Coding Agents · architect → spec → conductor flow
The real ALDC flow for development. Three roles that don't overlap. Three subagents orchestrated by the conductor. TDD in seven steps with HITL between phases. No-self-review as a non-negotiable rule.
Maturity levels · where are you today?
Before entering the flow, it's worth setting the bar. Most BC teams have passed through all three levels — but not all in the same order, and many get stuck at the second.
Assisted Copilot
Tab-completion. Spot questions. The dev writes, the agent helps.
Directed Copilot
Structured prompts, prompt files, skills. The dev directs, the agent executes pieces.
Coding agents
The agent orchestrates. The dev validates at gates. Spec-driven + HITL + evidence.
Block 3 is the leap from the second to the third. It's not about using a bigger model — it's about architecture.
Real ALDC flow · 3 moments, 1 workflow between them
architect DESIGNS · the workflow DETAILS · conductor EXECUTES with 3 subagents under human supervision
The 3 main roles · they don't overlap
architecture.md with ADRs and Skills Applied at the top.spec.md file.LOW vs MEDIUM-HIGH · the flow adapts to complexity
LOW complexity · fast path
For isolated changes, small evolutions, fixes with clear scope.
- Skips
al-architectand theal-spec.createworkflow - Goes directly to
al-developeror the conductor with a minimal plan - HITL reduced to a single final gate (PR)
When: <50 lines, no new tables, no external integrations.
MEDIUM-HIGH complexity · full path
For new features, integrations, changes with cross-cutting impact.
- Full cycle:
architect→spec.create→conductor - Plan approval + phase commit + PR · 3 HITL gates minimum
- Skills Evidencing mandatory in all 3 subagents
When: anything touching more than 2 objects or exposing an API.
The triage is done by the human at the start of the session, or by al-architect if in doubt. The conservative rule is to escalate: when in doubt, full path.
The conductor's 3 subagents
The conductor does not generate code. It coordinates three specialised subagents that do, each with a bounded responsibility.
al-planning
Reads the spec. Produces phased execution plan. Identifies dependencies between objects. Marks HITL gates. Emits plan.md.
al-implement
Executes one plan phase. Writes AL code. Loads relevant skills and declares them in the Phase Summary. Emits phase-N.md.
al-review
Reviews the phase the implementor just wrote. Compliance check against the contract. Skills Compliance table. Emits review in phase-N.review.md.
TDD in 7 steps · the loop the conductor executes
The loop repeats for each plan phase. At the end of each phase there is a HITL gate: the human approves or requests changes. The conductor does not advance without approval.
Skills Compliance Check · how al-review audits
When closing each phase, al-review produces a table crossing skills declared by the implementor with skills actually applied in the code. If there is a discrepancy, it is flagged.
| Declared skill | Expected pattern | Evidence in code | Status |
|---|---|---|---|
| skill-api | API page v2.0 + bound actions | /api/v2.0 · POST /incidents/{id}/Microsoft.NAV.resolve | ✓ PASS |
| skill-performance | SetLoadFields on repetitive queries | CalcFormula en flowfield, sin SetLoadFields en loops | ✗ FAIL · Major |
| skill-permissions | Permission set per new object | CEB Barista Incidents Basic + Full presentes | ✓ PASS |
| skill-events | OnBefore/OnAfter instead of direct modification | Publisher declarado, integration event tipado | ✓ PASS |
The table travels to the conductor's phase-complete.md. If there is a FAIL, the HITL gate is not passed — the human sees the detail and decides whether to accept, request a refactor, or readjust the spec.
Mini-demo · al-architect on Barista Incidents
To close the block, al-architect works from a page and a half of business context — the upcoming Block 4 practical case. Architecture only, no code. The goal is to see the real output and how it maps to skills.
Prompt to the architect
Load al-architect.
Context:
Barista Incidents is an extension for a coffee shop chain running BC.
Baristas report incidents (machine breakdown, supply shortage, customer
complaint) from a simple Card page. Incidents have severity levels, are
auto-assigned to a technician queue, and trigger notifications. Once
resolved, they feed a weekly KPI report shown on a Role Center tile.
Task: Produce {barista-incidents}.architecture.md at MEDIUM-HIGH complexity.
Include: ADRs, data model, APIs exposed, events, permissions strategy,
Skills applied at the top.
What should come out of the architect
- Skills applied at the top of the document · predictable:
skill-api,skill-events,skill-pages,skill-permissions, optionallyskill-copilotif the architect decides to include natural language assistance - ADRs numbered · "We decided X because Y, alternatives considered Z"
- Data model · Incident, Incident Severity, Incident Assignment, Incident KPI
- APIs · POST /incidents, POST /incidents/{id}/resolve (bound action), GET /incidents (query)
- Events · OnIncidentCreated, OnIncidentResolved (for other modules to hook into)
- Permissions · two permission sets (Basic for baristas, Full for technicians/managers)
Watch how the architect operates on your screen
Anyone with the workspace open can replicate in parallel. The goal is not to produce exactly the same output — it's to see how the architect loads skills on its own and how its own description makes it an invocable agent.
- Open
.github/agents/al-architect.agent.mdbefore launching. Look for the Responsibilities and Skills Evidencing sections. - Paste the full prompt into Copilot Chat.
- Watch how the output starts with
> **Skills applied**:— that line is Skills Evidencing in action. - Compare the skills the architect declares with those in our expected list.
al-spec.create + al-conductor to implement it — but that's up to you.
What this block covers
Maturity levels
Assisted Copilot · Directed Copilot · Coding agents. Where the real leap is.
ALDC flow
architect → spec.create → conductor with 3 subagents. Roles that don't overlap.
LOW vs MEDIUM-HIGH
Fast path for isolated changes · full path for anything with impact.
7-step TDD
Conductor loop with HITL at the end of each phase. No-self-review.
Skills Compliance Check
The table that audits declared skills vs those applied in code.
Mini-demo architect
Barista Incidents architecture generated live. Preamble to Block 4.