LuxePlatforms
Rather just talk?(816) 477-6802hello@luxeplatforms.comKansas City · Building nationwide
Developer Tooling · AI Agent16 / 16

A reproducible, testable system-building agent that applies repo changes via hunk-level diffs

An autonomous coding agent you can actually test.

A deterministic system-building agent that takes a YAML mission, produces a multi-phase plan, and scaffolds and applies repository changes via hunk-level unified-diff patching, with full dry-run previews and a mock model for offline runs.

Prototype

A look at the interface.

Representative UI — abstracted, never a client's real data.
🔒chat.workspace.dev
New chat
Recent
Quarterly report draft
Refactor billing logic
Summarize call notes
Schema migration plan
Workspace · Pro
AssistantonlineOpus 4.8 ⌄
Pull last quarter's numbers from the PDF and chart revenue vs target.
analyze_document(Q4-report.pdf)done
Revenue
$128k
Target
$110k
Δ
+16%
Revenue came in 16% above target. The lift is driven by Q4 enterprise renewals — here's the breakdown:
  • Enterprise +$22k (renewals)
  • Self-serve flat MoM
[1] Q4-report.pdf[2] forecast.xlsx
Ask anything…Opus 4.8
AI / conversational · representative UI
Reliable
Same result every time
Safe
Previews every change first
Offline
Runs with no internet needed
Role
Solo, agent design
Year
2026
Status
Prototype
Category
Developer Tooling · AI Agent
Built with
  • Python
  • PyYAML
  • pytest
  • GitHub Actions
(01) The Challenge

Autonomous coding agents are usually nondeterministic and hard to trust. Vacant Lot makes the build loop reproducible and inspectable: every change is a parseable diff hunk, applied atomically, so plans can be previewed and regression-tested before anything touches disk.

(02) The Approach

How it
works

A YAML mission produces a multi-phase plan. Every change is applied as a parseable unified-diff hunk with atomic writes and rejection files, not full-file overwrites, so plans can be previewed and regression-tested before touching disk. A deterministic mock model adapter lets the whole loop run with no remote model, validated by a CI smoke test on every push.

What I built

(03) Inside the build
01

Multi-phase planner

Generates plan, scaffold, implement, test, and refine phases from a mission file, and can author per-feature plans with spec, implementation, and test steps.

02

Hunk-level diff applier

Parses and applies unified diffs hunk-by-hunk with atomic writes and rejection files, exposing pretty and machine-readable dry-run previews.

03

Offline-capable

A deterministic mock model adapter lets the whole loop run with no remote model configured, validated by a CI smoke test on every push.

(04) Highlights

The
receipts

  • Fully deterministic agent loop: dry-runs are reproducible and unit-tested
  • Hunk-level patching with atomic writes, not full-file overwrites
  • Runs offline via a deterministic mock adapter
  • Bundled tool layer for filesystem, git, http, and shell
← Previous
Automated Video-Clipping Pipeline
Next →
AI Operations Platform for Millwork Shops