Products

Auto-Dev Universe

Agent-driven development with responsibility gates at every phase. Code is generated, reviewed, tested, and merged through a governed pipeline — not a magic wand.

DEVELOPMENT CYCLE

Not a Code Generator. A Development System.

Even with ambiguous instructions, auto-dev reaches the completion line.

Process

Define Completion Line

Not perfect spec, but minimum success criteria that can be verified

Acceptance: verifiable

Small Iterations

Build, run, verify, fix — always recoverable, never destructive

Max cycles: 3

Auto-Complete

Continues until acceptance criteria met or stops with full context

False-done: 0%
Iteration Cycle
Cycle1/3
Build
Run
Verify
Fix
Build: Patch generation
Pass & Complete
or
Stop + Context
Why It Completes

Executor AI

Builds & Runs

separated

Judge AI

Verifies & Approves

No RunawayExecutor & Judge are structurally separate
No Goal DriftCompletion criteria locked at ticket creation
No False DoneOnly verifiable acceptance counts
Ideal for:Code improvementsTest additionsFeature buildsRefactoringPrototype drafts

Ambiguity in. Verified completion out.

AUTO-DEV UNIVERSE — Section 01 — Development Pipeline

From Spec to Ship — With Gates at Every Phase.

Speed is not the goal. Structured evolution that never breaks is.

Input Packs
Repo Pack

Code, deps, build

Spec Pack

Issue, PRD, ADR

Policy Pack

Gate YAML, rules

Quality Pack

Tests, SLO, lint

Work DAGtopological order
Plan→Design→Implement→Test→QA→Docs
Responsibility DAGfail-closed
Scope Gate→Risk Gate→Quality Gate→Release Gate
Action Gateway
git pushPR createDeploySecrets

require_ticket: true · require_trace: true

Trace Store
Event Sourcing→Immutable Records→Audit Replay

No trace, no side effects. Gaps are impossibilities.

Agents propose. Gates authorize. Gateway executes. Trace proves.

Universe Builder

Configure Your Development Universe.

5 agents, each with sub-agents. Risk surfaces at every step.

BuilderRepo NavPatch CraftBuild Run
TestTest GenFailure LocRepro
ReviewerDiff CheckImpact EvalInvariant
SecurityDep ScanAuth ReviewSecret Det
ReleaseCanary PlanRollbackStage
Dev Chief
01
Ticket
Issue accepted
02
Scope
Blast radius estimated
03
Plan
DAG assembled
04
Execute
Builder + sub-agents run
05
Test
Coverage verified
06
Review
Schema + invariants checked
07
Security
Vuln scan + auth review
08
Release
Canary plan + deploy

Five agents. Fifteen sub-agents. Every risk scored before execution.

AUTO-DEV UNIVERSE — WORK DAG

Judgment Controlled, Execution Parallelized

Three zones: judgment, execution, verification.

Zone A

ImplementDONE
TestRUNNING
AnalysisREADY
SecurityBLOCKED
DocsBLOCKED

Zone B

ImplementDONE
TestDONE
AnalysisRUNNING
SecurityRUNNING
DocsREADY

Zone C

ImplementRUNNING
TestBLOCKED
AnalysisBLOCKED
SecurityBLOCKED
DocsBLOCKED

Formal Definition

Executable(n) ⟸ ∀ d ∈ deps(n) : status(d) = DONE
DAGzone = (N, E)  where  E ⊆ N × N  is acyclic

Parallel by default

Ready nodes across zones execute simultaneously

No cross-zone side effects

Zones are isolated; coupling only through Decision DAG

Deterministic replay

Same inputs, same execution order, same results

Parallelism is not a performance hack. It is a structural guarantee.

AUTO-DEV UNIVERSE — AGENT CAPABILITIES

5 Agents. Clear Boundaries. No Overlap.

Each agent owns a phase of the development lifecycle.

Builder

Implementation-focused execution

Repo NavigationPatch CraftingBuild & TestTool Discipline
Test

Test generation and failure isolation

Test GenFailure LocalizationRepro StepsCoverage Analysis
Reviewer

Design integrity and diff quality

Schema DisciplineArchitecture InvariantsImpact AnalysisEvidence Production
Security

Vulnerability and permission audit

Dependency ScanAuth ReviewSecret DetectionThreat Model
Release

Deploy planning and rollback design

Canary PlanFeature FlagsRollback DesignStage Deploy
AExecution
BStructure Preservation
CRisk & Responsibility
DAudit Readiness

Risk Scoring Function

risk(v) = w1·financial + w2·auth + w3·PII + w4·blast_radius − w5·rollback

Risk determines gate escalation thresholds. Higher risk requires stronger evidence and human approval.

Capability is not intelligence. It is accountable execution within governed boundaries.

Parallel Development, Gated Merge

Agents work simultaneously. Merge requires gate approval.

Each agent spawns specialized sub-agents. Risk scores aggregate upward. Quality loops never stop.

Builder
Repo Nav
Patch Craft
Build Run
Patch Set
blast_radius: 3
Test
Test Gen
Failure Loc
Repro Steps
Coverage Report
coverage_gap: 0
Reviewer
Diff Check
Impact Eval
Invariant
Review Verdict
schema_drift: 1
Security
Dep Scan
Auth Review
Secret Det
Security Report
vuln_surface: 2
Release Gate Convergence
risk(v) = w1·blast + w2·vuln + w3·drift ≤ threshold
Verified Release Package
Built, tested, reviewed, scanned — with canary plan
4
Parallel Agents
12
Sub-Agents Active
3
Risk Score (max)
0
Gate Violations

Parallel execution. Aggregated risk. Gate-enforced release.

AUTO-DEV UNIVERSE — QUALITY GATES

4 Gates Before Any Code Ships.

Gates are not monitoring. They are execution boundaries. If the gate does not open, the action cannot happen.

Agent→Scope→Risk→Quality→Release→Ticket→Gateway→Trace
AgentAction GatewayDirect execution: impossible
Scope Gate

Trigger: files_changed > 25, sensitive paths touched

Action: BLOCK or ESCALATE

Risk Gate

Trigger: risk >= 3

Action: REQUIRE_HUMAN_APPROVAL

Quality Gate

Trigger: Evidence incomplete (tests, typecheck, lint, security)

Action: BLOCK

Release Gate

Trigger: Missing canary_plan or rollback_plan

Action: BLOCK_IF_MISSING

Gate Policy YAML

principles:
  fail_closed: true
  no_ticket_no_side_effects: true
  no_trace_no_side_effects: true

action_gateway:
  require_ticket: true
  require_trace_prewrite: true
  verify_signature: true

No Ticket, No Side Effects

If the gate did not issue a ticket, the action cannot execute. Enforcement by construction.

No Trace, No Side Effects

If trace cannot be written synchronously, execution is denied. Gaps are not bugs, they are impossibilities.

Enforcement is not detection. It is structural impossibility.

AUTO-DEV UNIVERSE — CONVERGENCE

From Generation to Deployment — One Pipeline.

4 state variables track every code artifact through the pipeline.

G0→Evaluate→Propose→Approve→G1→Evaluate→Propose→Approve→G2
Self-rewrite within same generation: FORBIDDEN

State Variables

q_k
Quality

Tests, static analysis, SLO compliance

e_k
Uncertainty

Unverified scope, low repro rate

r_k
Risk

Change area, permissions, data impact

d_k
Diff Size

Lines, files, dependency reach

Convergence Criterion

Converged ⟸ ∀ k ∈ [t−N, t] :
 qk ≥ qtarget  ∧  ek ≤ etarget
 ∧  critical_alerts = 0
 ∧  replay_match = 100%
 ∧  dk ≤ dthreshold

Scope Bound

d_k <= d_max

Auto-split if exceeded

Risk Escalation

r_k >= r_human

BLOCKED until approval

Evidence Required

EvidenceComplete(v)

No downstream without it

Convergence Meters

Quality↑ 85%
Uncertainty↓ 20%
Diff Size↓ 15%
Replay Match↑ 100%

Divergence Detection

Same failure repeated M times triggers spec-request or human escalation. Never retries blindly.

Auto-Dev is not about building faster. It is about converging with certainty.