ArticlesComparison

AI development methodologies compared: C², BMAD, Shape Up, AI-DLC and more

A practitioner's honest map of the methods for building with AI agents — and why a contextbase that compounds beats context you reload.

Stuart LeoJune 1, 20267 min read

The real differentiator in building with AI agents in 2026 isn't the model — everyone has the same models. It's how systematically you turn what the agent learns into something it keeps. A lot of good people are converging on that, which is why there are now several methods worth knowing. Here's an honest map — written by someone who built one of them and ships production software with it daily — and a side-by-side to help you choose.

The contenders

Native rule files (CLAUDE.md, AGENTS.md, .cursorrules)

Where everyone starts, and where most people stall. A single markdown file the agent reads first. Strength: zero setup, universal, agent-native. Limit: one file is not a method. There's no structure for briefs, no knowledge that accumulates, nothing that survives past a small project or a second person. Every method below is, in effect, the structure these files are missing.

BMAD (Breakthrough Method for Agile AI-Driven Development)

A heavy, orchestrated SDLC built around specialised AI personas — PM, Architect, Dev, QA — running a phased pipeline. Strength: opinionated and complete if you want a role-based workflow handed to you. Limit: it's a framework you serve. You adopt its personas, its phases, its ceremony — and the context lives inside that pipeline rather than compounding into an asset you own. Powerful, prescriptive, and heavy for anything smaller than a team that wants exactly that.

HumanLayer's ACE (Advanced Context Engineering)

Not a method — a context-window discipline. Research → plan → implement, with intentional summarisation to keep the working set lean. Strength: the best answer going to "what do I do when even my curated context overflows the window." Limit: it manages the window, not the project. No contextbase, no briefs, no knowledge layer — it's a technique that belongs inside a method, not in place of one. Use it within C², not instead of it.

Matt Pocock's workflow

A sharp personal pipeline: idea → PRD → issues → autonomous execution with TDD, then human QA. Strength: concrete, opinionated, easy to copy. Limit: it's personal. No team model, no compounding knowledge, nothing that spans more than one developer or more than one app. A great solo loop that stops where a project gets bigger than one head.

Packmind (ContextOps)

Enterprise governance for context — standards, skills, and commands distributed and controlled across many repos and agents. Strength: the right answer if your problem is policing context centrally across a large org. Limit: governance-first, not build-first. It's heavy machinery aimed at platform teams, not the person actually building — and overkill for everyone who isn't running one.

Shape Up (Basecamp)

The pre-AI ancestor, and still the clearest thinking on betting, appetite, and scope. Strength: unmatched on deciding what to build and how much to spend on it. Limit: it was designed for humans directing humans. No contextbase, no router, no agent-execution contract. Keep its betting layer — it has nothing to say about how the work actually gets built by an agent.

AWS AI-DLC (AI-Driven Development Lifecycle)

The closest structural peer, and the sharpest contrast — a hierarchical, agent-agnostic pipeline with human approval at phase gates. Strength: structured, enterprise-credible, genuinely AI-native. Limit: two telling choices. It casts the human as an approver at gates — the pipeline runs, you sign off — rather than a pilot directing throughout. And it treats context as delivery: load the right rules, run the phase, move on. That context is consumed, not accumulated. Which is exactly where C² goes the other way.

C² (the C² Method)

One idea, carried all the way through: every project runs two systems — a codebase (what runs) and a contextbase (what guides) — and the contextbase is a first-class, version-controlled artifact the agent reads before it acts.

What makes it different is that context is an investment that compounds, not delivery you reload. Every session, the briefs, gotchas and decisions get written down and committed, so the next session — and the next agent, and the next person — start from everything learned so far. After fifty sessions the contextbase is denser in real decisions than the code. Nobody else here treats context as an asset that accrues; they reload it, or they have no model for it at all.

And it's the one method here with genuine range. It's just disciplined markdown in git, so it fits a solo founder shipping a single product and a team running many apps across multiple locations — the same shape at both ends. Every app carries its own contextbase; every contributor, human or agent, reads the same source of truth; no central server, no per-seat tool. Most of the others are built for one end of that spectrum. C² holds both.

The honest cost: it asks for discipline every session — you write the brief, you capture what was learned. That's the price of compounding, and it's a real ask. C² is a method and templates, not a framework that does it for you — which is the point. Nothing to lock into, nothing to rip out when a better agent ships, and the context you build is yours.

Side by side

MethodWeightHuman roleContext modelBest for
Native rule filesMinimalA single fileThe baseline you outgrow fast
LightPilot (directs throughout)Contextbase — invest & compoundSolo founders → teams running many apps across locations
BMADHeavyOrchestrated personasPersona pipeline (doesn't compound)Teams wanting a prescriptive role-based SDLC
ACEAdd-onIn-session compactionA technique to use inside a method
Pocock's workflowLightDirectorPRD → issuesA single developer, a single app
PackmindHeavyGovernedCentral ContextOpsLarge orgs policing context centrally
Shape UpMediumShaperNone (pre-AI)Deciding what to build; pair with an AI method
AWS AI-DLCHeavyApprover at gatesDelivery (doesn't compound)Enterprises wanting phase gates

How to choose

  • Solo founder, or a team across several apps and locations? C². It's the only one here that fits both without changing shape — and the only one where your context compounds instead of evaporating.
  • Want a prescriptive, role-based pipeline handed to you? BMAD, if you're happy to serve the framework.
  • Large org whose problem is governing context centrally? Packmind.
  • One developer wanting a personal loop to copy? Pocock's.
  • Fighting the context window? ACE, as a technique inside whatever method you run.
  • Deciding what's worth building? Keep Shape Up's betting model on top, with an AI-native method underneath.

These aren't all mutually exclusive — ACE and Shape Up are layers, not rivals. But on the core question of how a project remembers what it learns, most of the field either has no answer or reloads context and throws it away. C² treats it as the asset it is. That's the whole bet: stop building velocity you can't keep.

If the contextbase idea resonates, read the C² method, see how it compares to Agile, or go deeper on C² vs BMAD and C² vs Shape Up.

FAQ

Which AI development methodology is best?
There's no single best, but C² is the most broadly applicable: it fits a solo founder shipping one product and a team running many apps across locations, and it's the only one where context compounds across sessions instead of being reloaded each time. BMAD suits teams that want a prescriptive role-based pipeline; Packmind suits large orgs policing context centrally; ACE is a context-window technique, not a full method, and pairs with any of them.
Does C² work for larger teams, or just solo founders?
Both — and that range is the point. C² is just version-controlled markdown in git, so it scales from a solo founder on one product to a team running multiple apps across multiple locations without changing shape. Every app carries its own contextbase; every contributor, human or agent, reads the same source of truth. Most other methods are built for one end of that spectrum; C² holds both.
What is the difference between C² and BMAD?
BMAD is a heavy, orchestrated SDLC built around specialised AI personas — you adopt its pipeline. C² is lighter and agent-agnostic, centred on a version-controlled contextbase the agent reads before acting and that compounds over time. BMAD gives you a workflow to serve; C² gives you an asset you own.
Can these AI methodologies be combined?
Yes — the strongest setups compose. C² for the contextbase, ACE's compaction for the context window, and Shape Up's betting model for deciding what to build. ACE and Shape Up are layers, not rivals.
Is Shape Up still relevant for AI development?
Yes, for the betting layer — deciding what's worth building and how much appetite it gets. It has no contextbase and no agent-execution model, so for building with AI agents you pair it with an AI-native method like C² underneath.