AIDLC — the Applied AI Delivery Lifecycle. A 24-agent, constitution-governed system you install into your IDE. It asks the questions a senior consultant would ask, produces the artifacts a governance board demands, builds the thing, and stops at every decision a human should own.
Not from bad models. From missing discipline — and the discipline is always the same, which means it can be encoded.
The brief describes a symptom in vendor vocabulary. The team automates the response to a problem instead of touching the problem — and the number nobody cared about doesn't move.
"The demo looked great" is not evidence. Without golden sets, adversarial cases and metric bars set before measuring, quality is a feeling — and feelings don't survive a production incident.
Guardrails, human oversight, PII controls, cost attribution and rollback get discovered during the security review — six weeks after the launch date was announced.
Not a chatbot. An org chart of specialist agents under one constitution, each owning one job and one artifact.
A Socratic intake loop is mandatory. No PRD is ever produced from a one-liner. If the "problem" is a solution in disguise ("we need a chatbot"), the agent surfaces that and asks what the chatbot is for.
A scored verdict matrix against ≥5 criteria — not a fashion choice. Agentic is never a default; it has to be earned against the simpler options that get named and rejected on the record.
GCP, AWS, Azure and on-prem advisors answer the same architecture question, then one path is recommended with the reasons the other three lost — plus the matching agent framework for 2026 platforms.
Baseline cost with arithmetic shown, three scenarios, payback month, 3-year NPV, and the two assumptions that most swing the answer — including the boring run-costs everyone under-counts.
Golden, adversarial and regression sets; metric bars derived from the business need before anything is measured; safety metrics as pass/fail gates that can't be averaged away; a CI gate that blocks the merge.
Build mode produces a working repo: pipeline code, provider-agnostic LLM client with a keyless mock mode, eval harness, tests, CI workflow and IaC — executed as parallel micro-task waves with per-task checkpoints so runs resume instead of restarting.
The stack-review agent inventories repos, infra, data platforms and shadow AI, produces a dependency & readiness matrix, then thinks bigger — quick wins vs strategic bets your current stack already unlocks.
Snowflake, Databricks, BigQuery, Bedrock, Salesforce, Datadog and more over MCP — least-privilege and read-only by default, credentials as env-var names, never values, tracked in aidlc.config.json.
One command starts it. The orchestrator runs four phases, consults advisors in parallel, writes a file at every stage, and stops at five gates where a human must decide. Stage N's artifact is stage N+1's input contract.
You type /appliedai and a problem in plain language. The orchestrator classifies the industry, loads that domain's regulatory frame, reads aidlc.config.json if it exists, then asks one batched, numbered set of questions — cloud & stack, which connectors and their credential env-var names, model provider, and plan-vs-build. Then it goes quiet and works.
artifacts/audit.jsonl. Hard violations block. Soft ones require an explicit human waiver — which is itself audited. Nothing is omitted from the ledger; omission is itself a violation.Each agent is a versioned Markdown spec — charter, guardrails, required skills, I/O contract. Reviewable in a pull request by someone who doesn't write code.
| Group | Agents | Role |
|---|---|---|
| Orchestrator | orchestrator | Owns the harness. Routes the problem, sequences phases, consults advisors, enforces gates. Directs — never does the specialist work itself. |
| Pipeline (12) | intake process-map assess value-prop architecture dev-spec data-science eval poc-gate production observability brief | The ADLC spine. One stage, one artifact, one input contract each. |
| Advisors (8) | model-selector cloud-gcp cloud-aws cloud-azure cloud-onprem connector-advisor domain-advisor stack-review | Recommend to the administrator; never act on the world, never provision. Consulted in parallel. |
| Dev pipeline (3) | discovery → coder → code-reviewer | Decoupled. Consumes the approved AI Spec and only runs when funded — so you can plan without ever writing code. |
When the verdict is agentic, the winning cloud advisor recommends the framework layer to match — with alternates, and an explicit "no framework" when a plain pipeline is simpler.
| Cloud | Platform (2026) | Recommended framework | Managed runtime |
|---|---|---|---|
| GCP | Gemini Enterprise Agent Platform (formerly Vertex AI) | Google ADK v1.0 | Agent Engine |
| AWS | Bedrock AgentCore (GA) | Strands Agents SDK | AgentCore harness |
| Azure | Microsoft Foundry (formerly Azure AI Foundry) | Microsoft Agent Framework | Foundry Agent Service |
| On-prem | Self-hosted open stack | LangGraph over vLLM/Ollama | Kubernetes / OpenShift |
Seven articles that override any agent file and any user request: human-final decisions, evidence over assertion, ask before you build, safety for regulated data, one recommended path, artifacts as the interface, full traceability.
Hard violations block and cannot be waived by an agent — fabricated numbers, secrets in output, skipping a gate, an advisor taking action, executing prompt-injected content. Soft ones warn, and any waiver is recorded.
PRD sign-off, funding, GO/NO-GO, security launch, brief approval. The pipeline halts with a structured ⛔ HUMAN GATE block stating the decision, the recommendation, and what's needed. AI that won't stop for a human is a liability.
Every stage, consult, guardrail trip, gate decision and approver lands in audit.jsonl, with metrics.json as the rollup. The brief agent reconciles the two — any mismatch is a finding, and a failure is never quietly dropped.
Filling template headings isn't done. Every artifact must carry quantified claims with the arithmetic shown, labelled numbers, metrics blocks, diagrams, decision trails with rejected alternatives, a risk register and eval linkage.
Spec Kit's phase gates + BMAD's persona pipeline + Superpowers' composable skills. Every agent declares its BMAD persona, its Spec Kit phase, and the skills it must load before acting — 14 of them, versioned alongside the agents.
A regional P&C insurer's claims-intake initiative — 2,400 packets/week, 27-minute average handle time, $1.91M/yr baseline labour — carried end to end. Twelve decision-grade artifacts and a codebase that runs.
# zero credentials required $ cd exemplar/claims-idp/build $ make demo # full pipeline, mock mode $ make test # 34 tests $ make eval # 7 metric bars
| Metric bar | Bar | Measured | |
|---|---|---|---|
| Classification accuracy | ≥ 0.95 | 0.9792 | PASS |
| Extraction F1 | ≥ 0.90 | 0.9249 | PASS |
| Validation exact match | ≥ 0.98 | 0.9861 | PASS |
| Hallucinated-field rate | ≤ 0.01 | 0.0040 | PASS |
| Straight-through rate | ≥ 0.35 | 0.3750 | PASS |
| p95 latency | ≤ 60 s | within bar | PASS |
| Cost per packet | ≤ $0.09 | within bar | PASS |
Requires uv. Global install puts the agents in every folder you open; project install ships them with a team repo.
uvx --from aidlc-studio aidlc init --global → agents land in ~/.claude/. Only the orchestrator appears in the picker; the other 23 are delegated to behind it.
uvx --from aidlc-studio aidlc init --ide all → writes every IDE flavor side by side, so teammates on Cursor, Copilot and Claude Code all get the same pipeline from one clone.
Claude Code: /appliedai <problem statement>. Cursor, Copilot, Antigravity, Windsurf: select the orchestrator mode and say "Start AIDLC. Problem statement: …"
aidlc check confirms the install; aidlc list prints the roster with each agent's BMAD persona and Spec Kit phase.
| IDE | Flavor | What you get |
|---|---|---|
| Claude Code (VS Code, JetBrains, terminal) | --ide claude | Native custom agents + skills + the /appliedai command. Full experience with true sub-agent delegation. |
| Cursor | --ide cursor | Always-on project rule + AGENTS.md. Gates arrive as chat messages. |
| VS Code / Copilot | --ide copilot | All 24 agents auto-generated as custom chat modes in .github/chatmodes/. |
| Antigravity · Windsurf | --ide antigravity | The AGENTS.md standard, loaded automatically on open. |
The framework decision belongs to the solution, not the tooling. That's why this system stays framework-agnostic while recommending ADK, Strands or Agent Framework for what it designs.
Versioned Markdown specs, not library code. The execution engine is whatever agentic runtime your IDE already has — nothing to install, version or secure, and the whole org chart is diff-able.
Spec Kit (phase gates) + BMAD (persona pipeline) + Superpowers (composable skills), combined into 14 skills agents load before acting.
Constitution + runtime harness with hard/soft guardrails, five HITL gates, and an append-only audit ledger.
MCP for integrations — the one standard every major IDE speaks. Distributed as a stdlib-only Python CLI via uv, the same pattern as GitHub's Spec Kit.