← Evidence Lab
PILOT · DG-BM-001

DeployGuard incident CRUD

First external-project pilot of FORGE on a real application task, run on 10 September 2026.

Question

Does a FORGE-assisted AI coding workflow show less repository-discovery noise and less implementation rework while preserving successful build, type-check and automated-test outcomes?

Task

Add PostgreSQL-backed incident management to DeployGuard: create, list, get, update and delete endpoints; title and description; severity levels; incident status; validation; tests; and preservation of the existing health endpoint.

Observed results

MetricPlain AI controlFORGE-assistedObservation
Unique files inspected7528.6% fewer
Clearly unnecessary files inspected30 establishedLower discovery noise
Failed commandsSeveral0 during implementationCleaner assisted run
Retries / reworkSeveral0Cleaner assisted run
Automated tests3 / 3 passed3 / 3 passedSame tested outcome
BuildPassedPassedSame
Type-checkPassedPassedSame
Feature completionPartial*Yes at implementation level*Verification scopes differed
Provider tokens / costNot availableNot availableNo cost claim possible

*The control attempted live Docker verification and encountered unresolved connection resets/timeouts. Docker runtime verification was not rerun on the FORGE branch, so completion labels are not directly comparable.

3prepare events
263 msaverage prepare duration
695 / 2748characters selected / considered
514estimated context tokens avoided
74.7%estimated context reduction
15deterministic steps completed

FORGE telemetry

The assisted run reported 3 preparation events, 0 cache hits, 263 ms average preparation duration, 695 of 2,748 context characters selected, 514 estimated context tokens avoided, 74.7% estimated context reduction, and 15 deterministic steps completed.

Important: FORGE token values use an approximate engineering heuristic. They are not provider billing data and do not mean the run used 74.7% fewer paid credits.

Why this is labelled a pilot

DG-BM-001 is therefore evidence that the measurement workflow works and a promising signal — not proof of a universal performance or cost reduction.

What we learned about FORGE itself

The pilot also found a classifier weakness: a new incident CRUD capability was classified as a bug rather than a feature. External testing is being used to turn these observations into product improvements rather than hiding them.

Next benchmark

Future runs will use identical application starting states and equal acceptance criteria across both branches. Planned categories include authentication/security, database changes, CI/CD, and Kubernetes/infrastructure.

Install FORGEBack to Evidence Lab