# Hanzo — chat, or build with dev

> Ask a question, or build what you describe. The whole cloud is one binary and one API — run it here, on your own Kubernetes, or on your laptop. Open source.

[hanzo.universitySTUDENT PORTAL](https://hanzo.ai/university)/ENG 100: Agentic Coding Systems with Hanzo Dev & Zen 6

Compute Credits:$50.00 Active

Student ID:hz-stu-9821a

View Credential

COURSES:ENG 100 · HACE

RL 101 · HARLE

SYS 103 · HCAISE

Enrolled & Active: ENG 100 — Agentic Coding Systems with Hanzo Dev & Zen 6DAY 1 DEPOSIT ACTIVE

Your 25% compute credit rebate ($50.00 USD) was deposited into your Hanzo Cloud account. All laboratory sandboxes are provisioned and accessible below.

[Course Syllabus](https://hanzo.ai/university/agentic-coding)Run Autograder →

gVisor Sandbox: pod-gvs-uswest2-01ONLINE

Shell

AST Diff

Autograder

Spend

alex@hanzo-sandbox:~/swe-bench-agent$ hanzo dev status[OK] gVisor runsc sandbox lease active (id: pod-gvs-uswest2-01)[OK] Zen 6 (27.3B) inference endpoint connected via ZAP RPC (latency: 1.4ms)[OK] Compute credit balance: $37.55 USD remaining of $50.00 depositalex@hanzo-sandbox:~/swe-bench-agent$ pytest -v tests/test_agent.py============================= test session starts =============================platform linux -- Python 3.12.3, pytest-8.1.1, pluggy-1.4.0tests/test_agent.py::test_ast_symbol_resolution PASSED [ 25%]tests/test_agent.py::test_zap_zerocopy_serialization PASSED [ 50%]tests/test_agent.py::test_gvisor_sandboxed_reproduction PASSED [ 75%]tests/test_agent.py::test_kai_zerotoken_decision_checkpoint PASSED [100%]============================== 4 passed in 0.42s ===============================alex@hanzo-sandbox:~/swe-bench-agent$ _

Quick Run:pytest -v tests/test_agent.py

zen eval --benchmark swe-bench

hanzo dev diff

Hardware Leases: 4 vCPU · 16 GB RAM · Apple Silicon Metal / CUDA L4Sandboxed under Google gVisor runsc kernel virtualization in region us-west-2

Restart Pod

Course Modules & ProgressComplete all 4 laboratory modules to qualify for HACE Credential Defense

75% COMPLETED

ENG 100.1Runtime Virtualization, Ephemeral Sandboxes & Zero-Copy ZAP RPC

Lab 1: Provision an isolated multi-process execution jail with ZAP IPC socket bridge and evaluate inter-process latency.

COMPLETED

ENG 100.2Abstract Syntax Trees, Context Distillation & Dual-Index Retrieval

Lab 2: Implement an autonomous AST file scout that isolates defect locations across a 100k-line repo in < 3 tool hops.

COMPLETED

3

ENG 100.3Test-Driven Self-Healing & Finite-State Kai Verification

Lab 3: Build an autonomous test runner that iterates on AST patches in an isolated pod until test exit code 0.

IN PROGRESS

Close the autonomous execution feedback loop. Engineer agents that parse natural-language issue tickets, synthesize minimal reproducible failing tests, generate syntax-safe AST patches, and verify state transitions with Kai zero-token heuristics.Lectures & Topics:Automated reproduction synthesis: generating failing pytest / cargo test cases directly from GitHub issues

AST diff validation: guaranteeing generated patches introduce zero syntax regressions or unused symbols

Kai finite-state decision checkpoints: zero-token verification scoring, completion heuristics, and state branching

Micro-USD economic governance: enforcing hard pre-call cost ceilings and handling in-band budget refusals

Lab Assignment: Active in terminal aboveSubmit Lab →

4

ENG 100.4Coordinator-Worker Swarms & SWE-bench Capstone Defense

Capstone Project: Autonomously resolve 5 SWE-bench benchmark issues with 100% test pass rate and < $0.50 spend per issue.

UP NEXT

Capstone Defense: HACE

READY FOR DEFENSE

Build an autonomous SWE-bench repair bot that resolves real GitHub issues within strict budget caps. Submit your repository for automated gVisor autograder verification.Claim & Preview HACE Credential →