here's the difference. - [Values reveal character, character scales culture](https://stuartleo.com/articles/values-reveal-character): The third Resolute principle explained: the values you act on show your character, and your character is what your culture copies as the business grows. - [How to run a leadership meeting that solves problems](https://stuartleo.com/articles/how-to-run-a-leadership-meeting): How to run a leadership team meeting that produces decisions, not status updates — the cadence, the agenda, and the one test, the Resolute way. - [Why most businesses stall as they scale](https://stuartleo.com/articles/why-businesses-stall-at-calibrate): Why most businesses stall at the same stage of growth — Calibrate — when what worked with the founder in every room breaks once they step away. - [Writing a vision statement a team can actually use](https://stuartleo.com/articles/writing-a-vision-statement): How to write a vision and purpose short enough to remember and sharp enough to steer by — with the Vision Canvas, the Resolute way. - [The Resolute Leadership Curve](https://stuartleo.com/articles/the-resolute-leadership-curve-a-primer): Growth emerges from navigating three tensions — leading vs managing, values vs character, skills vs systems. The Resolute Leadership Curve is the map. - [The Three Tensions](https://stuartleo.com/articles/the-three-tensions): Three permanent pulls underneath every growing business. The leader who learns to live inside them grows. The one who picks a side stalls. - [The Twelve Questions](https://stuartleo.com/articles/the-twelve-questions): Five questions for executing the present, seven for leading the future. How the Resolute Leadership Curve gets applied on a Tuesday. ## Articles: C² Method - [AGENTS.md vs CLAUDE.md: what Claude Code actually loads (tested)](https://stuartleo.com/articles/agents-md-vs-claude-md): AGENTS.md vs CLAUDE.md, tested in Claude Code 2.1.329: which file loads when both exist, how @AGENTS.md imports work, and the CLAUDE.local.md trap. - [Claude Code compaction ate my work: recovery and prevention](https://stuartleo.com/articles/claude-code-compaction-lost-context): Claude Code compaction lost context mid-task? Nothing on disk is gone. How to recover from git, your briefs and the session transcript, and how to prevent it. - [Claude Code hooks I actually run, and the one I turned off](https://stuartleo.com/articles/claude-code-hooks-i-actually-run): Claude Code hooks examples from a real repo: a SessionStart brief list, a SessionEnd worktree prune, a PostToolUse reminder, and the block I turned off. - [How to rescue a vibe-coded app without rewriting it](https://stuartleo.com/articles/how-to-fix-a-vibe-coded-app): How to fix a vibe coded app without a rewrite: freeze features, map it, add a router and contextbase, pin behaviour with tests, fix in small briefs. - [How to write a prompt brief an agent can run without you](https://stuartleo.com/articles/how-to-write-a-prompt-brief-an-agent-can-run-without-you): How to write instructions for an AI coding agent that runs unattended: standing approval, pre-flight reads, one item at a time, exact commands, and a real DoD. - [What goes in a session brief: a template and three real briefs](https://stuartleo.com/articles/session-brief-template-with-real-examples): A Claude Code session handoff template, section by section, with three real session briefs from my repos and what each part bought the next session. - [Task Master vs BMAD vs Agent OS: which fits your repo?](https://stuartleo.com/articles/task-master-vs-bmad-vs-agent-os): Task Master vs BMAD vs Agent OS: what each is, how it installs, what files it adds to your repo, licences, and who each suits. Checked on their own docs. - [The gotchas folder: the cheapest context your agent reads](https://stuartleo.com/articles/the-gotchas-folder): How to stop an AI agent repeating mistakes: a gotchas folder of one-file traps, how to name and write them, when to add one, and how the router points at them. - [How to customise the C² Method for your team and project](https://stuartleo.com/articles/customise-the-c2-method): C²'s folders are a starting shape, not a rulebook. What's load-bearing, how to adapt the rest to your team, and a worked example: adding a metrics folder. - [How to stop Claude Code losing context between sessions](https://stuartleo.com/articles/how-to-stop-claude-code-losing-context-between-sessions): Claude Code loses context when a session ends or compacts. What CLAUDE.md and auto memory keep, and the session-brief routine that carries the rest in git. - [Spec-driven development tools compared (2026)](https://stuartleo.com/articles/spec-driven-development-tools-compared): Spec Kit, Kiro, BMAD, Agent OS, Task Master and OpenSpec compared from their own docs: artefacts, workflow, agents, licence and who each one is for. - [Why Claude Code ignores your CLAUDE.md, and how to fix it](https://stuartleo.com/articles/why-claude-code-ignores-your-claude-md): Claude Code ignores CLAUDE.md rules when the file is too long, the rule is buried, or it needed a hook. Why it happens, and the router pattern that fixes it. - [The repo you hand over is a deliverable from day one](https://stuartleo.com/articles/the-repo-you-hand-over): A client repo is a deliverable from its first commit. The rule I keep for what context may compound there, and the near-miss that taught it. - [Closing the flight plan: the gate nobody runs](https://stuartleo.com/articles/closing-the-flight-plan): Flight Planning spends context. Closing is where context gets made. The landing gate, its four parts, and why it scales from a room to one person. - [Don't draw the graph on day one](https://stuartleo.com/articles/dont-draw-the-graph-on-day-one): Diagramming a big agent workflow before you have watched the work behave produces brittle structure. Why your contextbase is already the trace collection. - [Don't loop on confidence. Loop on evidence.](https://stuartleo.com/articles/dont-loop-on-confidence-loop-on-evidence): A system of agents checking each other's reports is consistent and unverified. Anchors, frozen rules, and what makes a result actually count as done. - [The pilot's bottleneck changes](https://stuartleo.com/articles/the-pilots-bottleneck-changes): The Pilot model was never static. Attention, then review throughput, then trust in the loop, then knowing what to automate. Four stages, four questions. - [The prompt brief is a node contract](https://stuartleo.com/articles/the-prompt-brief-is-a-node-contract): A fan-out returns twelve confident, unusable outputs unless every agent has a contract. What that contract specifies — and why the prompt brief already is one. - [The shape of the work is a graph, not a queue](https://stuartleo.com/articles/the-shape-of-the-work-is-a-graph): Work has a shape, and the shape is a graph. Nodes, edges and barriers in plain terms — and why your prompt briefs were always a fan-out. - [The two ladders of AI adoption](https://stuartleo.com/articles/the-two-ladders-of-ai-adoption): Risk of the work and agent count are orthogonal axes, and confusing them is why adoption advice keeps missing. The 2x2, and how to find where you sit. - [When can AI agents actually run in parallel?](https://stuartleo.com/articles/when-can-agents-run-in-parallel): Multi-agent vs single agent, decided by two questions: is there an edge, and is there a shared surface? When to fan out, sequence, or stay with one. - [Which layer broke your agent? Environment, loop, topology](https://stuartleo.com/articles/which-layer-broke-your-agent): At the 30-minute limit, name the layer that owns the failure before you escalate: the environment, the loop and its stop rule, or the topology. - [Your agent fleet forgets everything](https://stuartleo.com/articles/your-agent-fleet-forgets-everything): A fleet fans out, converges, prints an answer, and the shape that produced it evaporates. A field note on what makes an expensive run worth doing twice. - [Flight Planning: file the plan before you take off](https://stuartleo.com/articles/flight-planning-before-the-build): Flight Planning is the C² review where you file your plan — scope, briefs, and ETA — before an agent builds. What it is, who's in the room, and why. - [C² vs enterprise AI coding platforms](https://stuartleo.com/articles/c2-vs-enterprise-ai-platforms): Enterprise platforms sell governance, SSO and control for AI coding. C² gives you a method and context you own. What each is for, and where they meet. - [Context files vs fine-tuning for your codebase](https://stuartleo.com/articles/context-files-vs-fine-tuning): Want an agent that knows your codebase? You could fine-tune a model or write context files. Why context wins for most teams — cheaper, faster, and yours. - [Crawl, walk, run: adopting AI agents safely](https://stuartleo.com/articles/crawl-walk-run-adopting-ai-agents): Teams that jump straight to autonomous agents fail. The crawl-walk-run path that gets AI agents from first try to production work — without the wreckage. - [Defend against prompt injection in coding agents](https://stuartleo.com/articles/defend-against-prompt-injection): Prompt injection turns content your agent reads into commands it follows. Why coding agents are exposed, the real incidents, and the defences that hold. - [Document an inherited codebase with an agent](https://stuartleo.com/articles/document-a-codebase-with-an-agent): Inherited a codebase with no docs? How to have an agent draft the documentation, verify it, and grow a contextbase into a legacy project one change at a time. - [Greenfield vs brownfield: building with agents](https://stuartleo.com/articles/greenfield-vs-brownfield-with-agents): Starting fresh and working in a legacy codebase are different sports with AI agents. What changes, why brownfield is harder, and how to handle each. - [Least privilege for coding agents: scope the blast radius](https://stuartleo.com/articles/least-privilege-for-coding-agents): An agent can only do damage where you let it reach. How to apply least privilege to coding agents — file scope, command limits, no prod, sandboxes. - [Onboard to any codebase in hours with an agent](https://stuartleo.com/articles/onboard-to-any-codebase-with-an-agent): Understanding an unfamiliar codebase used to take weeks. An agent can guide you through it in hours — here's how to use one to get oriented fast. - [Onboarding a new dev with the contextbase](https://stuartleo.com/articles/onboarding-a-dev-with-the-contextbase): A field note on a new developer who got productive in a day instead of a fortnight, because the contextbase already held what usually lives in people's heads. - [PRD-first vs prototype-first with AI](https://stuartleo.com/articles/prd-first-vs-prototype-first): Should an agent write the spec or build the prototype first? The case for each, when a clickable prototype beats a document, and how C² uses both. - [Rolling C² out to my team: what stuck, what didn't](https://stuartleo.com/articles/rolling-c2-out-to-my-team): A field note on introducing C² to a team — the parts that caught on immediately, the parts that met resistance, and what I'd do differently. - [Keep secrets safe when coding with agents](https://stuartleo.com/articles/secure-secrets-when-coding-with-agents): An agent with shell access and secrets in scope is the worst-case setup. How to keep API keys and credentials out of an agent's reach — and out of its context. - [The Cascade: from PRD to Prompt Brief](https://stuartleo.com/articles/the-cascade-from-prd-to-prompt-brief): Big goals don't fit in one prompt. The C² Cascade breaks work from Platform PRD down to the Prompt Brief an agent can actually build. How the tiers fit. - [The legacy codebase the agent couldn't read](https://stuartleo.com/articles/the-legacy-codebase-the-agent-couldnt-read): A field note on pointing an agent at a ten-year-old codebase, watching it confidently misunderstand everything, and the context that finally let it help. - [The prompt injection I almost shipped](https://stuartleo.com/articles/the-prompt-injection-i-almost-shipped): A field note on an agent that read a malicious instruction buried in a dependency's docs, nearly acted on it, and what caught it before it shipped. - [The secret that leaked into context](https://stuartleo.com/articles/the-secret-that-leaked-into-context): A field note on an API key that ended up in an agent's context window, where it didn't belong, and the rule I keep now to stop it happening again. - [What is a PRD, and why agents need one](https://stuartleo.com/articles/what-is-a-prd-in-ai-development): A PRD (product requirements document) says what to build and why. Why AI agents need one more than human teams, what goes in it, and how to draft one. - [Why most AI agent pilots never reach production](https://stuartleo.com/articles/why-agent-pilots-never-reach-production): Most AI agent pilots never ship — and it's rarely the agent's fault. The real blockers are governance, context and trust, and how to clear them. - [Write acceptance criteria your agent can check itself](https://stuartleo.com/articles/acceptance-criteria-for-agents): The difference between an agent that drifts and one that self-verifies is acceptance criteria you can run. How to write briefs with criteria the agent checks itself. - [Agentic coding vs AI pair programming](https://stuartleo.com/articles/agentic-coding-vs-ai-pair-programming): Pair programming has the AI beside you, suggesting. Agentic coding has it running the loop while you direct. The difference, and which one you're doing. - [AI agent teams, explained: lead, bench, specialist](https://stuartleo.com/articles/ai-agent-teams-explained): When one agent isn't enough you reach for a team — but more agents on one problem makes things worse, not better. The roles that actually work, and why. - [Set up AI code review with a bench agent](https://stuartleo.com/articles/ai-code-review-with-a-bench-agent): An independent agent reviewing the work — not the one that wrote it — catches what the author misses. How to run a bench-agent review that adds signal. - [C² vs AWS AI-DLC: pilot versus approver at the gate](https://stuartleo.com/articles/c2-vs-ai-dlc): AWS AI-DLC and C² are the closest AI-native peers. The two telling differences: human as approver-at-gates vs pilot, and context as delivery vs investment. - [C² vs GUARDRAILS.md: safety that compounds](https://stuartleo.com/articles/c2-vs-guardrails-md): GUARDRAILS.md captures safety lessons so an autonomous agent stops repeating failures. A useful file — and how it relates to a contextbase that compounds. - [C² vs native rule files: when one CLAUDE.md isn't enough](https://stuartleo.com/articles/c2-vs-native-rule-files): CLAUDE.md, AGENTS.md and cursorrules are where everyone starts. An honest look at what a single rules file does well, where it breaks, and how C² extends it. - [C² vs spec-driven development: specs that persist](https://stuartleo.com/articles/c2-vs-spec-driven-development): Spec-driven development makes an executable spec the source of truth. C² agrees — and adds the part SDD leaves out: a contextbase that compounds across every spec. - [Context rot: how compaction keeps your agent sharp](https://stuartleo.com/articles/compaction-keep-the-context-window-lean): Context rot: every model degrades as its window fills. What it looks like, how I diagnosed it, and the compaction habits that keep the context lean. - [Context engineering, explained: the skill that replaced prompting](https://stuartleo.com/articles/context-engineering-explained): Context engineering is the discipline that overtook prompt engineering: curating what your AI agent knows before it acts. What it is, why it matters, and how to start. - [Context engineering for people who aren't engineers yet](https://stuartleo.com/articles/context-engineering-for-non-engineers): Context engineering is the skill of writing down what your AI agent needs to know so it acts well. A plain-English guide for builders from business, not CS. - [Context engineering vs RAG for coding agents](https://stuartleo.com/articles/context-engineering-vs-rag): RAG retrieves context on the fly; context engineering curates and keeps it. How they differ for coding agents, where each fits, and why a contextbase isn't RAG. - [Cursor vs Claude Code: why C² works with either](https://stuartleo.com/articles/cursor-vs-claude-code-which-fits-c2): Cursor or Claude Code or Codex — the tool debate misses the point. Why an agent-agnostic method means you can pick any, and switch without losing context. - [How to build software with AI agents: a starting guide](https://stuartleo.com/articles/how-to-build-with-ai-agents): A plain-English guide to building real software with AI coding agents — the loop, the context, and the habits that separate shipping from vibe-coding into a mess. - [How to stop your AI agent forgetting what it learned](https://stuartleo.com/articles/how-to-stop-your-agent-forgetting): AI agents forget when the session ends or the window fills, and the model never learns your project. The written-context fix that makes learning stick. - [How to write an AGENTS.md that agents actually follow](https://stuartleo.com/articles/how-to-write-agents-md): AGENTS.md (and CLAUDE.md) is the file your coding agent reads first. What belongs in it, a worked example line by line, and how to keep it lean. - [I ran five agents at once and regretted it](https://stuartleo.com/articles/i-ran-five-agents-at-once-and-regretted-it): A field note on spinning up five agents on one feature to go faster, the contradictory mess that followed, and what I got wrong for a year about why it failed. - [Parallel Claude Code agents with git worktrees](https://stuartleo.com/articles/parallel-agents-with-git-worktrees): Run parallel Claude Code agents in git worktrees: isolation, sequential merges, and the disk, cleanup and CI-minute costs that arrive once you do it for real. - [Prompt engineering vs context engineering for coding](https://stuartleo.com/articles/prompt-engineering-vs-context-engineering): Prompt engineering tunes the instruction. Context engineering curates what the agent knows. Why the second is the skill that now pays — and how C² operationalises it. - [How to run AI coding agents overnight, safely](https://stuartleo.com/articles/run-agents-overnight-safely): Unattended agents can ship real work while you sleep — or wreck things. The guardrails that make overnight runs safe: branches, scopes, cost caps, no prod. - [Subagents, MCP and skills: fitting tools into C²](https://stuartleo.com/articles/subagents-mcp-and-c2): Subagents, MCP servers, slash commands, skills — the agent harness has a lot of tools. How they fit a C² contextbase, and which to reach for without losing the plot. - [Test-driven development with AI agents](https://stuartleo.com/articles/test-driven-development-with-ai-agents): TDD turns an agent from hopeful to reliable: write the test first, let the agent go red-green-refactor at machine speed. How to run it, and what it needs. - [The 30-minute debug limit: when to stop the agent](https://stuartleo.com/articles/the-30-minute-debug-limit): An agent stuck on a bug will burn an hour going in circles. The pilot's move is a time limit and an escalation — here's how to set and use one. - [The CLAUDE.md that got too big](https://stuartleo.com/articles/the-claude-md-that-got-too-big): A short field note: my Router file bloated into an unreadable wall of rules. How I noticed, what I moved where, and the line-count rule I now keep. - [The overnight run that went wrong](https://stuartleo.com/articles/the-overnight-run-that-went-wrong): A field note on letting an agent run unattended overnight, waking to a branch full of confident damage, and the guardrails I never skip now. - [The Pilot model: directing agents instead of typing](https://stuartleo.com/articles/the-pilot-model-directing-ai-agents): The biggest shift in building with AI isn't the code the agent writes — it's that you stop being crew and start being the pilot. What that changes, in practice. - [The test that saved the refactor](https://stuartleo.com/articles/the-test-that-saved-the-refactor): A field note on a big agent-driven refactor that should have broken everything, and the test suite that turned a risky change into a boring one. - [I vibe-coded into a corner — here's the climb out](https://stuartleo.com/articles/vibe-coding-into-a-corner): A field note on letting an agent vibe-code a feature with no spec, the mess that followed, and how a brief with acceptance criteria turned it around. - [What is a contextbase? The asset that makes agents remember](https://stuartleo.com/articles/what-is-a-contextbase): A contextbase is the version-controlled folder of markdown your AI coding agent reads before it acts. What goes in it, why it compounds, and how to start one today. - [What is agentic coding? Beyond autocomplete](https://stuartleo.com/articles/what-is-agentic-coding): Agentic coding is the shift from AI autocomplete to an agent that plans, edits, runs and verifies in a loop. What it is, how it differs, and how to start. - [What is an agent harness? Agent = model + harness](https://stuartleo.com/articles/what-is-an-agent-harness): An AI agent is the model plus the harness around it — the tools, memory, and the gather-act-verify loop that make it act. What a harness is, and where C² fits. - [Why AI agents get expensive (and how to fix it)](https://stuartleo.com/articles/why-ai-agents-get-expensive): Agentic tasks burn far more tokens than chat, mostly from re-sending context. Why the bill climbs, and how lean context and model routing bring it down. - [Write your first session brief](https://stuartleo.com/articles/write-your-first-session-brief): A session brief is a short note at the end of each working session: what changed, why, what's verified, what's next. How to write one and why it compounds. - [AI development methodologies compared: C², BMAD & more](https://stuartleo.com/articles/ai-development-methodologies-compared): An honest comparison of the methods for building with AI agents — native rule files, BMAD, ACE, Shape Up, AWS AI-DLC and C² — with a side-by-side table and how to choose. - [An alternative to Agile for AI-native teams](https://stuartleo.com/articles/alternative-to-agile): Agile coordinated humans at human speed. With AI agents in the loop the bottleneck moves from execution to direction, and the ceremonies become drag. - [C² vs BMAD: two ways to build with AI agents](https://stuartleo.com/articles/c2-vs-bmad): BMAD and C² both bring discipline to building with AI agents — BMAD runs personas through a heavier SDLC, C² centres on a contextbase you own that compounds. - [C² vs Shape Up: from human teams to human + AI teams](https://stuartleo.com/articles/c2-vs-shape-up): Shape Up gave product teams appetite-based betting and an escape from sprint theatre. C² keeps those instincts and adds what AI needs — a contextbase that compounds. ## Articles: essays - [What is context leadership? Leading people and agents](https://stuartleo.com/articles/what-is-context-leadership): Context leadership is writing down the plan, decisions and standards so people and AI agents can act without you. What it is, and the two methods that run it. - [The Fifteen Percent Sony Couldn't See](https://stuartleo.com/articles/the-fifteen-percent-sony-couldnt-see): Sony is killing the PlayStation disc — just 15% of sales, but the last thing securing ownership, resale, a price ceiling, and its own antitrust defence. - [IKEA Automated 47% of Its Calls — and Didn't Fire Anyone](https://stuartleo.com/articles/the-8500-ikea-didnt-fire): IKEA's chatbot resolved 47% of contacts. Instead of layoffs, it retrained 8,500 staff into design advisors — a lesson in leading people, not managing them. - [Four AI Giants, Four Doors, One Lesson in Strategy](https://stuartleo.com/articles/the-four-doors): OpenAI, Anthropic, Google and xAI aren't competing on the same axis — each claimed different real estate in the customer's mind. Porter's doors, read through the AI race. - [The $240 Million Goodbye](https://stuartleo.com/articles/the-240-million-goodbye): Graham Walker gave $240M to employees with no equity when he sold Fibrebond — and attached a five-year string he told everyone about. A gift, or an exchange? - [Bolt Killed HR. Was That an EX Move?](https://stuartleo.com/articles/bolt-killed-hr): Bolt's CEO fired his entire HR department and announced the problems disappeared. This piece isn't about whether he was right — it's about the distinction between subtraction and design, and what every operator should ask after reading that headline. - [Nike Forgot What It Was Selling](https://stuartleo.com/articles/nike-forgot-what-it-was-selling): Nike's stock hit a twelve-year low after four years of optimising how they sell while quietly letting what they sell fall behind. The Substance vs. Form tension — at scale. - [Why Toyota's Slowness Is Every Mature Business's Trap](https://stuartleo.com/articles/the-mature-business-trap): Toyota's CFO named internal slowness as the cause of three years of decline. The Mastery trap on the Leadership Curve — and how it scales to any business. - [Values as the Commons — The Test Most Leaders Get Wrong](https://stuartleo.com/articles/values-as-the-commons): Pete Hegseth led with values. The move was textbook — and reveals why AI exposes whether your team's values were ever truly common. - [AI Business Engineering: A Working Definition](https://stuartleo.com/articles/ai-business-engineering-a-working-definition): A working definition for the discipline that sits at the intersection of AI, transformation, and SME C-suite operating — and why the existing labels keep missing it.